Authors: Nilay Yilmaz, Maitreya Patel, Yiran Lawrence Luo, Tejas Gokhale, Chitta Baral, Suren Jayasuriya, Yezhou Yang
Abstract: Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information. Despite their exceptional performance on visual understanding benchmarks, measuring their ability to reason abstractly across multiple images remains a significant challenge. To address this, we introduce VOILA, a large-scale, open-ended, dynamic benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning. VOILA employs an analogical mapping approach in the visual domain, requiring models to generate an image that completes an analogy between two given image pairs, reference and application, without relying on predefined choices. Our experiments demonstrate that the analogical reasoning tasks in VOILA present a challenge to MLLMs. Through multi-step analysis, we reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning. Notably, we observe that performance improves when following a multi-step strategy of least-to-most prompting. Comprehensive evaluations on open-source models and GPT-4o show that on text-based answers, the best accuracy for challenging scenarios is 13% (LLaMa 3.2) and even for simpler tasks is only 29% (GPT-4o), while human performance is significantly higher at 70% across both difficulty levels.
Authors: Shuaiang Rong, Lina He, Salih Furkan Atici, Ahmet Enis Cetin
Abstract: Power line infrastructure is a key component of the power system, and it is rapidly expanding to meet growing energy demands. Vegetation encroachment is a significant threat to the safe operation of power lines, requiring reliable and timely management to enhance the resilience and reliability of the power network. Integrating smart grid technology, especially Unmanned Aerial Vehicles (UAVs), provides substantial potential to revolutionize the management of extensive power line networks with advanced imaging techniques. However, processing the vast quantity of images captured by UAV patrols remains a significant challenge. This paper introduces an intelligent real-time monitoring framework for detecting power lines and adjacent vegetation. It is developed based on the deep-learning Convolutional Neural Network (CNN), You Only Look Once (YOLO), renowned for its high-speed object detection capabilities. Unlike existing deep learning-based methods, this framework enhances accuracy by integrating YOLOv8 with directional filters. They can extract directional features and textures of power lines and their vicinity, generating Oriented Bounding Boxes (OBB) for more precise localization. Additionally, a post-processing algorithm is developed to create a vegetation encroachment metric for power lines, allowing for a quantitative assessment of the surrounding vegetation distribution. The effectiveness of the proposed framework is demonstrated using a widely used power line dataset.
Authors: Zhaoyi Joey Hou, Adriana Kovashka, Xiang Lorraine Li
Abstract: Evaluating creativity is challenging, even for humans, not only because of its subjectivity but also because it involves complex cognitive processes. Inspired by work in marketing, we attempt to break down visual advertisement creativity into atypicality and originality. With fine-grained human annotations on these dimensions, we propose a suit of tasks specifically for such a subjective problem. We also evaluate the alignment between state-of-the-art (SoTA) vision language models (VLM) and humans on our proposed benchmark, demonstrating both the promises and challenges of using VLMs for automatic creativity assessment.
Authors: Jiamin Luo, Jingjing Wang, Junxiao Ma, Yujie Jin, Shoushan Li, Guodong Zhou
Abstract: Prior studies on Visual Sentiment Understanding (VSU) primarily rely on the explicit scene information (e.g., facial expression) to judge visual sentiments, which largely ignore implicit scene information (e.g., human action, objection relation and visual background), while such information is critical for precisely discovering visual sentiments. Motivated by this, this paper proposes a new Omni-scene driven visual Sentiment Identifying, Locating and Attributing in videos (Omni-SILA) task, aiming to interactively and precisely identify, locate and attribute visual sentiments through both explicit and implicit scene information. Furthermore, this paper believes that this Omni-SILA task faces two key challenges: modeling scene and highlighting implicit scene beyond explicit. To this end, this paper proposes an Implicit-enhanced Causal MoE (ICM) approach for addressing the Omni-SILA task. Specifically, a Scene-Balanced MoE (SBM) and an Implicit-Enhanced Causal (IEC) blocks are tailored to model scene information and highlight the implicit scene information beyond explicit, respectively. Extensive experimental results on our constructed explicit and implicit Omni-SILA datasets demonstrate the great advantage of the proposed ICM approach over advanced Video-LLMs.
Authors: Quan Quan, Dun Dai
Abstract: 6D pose estimation is a central problem in robot vision. Compared with pose estimation based on point correspondences or its robust versions, correspondence-free methods are often more flexible. However, existing correspondence-free methods often rely on feature representation alignment or end-to-end regression. For such a purpose, a new correspondence-free pose estimation method and its practical algorithms are proposed, whose key idea is the elimination of unknowns by process of addition to separate the pose estimation from correspondence. By taking the considered point sets as patterns, feature functions used to describe these patterns are introduced to establish a sufficient number of equations for optimization. The proposed method is applicable to nonlinear transformations such as perspective projection and can cover various pose estimations from 3D-to-3D points, 3D-to-2D points, and 2D-to-2D points. Experimental results on both simulation and actual data are presented to demonstrate the effectiveness of the proposed method.
Authors: Yan Su, Qiulin Wu, Weizhen Li, Chengchang Pan, Honggang Qi
Abstract: The training of deep learning models relies on a large amount of labeled data. However, the high cost of medical labeling seriously hinders the development of deep learning in the medical field. Our study proposes a general disease diagnosis approach based on Zero-Shot Learning. The Siamese neural network is used to find similar diseases for the target diseases, and the U-Net segmentation model is used to accurately segment the key lesions of the disease. Finally, based on the ResNet-Agglomerative clustering algorithm, a clustering model is trained on a large number of sample data of similar diseases to obtain a approximate diagnosis of the target disease. Zero-Shot Learning of the target disease is then successfully achieved. To evaluate the validity of the model, we validated our method on a dataset of ophthalmic diseases in CFP modality. The external dataset was used to test its performance, and the accuracy=0.8395, precision=0.8094, recall=0.8463, F1 Score=0.8274, AUC=0.9226, which exceeded the indexes of most Few-Shot Learning and One-Shot Learning models. It proves that our method has great potential and reference value in the medical field, where annotation data is usually scarce and expensive to obtain.
Authors: Sarmistha Das, Basha Mujavarsheik, R E Zera Lyngkhoi, Sriparna Saha, Alka Maurya
Abstract: In today's competitive marketing landscape, effective complaint management is crucial for customer service and business success. Video complaints, integrating text and image content, offer invaluable insights by addressing customer grievances and delineating product benefits and drawbacks. However, comprehending nuanced complaint aspects within vast daily multimodal financial data remains a formidable challenge. Addressing this gap, we have curated a proprietary multimodal video complaint dataset comprising 433 publicly accessible instances. Each instance is meticulously annotated at the utterance level, encompassing five distinct categories of financial aspects and their associated complaint labels. To support this endeavour, we introduce Solution 3.0, a model designed for multimodal aspect-based complaint identification task. Solution 3.0 is tailored to perform three key tasks: 1) handling multimodal features ( audio and video), 2) facilitating multilabel aspect classification, and 3) conducting multitasking for aspect classifications and complaint identification parallelly. Solution 3.0 utilizes a CLIP-based dual frozen encoder with an integrated image segment encoder for global feature fusion, enhanced by contextual attention (ISEC) to improve accuracy and efficiency. Our proposed framework surpasses current multimodal baselines, exhibiting superior performance across nearly all metrics by opening new ways to strengthen appropriate customer care initiatives and effectively assisting individuals in resolving their problems.
Authors: Ranjan Sapkota, Manoj Karkee
Abstract: This study evaluated the performance of the YOLOv12 object detection model, and compared against YOLOv11 and YOLOv10 for apple detection in commercial orchards using synthetic images generated by Large Language Models (LLMs). The YOLOv12n configuration excelled, achieving the highest precision at 0.916, the highest recall at 0.969, and the highest mean Average Precision (mAP@50) at 0.978. In comparison, the YOLOv11 series was led by YOLO11x, which recorded the highest precision at 0.857, recall at 0.85, and mAP@50 at 0.91. For the YOLOv10 series, YOLOv10b and YOLOv10l tied for the highest precision at 0.85, with YOLOv10n achieving the highest recall at 0.8 and mAP@50 at 0.89. The study also highlighted efficiency in processing speeds, where YOLOv11n reported the lowest inference time at 4.7 ms, compared to YOLOv12n's 5.6 ms and YOLOv10n's 5.9 ms. Although YOLOv12 is new in more accurate than YOLOv11, and YOLOv10, the YOLO11n still stays the fastest YOLO algorithm among YOLOv10, YOLOv11 and YOLOv12. These findings demonstrated that YOLOv12, when trained on high-quality LLM-generated datasets, not only surpassed its predecessors in key performance metrics but also offered a cost-effective solution by reducing the need for extensive manual data collection in the field.
Authors: Samuel Ozechi
Abstract: Human attribute identification and classification are crucial in computer vision, driving the development of innovative recognition systems. Traditional gender classification methods primarily rely on facial recognition, which, while effective, struggles under non-ideal conditions such as blurriness, side views, or partial occlusions. This study explores an alternative approach by leveraging clothing identification, specifically focusing on African traditional attire, which carries culturally significant and gender-specific features. We use the AFRIFASHION1600 dataset, a curated collection of 1,600 images of African traditional clothing labeled into two gender classes: male and female. A deep learning model, based on a modified VGG16 architecture and trained using transfer learning, was developed for classification. Data augmentation was applied to address the challenges posed by the relatively small dataset and to mitigate overfitting. The model achieved an accuracy of 87% on the test set, demonstrating strong predictive capability despite dataset imbalances favoring female samples. These findings highlight the potential of clothing-based identification as a complementary technique to facial recognition for gender classification in African contexts. Future research should focus on expanding and balancing datasets to enhance classification robustness and improve the applicability of clothing-based gender recognition systems.
Authors: Rui Hu, Delai Qiu, Shuyu Wei, Jiaming Zhang, Yining Wang, Shengping Liu, Jitao Sang
Abstract: Omnimodal Large Language Models (OLLMs) have shown significant progress in integrating vision and text, but still struggle with integrating vision and audio, often exhibiting suboptimal performance when processing audio queries compared to text queries. This disparity is primarily due to insufficient alignment between vision and audio modalities during training, leading to inadequate attention to visual information when using audio queries. To mitigate this issue, we propose a Self-Knowledge Distillation (Self-KD) training method where the vision-text component of the OLLM serves as the teacher and the vision-audio component as the student. This enables the model to process audio in a manner analogous to its text processing. Our experimental results demonstrate that Self-KD is an effective method for enhancing the vision-audio capabilities of OLLMs by learning from the vision-text components, which subsequently improves the interaction between audio and images and results in improved performance on multimodal tasks.
Authors: Youbing Hu, Yun Cheng, Anqi Lu, Dawei Wei, Zhijun Li
Abstract: The Vision Transformer (ViT) excels in global modeling but faces deployment challenges on resource-constrained devices due to the quadratic computational complexity of its attention mechanism. To address this, we propose the Semantic-Aware Clustering Vision Transformer (SAC-ViT), a non-iterative approach to enhance ViT's computational efficiency. SAC-ViT operates in two stages: Early Exit (EE) and Semantic-Aware Clustering (SAC). In the EE stage, downsampled input images are processed to extract global semantic information and generate initial inference results. If these results do not meet the EE termination criteria, the information is clustered into target and non-target tokens. In the SAC stage, target tokens are mapped back to the original image, cropped, and embedded. These target tokens are then combined with reused non-target tokens from the EE stage, and the attention mechanism is applied within each cluster. This two-stage design, with end-to-end optimization, reduces spatial redundancy and enhances computational efficiency, significantly boosting overall ViT performance. Extensive experiments demonstrate the efficacy of SAC-ViT, reducing 62% of the FLOPs of DeiT and achieving 1.98 times throughput without compromising performance.
Authors: Zezeng Li, Xiaoyu Du, Na Lei, Liming Chen, Weimin Wang
Abstract: Adversarial attacks exploit the vulnerability of deep models against adversarial samples. Existing point cloud attackers are tailored to specific models, iteratively optimizing perturbations based on gradients in either a white-box or black-box setting. Despite their promising attack performance, they often struggle to produce transferable adversarial samples due to overfitting the specific parameters of surrogate models. To overcome this issue, we shift our focus to the data distribution itself and introduce a novel approach named NoPain, which employs optimal transport (OT) to identify the inherent singular boundaries of the data manifold for cross-network point cloud attacks. Specifically, we first calculate the OT mapping from noise to the target feature space, then identify singular boundaries by locating non-differentiable positions. Finally, we sample along singular boundaries to generate adversarial point clouds. Once the singular boundaries are determined, NoPain can efficiently produce adversarial samples without the need of iterative updates or guidance from the surrogate classifiers. Extensive experiments demonstrate that the proposed end-to-end method outperforms baseline approaches in terms of both transferability and efficiency, while also maintaining notable advantages even against defense strategies. The source code will be publicly available.
Authors: Ziyu Wu, Yufan Xiong, Mengting Niu, Fangting Xie, Quan Wan, Qijun Ying, Boyan Liu, Xiaohui Cai
Abstract: Long-term in-bed monitoring benefits automatic and real-time health management within healthcare, and the advancement of human shape reconstruction technologies further enhances the representation and visualization of users' activity patterns. However, existing technologies are primarily based on visual cues, facing serious challenges in non-light-of-sight and privacy-sensitive in-bed scenes. Pressure-sensing bedsheets offer a promising solution for real-time motion reconstruction. Yet, limited exploration in model designs and data have hindered its further development. To tackle these issues, we propose a general framework that bridges gaps in data annotation and model design. Firstly, we introduce SMPLify-IB, an optimization method that overcomes the depth ambiguity issue in top-view scenarios through gravity constraints, enabling generating high-quality 3D human shape annotations for in-bed datasets. Then we present PI-HMR, a temporal-based human shape estimator to regress meshes from pressure sequences. By integrating multi-scale feature fusion with high-pressure distribution and spatial position priors, PI-HMR outperforms SOTA methods with 17.01mm Mean-Per-Joint-Error decrease. This work provides a whole
Authors: Esam Ghaleb, Bulat Khaertdinov, Asl{\i} \"Ozy\"urek, Raquel Fern\'andez
Abstract: In face-to-face interaction, we use multiple modalities, including speech and gestures, to communicate information and resolve references to objects. However, how representational co-speech gestures refer to objects remains understudied from a computational perspective. In this work, we address this gap by introducing a multimodal reference resolution task centred on representational gestures, while simultaneously tackling the challenge of learning robust gesture embeddings. We propose a self-supervised pre-training approach to gesture representation learning that grounds body movements in spoken language. Our experiments show that the learned embeddings align with expert annotations and have significant predictive power. Moreover, reference resolution accuracy further improves when (1) using multimodal gesture representations, even when speech is unavailable at inference time, and (2) leveraging dialogue history. Overall, our findings highlight the complementary roles of gesture and speech in reference resolution, offering a step towards more naturalistic models of human-machine interaction.
Authors: Alexander Immer, Jan-Matthis Lueckmann, Alex Bo-Yuan Chen, Peter H. Li, Mariela D. Petkova, Nirmala A. Iyer, Aparna Dev, Gudrun Ihrke, Woohyun Park, Alyson Petruncio, Aubrey Weigel, Wyatt Korff, Florian Engert, Jeff W. Lichtman, Misha B. Ahrens, Viren Jain, Micha{\l} Januszewski
Abstract: Large-scale neuronal activity recordings with fluorescent calcium indicators are increasingly common, yielding high-resolution 2D or 3D videos. Traditional analysis pipelines reduce this data to 1D traces by segmenting regions of interest, leading to inevitable information loss. Inspired by the success of deep learning on minimally processed data in other domains, we investigate the potential of forecasting neuronal activity directly from volumetric videos. To capture long-range dependencies in high-resolution volumetric whole-brain recordings, we design a model with large receptive fields, which allow it to integrate information from distant regions within the brain. We explore the effects of pre-training and perform extensive model selection, analyzing spatio-temporal trade-offs for generating accurate forecasts. Our model outperforms trace-based forecasting approaches on ZAPBench, a recently proposed benchmark on whole-brain activity prediction in zebrafish, demonstrating the advantages of preserving the spatial structure of neuronal activity.
Authors: Zhenxing Cui, Lu Chen, Yunhai Wang, Daniel Haehn, Yong Wang, Hanspeter Pfister
Abstract: This paper presents a systematic study of the generalization of convolutional neural networks (CNNs) and humans on relational reasoning tasks with bar charts. We first revisit previous experiments on graphical perception and update the benchmark performance of CNNs. We then test the generalization performance of CNNs on a classic relational reasoning task: estimating bar length ratios in a bar chart, by progressively perturbing the standard visualizations. We further conduct a user study to compare the performance of CNNs and humans. Our results show that CNNs outperform humans only when the training and test data have the same visual encodings. Otherwise, they may perform worse. We also find that CNNs are sensitive to perturbations in various visual encodings, regardless of their relevance to the target bars. Yet, humans are mainly influenced by bar lengths. Our study suggests that robust relational reasoning with visualizations is challenging for CNNs. Improving CNNs' generalization performance may require training them to better recognize task-related visual properties.
Authors: Alejo Silvarrey, Pablo Negri
Abstract: Biological invasions pose a significant threat to the sustainability of water sources. Efforts are increasingly being made to prevent invasions, eradicate established invaders, or control them. Remote sensing (RS) has long been recognized as a potential tool to aid in this effort, for example, by mapping the distribution of invasive species or identifying areas at risk of invasion. This paper provides a detailed explanation of a process for mapping the actual distribution of invasive species. This article presents a case studie on the detection of invasive Iris Pseudacorus L. using multispectral data captured by small Unmanned Aerial Vehicles (UAVs). The process involved spectral feature mapping followed by semi-supervised classification, which produced accurate maps of these invasive.
Authors: Anzhe Chen, Hongxiang Yu, Shuxin Li, Yuxi Chen, Zhongxiang Zhou, Wentao Sun, Rong Xiong, Yue Wang
Abstract: Visual servo based on traditional image matching methods often requires accurate keypoint correspondence for high precision control. However, keypoint detection or matching tends to fail in challenging scenarios with inconsistent illuminations or textureless objects, resulting significant performance degradation. Previous approaches, including our proposed Correspondence encoded Neural image Servo policy (CNS), attempted to alleviate these issues by integrating neural control strategies. While CNS shows certain improvement against error correspondence over conventional image-based controllers, it could not fully resolve the limitations arising from poor keypoint detection and matching. In this paper, we continue to address this problem and propose a new solution: Probabilistic Correspondence Encoded Neural Image Servo (CNSv2). CNSv2 leverages probabilistic feature matching to improve robustness in challenging scenarios. By redesigning the architecture to condition on multimodal feature matching, CNSv2 achieves high precision, improved robustness across diverse scenes and runs in real-time. We validate CNSv2 with simulations and real-world experiments, demonstrating its effectiveness in overcoming the limitations of detector-based methods in visual servo tasks.
Authors: Jacopo Teneggi, J Webster Stayman, Jeremias Sulam
Abstract: Uncertainty quantification is necessary for developers, physicians, and regulatory agencies to build trust in machine learning predictors and improve patient care. Beyond measuring uncertainty, it is crucial to express it in clinically meaningful terms that provide actionable insights. This work introduces a conformal risk control (CRC) procedure for organ-dependent uncertainty estimation, ensuring high-probability coverage of the ground-truth image. We first present a high-dimensional CRC procedure that leverages recent ideas of length minimization. We make this procedure semantically adaptive to each patient's anatomy and positioning of organs. Our method, sem-CRC, provides tighter uncertainty intervals with valid coverage on real-world computed tomography (CT) data while communicating uncertainty with clinically relevant features.
Authors: Sanchayan Santra, Vishal Chudasama, Pankaj Wasnik, Vineeth N. Balasubramanian
Abstract: Precise Event Spotting (PES) aims to identify events and their class from long, untrimmed videos, particularly in sports. The main objective of PES is to detect the event at the exact moment it occurs. Existing methods mainly rely on features from a large pre-trained network, which may not be ideal for the task. Furthermore, these methods overlook the issue of imbalanced event class distribution present in the data, negatively impacting performance in challenging scenarios. This paper demonstrates that an appropriately designed network, trained end-to-end, can outperform state-of-the-art (SOTA) methods. Particularly, we propose a network with a convolutional spatial-temporal feature extractor enhanced with our proposed Adaptive Spatio-Temporal Refinement Module (ASTRM) and a long-range temporal module. The ASTRM enhances the features with spatio-temporal information. Meanwhile, the long-range temporal module helps extract global context from the data by modeling long-range dependencies. To address the class imbalance issue, we introduce the Soft Instance Contrastive (SoftIC) loss that promotes feature compactness and class separation. Extensive experiments show that the proposed method is efficient and outperforms the SOTA methods, specifically in more challenging settings.
Authors: Kangda Wei, Zhengyu Zhou, Bingqing Wang, Jun Araki, Lukas Lange, Ruihong Huang, Zhe Feng
Abstract: In recent years, online lecture videos have become an increasingly popular resource for acquiring new knowledge. Systems capable of effectively understanding/indexing lecture videos are thus highly desirable, enabling downstream tasks like question answering to help users efficiently locate specific information within videos. This work proposes PreMind, a novel multi-agent multimodal framework that leverages various large models for advanced understanding/indexing of presentation-style videos. PreMind first segments videos into slide-presentation segments using a Vision-Language Model (VLM) to enhance modern shot-detection techniques. Each segment is then analyzed to generate multimodal indexes through three key steps: (1) extracting slide visual content, (2) transcribing speech narratives, and (3) consolidating these visual and speech contents into an integrated understanding. Three innovative mechanisms are also proposed to improve performance: leveraging prior lecture knowledge to refine visual understanding, detecting/correcting speech transcription errors using a VLM, and utilizing a critic agent for dynamic iterative self-reflection in vision analysis. Compared to traditional video indexing methods, PreMind captures rich, reliable multimodal information, allowing users to search for details like abbreviations shown only on slides. Systematic evaluations on the public LPM dataset and an internal enterprise dataset are conducted to validate PreMind's effectiveness, supported by detailed analyses.
Authors: Kuangyi Chen, Jun Zhang, Friedrich Fraundorfer
Abstract: Event cameras are bio-inspired sensors with some notable features, including high dynamic range and low latency, which makes them exceptionally suitable for perception in challenging scenarios such as high-speed motion and extreme lighting conditions. In this paper, we explore their potential for localization within pre-existing LiDAR maps, a critical task for applications that require precise navigation and mobile manipulation. Our framework follows a paradigm based on the refinement of an initial pose. Specifically, we first project LiDAR points into 2D space based on a rough initial pose to obtain depth maps, and then employ an optical flow estimation network to align events with LiDAR points in 2D space, followed by camera pose estimation using a PnP solver. To enhance geometric consistency between these two inherently different modalities, we develop a novel frame-based event representation that improves structural clarity. Additionally, given the varying degrees of bias observed in the ground truth poses, we design a module that predicts an auxiliary variable as a regularization term to mitigate the impact of this bias on network convergence. Experimental results on several public datasets demonstrate the effectiveness of our proposed method. To facilitate future research, both the code and the pre-trained models are made available online.
Authors: Benedikt Blumenstiel, Nassim Ait Ali Braham, Conrad M Albrecht, Stefano Maurogiovanni, Paolo Fraccaro
Abstract: This technical report presents SSL4EO-S12 v1.1, a multimodal, multitemporal Earth Observation dataset designed for pretraining large-scale foundation models. Building on the success of SSL4EO-S12 v1.0, the new version addresses the previous challenges of data misalignment and a limited data structure for low-barrier, analysis-ready EO processing. SSL4EO-S12 v1.1 covers the world's 10,000 largest cities and its surroundings within a 50 km radius across four seasons, resulting in a diverse collection of nearly one million patches. SSL4EO-S12 v1.1 packages the data in Zarr file format for cloud-efficient loading and representation of meta-information such as including cloud masks and geolocation. Released under the CC-BY-4.0 license, SSL4EO-S12 v1.1 facilitates open research and provides a robust foundation for future advancements in self-supervised learning and geospatial analysis. The dataset is available online through https://datapub.fz-juelich.de/ssl4eo-s12, and we provided additional resources at https://github.com/DLR-MF-DAS/SSL4EO-S12-v1.1.
URLs: https://datapub.fz-juelich.de/ssl4eo-s12,, https://github.com/DLR-MF-DAS/SSL4EO-S12-v1.1.
Authors: Denis Musinguzi, Andrew Katumba, Sudi Murindanyi
Abstract: Tuberculosis (TB) is a infectious global health challenge. Chest X-rays are a standard method for TB screening, yet many countries face a critical shortage of radiologists capable of interpreting these images. Machine learning offers an alternative, as it can automate tasks such as disease diagnosis, and report generation. However, traditional approaches rely on task-specific models, which cannot utilize the interdependence between tasks. Building a multi-task model capable of performing multiple tasks poses additional challenges such as scarcity of multimodal data, dataset imbalance, and negative transfer. To address these challenges, we propose PaliGemma-CXR, a multi-task multimodal model capable of performing TB diagnosis, object detection, segmentation, report generation, and VQA. Starting with a dataset of chest X-ray images annotated with TB diagnosis labels and segmentation masks, we curated a multimodal dataset to support additional tasks. By finetuning PaliGemma on this dataset and sampling data using ratios of the inverse of the size of task datasets, we achieved the following results across all tasks: 90.32% accuracy on TB diagnosis and 98.95% on close-ended VQA, 41.3 BLEU score on report generation, and a mAP of 19.4 and 16.0 on object detection and segmentation, respectively. These results demonstrate that PaliGemma-CXR effectively leverages the interdependence between multiple image interpretation tasks to enhance performance.
Authors: Amar Kumar, Anita Kriz, Mohammad Havaei, Tal Arbel
Abstract: Developing reliable and generalizable deep learning systems for medical imaging faces significant obstacles due to spurious correlations, data imbalances, and limited text annotations in datasets. Addressing these challenges requires architectures robust to the unique complexities posed by medical imaging data. The rapid advancements in vision-language foundation models within the natural image domain prompt the question of how they can be adapted for medical imaging tasks. In this work, we present PRISM, a framework that leverages foundation models to generate high-resolution, language-guided medical image counterfactuals using Stable Diffusion. Our approach demonstrates unprecedented precision in selectively modifying spurious correlations (the medical devices) and disease features, enabling the removal and addition of specific attributes while preserving other image characteristics. Through extensive evaluation, we show how PRISM advances counterfactual generation and enables the development of more robust downstream classifiers for clinically deployable solutions. To facilitate broader adoption and research, we make our code publicly available at https://github.com/Amarkr1/PRISM.
Authors: Ryosuke Kawamura, Hideaki Hayashi, Noriko Takemura, Hajime Nagahara
Abstract: Dynamic facial expression recognition (DFER) is an important task in the field of computer vision. To apply automatic DFER in practice, it is necessary to accurately recognize ambiguous facial expressions, which often appear in data in the wild. In this paper, we propose MIDAS, a data augmentation method for DFER, which augments ambiguous facial expression data with soft labels consisting of probabilities for multiple emotion classes. In MIDAS, the training data are augmented by convexly combining pairs of video frames and their corresponding emotion class labels, which can also be regarded as an extension of mixup to soft-labeled video data. This simple extension is remarkably effective in DFER with ambiguous facial expression data. To evaluate MIDAS, we conducted experiments on the DFEW dataset. The results demonstrate that the model trained on the data augmented by MIDAS outperforms the existing state-of-the-art method trained on the original dataset.
Authors: Yufei Guo, Xiaode Liu, Yuanpei Chen, Weihang Peng, Yuhan Zhang, Zhe Ma
Abstract: Transformers have demonstrated outstanding performance across a wide range of tasks, owing to their self-attention mechanism, but they are highly energy-consuming. Spiking Neural Networks have emerged as a promising energy-efficient alternative to traditional Artificial Neural Networks, leveraging event-driven computation and binary spikes for information transfer. The combination of Transformers' capabilities with the energy efficiency of SNNs offers a compelling opportunity. This paper addresses the challenge of adapting the self-attention mechanism of Transformers to the spiking paradigm by introducing a novel approach: Accurate Addition-Only Spiking Self-Attention (A$^2$OS$^2$A). Unlike existing methods that rely solely on binary spiking neurons for all components of the self-attention mechanism, our approach integrates binary, ReLU, and ternary spiking neurons. This hybrid strategy significantly improves accuracy while preserving non-multiplicative computations. Moreover, our method eliminates the need for softmax and scaling operations. Extensive experiments show that the A$^2$OS$^2$A-based Spiking Transformer outperforms existing SNN-based Transformers on several datasets, even achieving an accuracy of 78.66\% on ImageNet-1K. Our work represents a significant advancement in SNN-based Transformer models, offering a more accurate and efficient solution for real-world applications.
Authors: Kaleab A. Kinfu, Ren\'e Vidal
Abstract: Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have led to significant progress in 2D body pose estimation. However, achieving a good balance between accuracy, efficiency, and robustness remains a challenge. For instance, CNNs are computationally efficient but struggle with long-range dependencies, while ViTs excel in capturing such dependencies but suffer from quadratic computational complexity. This paper proposes two ViT-based models for accurate, efficient, and robust 2D pose estimation. The first one, EViTPose, operates in a computationally efficient manner without sacrificing accuracy by utilizing learnable joint tokens to select and process a subset of the most important body patches, enabling us to control the trade-off between accuracy and efficiency by changing the number of patches to be processed. The second one, UniTransPose, while not allowing for the same level of direct control over the trade-off, efficiently handles multiple scales by combining (1) an efficient multi-scale transformer encoder that uses both local and global attention with (2) an efficient sub-pixel CNN decoder for better speed and accuracy. Moreover, by incorporating all joints from different benchmarks into a unified skeletal representation, we train robust methods that learn from multiple datasets simultaneously and perform well across a range of scenarios -- including pose variations, lighting conditions, and occlusions. Experiments on six benchmarks demonstrate that the proposed methods significantly outperform state-of-the-art methods while improving computational efficiency. EViTPose exhibits a significant decrease in computational complexity (30% to 44% less in GFLOPs) with a minimal drop of accuracy (0% to 3.5% less), and UniTransPose achieves accuracy improvements ranging from 0.9% to 43.8% across these benchmarks.
Authors: Yanan Niu, Roy Sarkis, Demetri Psaltis, Mario Paolone, Christophe Moser, Luisa Lambertini
Abstract: Accurate intraday solar irradiance forecasting is crucial for optimizing dispatch planning and electricity trading. For this purpose, we introduce a novel and effective approach that includes three distinguishing components from the literature: 1) the uncommon use of single-frame public camera imagery; 2) solar irradiance time series scaled with a proposed normalization step, which boosts performance; and 3) a lightweight multimodal model, called Solar Multimodal Transformer (SMT), that delivers accurate short-term solar irradiance forecasting by combining images and scaled time series. Benchmarking against Solcast, a leading solar forecasting service provider, our model improved prediction accuracy by 25.95%. Our approach allows for easy adaptation to various camera specifications, offering broad applicability for real-world solar forecasting challenges.
Authors: Yufan Zhang, Yu Ji, Yu Guo, Jinwei Ye
Abstract: We present a snapshot imaging technique for recovering 3D surrounding views of miniature scenes. Due to their intricacy, miniature scenes with objects sized in millimeters are difficult to reconstruct, yet miniatures are common in life and their 3D digitalization is desirable. We design a catadioptric imaging system with a single camera and eight pairs of planar mirrors for snapshot 3D reconstruction from a dollhouse perspective. We place paired mirrors on nested pyramid surfaces for capturing surrounding multi-view images in a single shot. Our mirror design is customizable based on the size of the scene for optimized view coverage. We use the 3D Gaussian Splatting (3DGS) representation for scene reconstruction and novel view synthesis. We overcome the challenge posed by our sparse view input by integrating visual hull-derived depth constraint. Our method demonstrates state-of-the-art performance on a variety of synthetic and real miniature scenes.
Authors: Milad Yazdani, Yasamin Medghalchi, Pooria Ashrafian, Ilker Hacihaliloglu, Dena Shahriari
Abstract: Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative models, such as diffusion models, offer a potential solution by synthesizing medical images, but their practical adoption is hindered by long inference times. In this paper, we propose the use of an optimal transport flow matching approach to accelerate image generation. By introducing a straighter mapping between the source and target distribution, our method significantly reduces inference time while preserving and further enhancing the quality of the outputs. Furthermore, this approach is highly adaptable, supporting various medical imaging modalities, conditioning mechanisms (such as class labels and masks), and different spatial dimensions, including 2D and 3D. Beyond image generation, it can also be applied to related tasks such as image enhancement. Our results demonstrate the efficiency and versatility of this framework, making it a promising advancement for medical imaging applications. Code with checkpoints and a synthetic dataset (beneficial for classification and segmentation) is now available on: https://github.com/milad1378yz/MOTFM.
Authors: Haoxin Li, Yingchen Yu, Qilong Wu, Hanwang Zhang, Boyang Li, Song Bai
Abstract: Despite recent progress, video generative models still struggle to animate human actions from static images, particularly when handling uncommon actions whose training data are limited. In this paper, we investigate the task of learning to animate human actions from a small number of videos -- 16 or fewer -- which is highly valuable in real-world applications like video and movie production. Few-shot learning of generalizable motion patterns while ensuring smooth transitions from the initial reference image is exceedingly challenging. We propose FLASH (Few-shot Learning to Animate and Steer Humans), which improves motion generalization by aligning motion features and inter-frame correspondence relations between videos that share the same motion but have different appearances. This approach minimizes overfitting to visual appearances in the limited training data and enhances the generalization of learned motion patterns. Additionally, FLASH extends the decoder with additional layers to compensate lost details in the latent space, fostering smooth transitions from the initial reference image. Experiments demonstrate that FLASH effectively animates images with unseen human or scene appearances into specified actions while maintaining smooth transitions from the reference image.
Authors: Zihan Huang, Wei Fang, Tong Bu, Peng Xue, Zecheng Hao, Wenxuan Liu, Yuanhong Tang, Zhaofei Yu, Tiejun Huang
Abstract: Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather than rates directly, and explores its application across various layers. Additionally, the threshold iteration method is proposed to optimize thresholds based on activation distribution when converting Rectified Linear Units (ReLUs) to spiking neurons. Experimental results on various Convolutional Neural Networks (CNNs) and Transformers demonstrate that the proposed differential coding significantly improves accuracy while reducing energy consumption, particularly when combined with the threshold iteration method, achieving state-of-the-art performance.
Authors: Yangge Li, Chenxi Ji, Xiangru Zhong, Huan Zhang, Sayan Mitra
Abstract: We introduce abstract rendering, a method for computing a set of images by rendering a scene from a continuously varying range of camera positions. The resulting abstract image-which encodes an infinite collection of possible renderings-is represented using constraints on the image matrix, enabling rigorous uncertainty propagation through the rendering process. This capability is particularly valuable for the formal verification of vision-based autonomous systems and other safety-critical applications. Our approach operates on Gaussian splat scenes, an emerging representation in computer vision and robotics. We leverage efficient piecewise linear bound propagation to abstract fundamental rendering operations, while addressing key challenges that arise in matrix inversion and depth sorting-two operations not directly amenable to standard approximations. To handle these, we develop novel linear relational abstractions that maintain precision while ensuring computational efficiency. These abstractions not only power our abstract rendering algorithm but also provide broadly applicable tools for other rendering problems. Our implementation, AbstractSplat, is optimized for scalability, handling up to 750k Gaussians while allowing users to balance memory and runtime through tile and batch-based computation. Compared to the only existing abstract image method for mesh-based scenes, AbstractSplat achieves 2-14x speedups while preserving precision. Our results demonstrate that continuous camera motion, rotations, and scene variations can be rigorously analyzed at scale, making abstract rendering a powerful tool for uncertainty-aware vision applications.
Authors: Zhiwei Ling, Yachen Chang, Hailiang Zhao, Xinkui Zhao, Kingsum Chow, Shuiguang Deng
Abstract: Deep neural networks (DNNs) have been widely criticized for their overconfidence when dealing with out-of-distribution (OOD) samples, highlighting the critical need for effective OOD detection to ensure the safe deployment of DNNs in real-world settings. Existing post-hoc OOD detection methods primarily enhance the discriminative power of logit-based approaches by reshaping sample features, yet they often neglect critical information inherent in the features themselves. In this paper, we propose the Class-Aware Relative Feature-based method (CARef), which utilizes the error between a sample's feature and its class-aware average feature as a discriminative criterion. To further refine this approach, we introduce the Class-Aware Decoupled Relative Feature-based method (CADRef), which decouples sample features based on the alignment of signs between the relative feature and corresponding model weights, enhancing the discriminative capabilities of CARef. Extensive experimental results across multiple datasets and models demonstrate that both proposed methods exhibit effectiveness and robustness in OOD detection compared to state-of-the-art methods. Specifically, our two methods outperform the best baseline by 2.82% and 3.27% in AUROC, with improvements of 4.03% and 6.32% in FPR95, respectively.
Authors: Benjamin Schneider, Florian Kerschbaum, Wenhu Chen
Abstract: Visual embedding models excel at zero-shot tasks like visual retrieval and classification. However, these models cannot be used for tasks that contain ambiguity or require user instruction. These tasks necessitate a multimodal embedding model, which outputs embeddings that combine visual and natural language input. Existing CLIP-based approaches embed images and text independently, and fuse the result. We find that this results in weak interactions between modalities, and poor user control over the representation. We introduce ABC, an open-source multimodal embedding model that uses a vision-language model backbone to deeply integrate image features with natural language instructions. ABC achieves bestfor-size performance on MSCOCO image-to-text retrieval and is the top performing model on classification and VQA tasks in the Massive Multimodal Embedding Benchmark. With a strongly unified vision-language representation, ABC can use natural language to solve subtle and potentially ambiguous visual retrieval problems. To evaluate this capability, we design CtrlBench, a benchmark that requires interleaving textual instructions with image content for correct retrieval. ABC advances the state of multimodal embeddings by offering high-quality representations and flexible natural language control. Our model and datasets are available at our project page.
Authors: Samuel Garske, Konrad Heidler, Bradley Evans, KC Wong, Xiao Xiang Zhu
Abstract: The increasing frequency of environmental hazards due to climate change underscores the urgent need for effective monitoring systems. Current approaches either rely on expensive labelled datasets, struggle with seasonal variations, or require multiple observations for confirmation (which delays detection). To address these challenges, this work presents SHAZAM - Self-Supervised Change Monitoring for Hazard Detection and Mapping. SHAZAM uses a lightweight conditional UNet to generate expected images of a region of interest (ROI) for any day of the year, allowing for the direct modelling of normal seasonal changes and the ability to distinguish potential hazards. A modified structural similarity measure compares the generated images with actual satellite observations to compute region-level anomaly scores and pixel-level hazard maps. Additionally, a theoretically grounded seasonal threshold eliminates the need for dataset-specific optimisation. Evaluated on four diverse datasets that contain bushfires (wildfires), burned regions, extreme and out-of-season snowfall, floods, droughts, algal blooms, and deforestation, SHAZAM achieved F1 score improvements of between 0.066 and 0.234 over existing methods. This was achieved primarily through more effective hazard detection (higher recall) while using only 473K parameters. SHAZAM demonstrated superior mapping capabilities through higher spatial resolution and improved ability to suppress background features while accentuating both immediate and gradual hazards. SHAZAM has been established as an effective and generalisable solution for hazard detection and mapping across different geographical regions and a diverse range of hazards. The Python code is available at: https://github.com/WiseGamgee/SHAZAM
Authors: Yu-Ting Zhan, Cheng-Yuan Ho, Hebi Yang, Yi-Hsin Chen, Jui Chiu Chiang, Yu-Lun Liu, Wen-Hsiao Peng
Abstract: 3D Gaussian Splatting (3DGS) has recently emerged as a promising 3D representation. Much research has been focused on reducing its storage requirements and memory footprint. However, the needs to compress and transmit the 3DGS representation to the remote side are overlooked. This new application calls for rate-distortion-optimized 3DGS compression. How to quantize and entropy encode sparse Gaussian primitives in the 3D space remains largely unexplored. Few early attempts resort to the hyperprior framework from learned image compression. But, they fail to utilize fully the inter and intra correlation inherent in Gaussian primitives. Built on ScaffoldGS, this work, termed CAT-3DGS, introduces a context-adaptive triplane approach to their rate-distortion-optimized coding. It features multi-scale triplanes, oriented according to the principal axes of Gaussian primitives in the 3D space, to capture their inter correlation (i.e. spatial correlation) for spatial autoregressive coding in the projected 2D planes. With these triplanes serving as the hyperprior, we further perform channel-wise autoregressive coding to leverage the intra correlation within each individual Gaussian primitive. Our CAT-3DGS incorporates a view frequency-aware masking mechanism. It actively skips from coding those Gaussian primitives that potentially have little impact on the rendering quality. When trained end-to-end to strike a good rate-distortion trade-off, our CAT-3DGS achieves the state-of-the-art compression performance on the commonly used real-world datasets.
Authors: Qianqian Shen, Yunhan Zhao, Nahyun Kwon, Jeeeun Kim, Yanan Li, Shu Kong
Abstract: Instance detection (InsDet) aims to localize specific object instances within a novel scene imagery based on given visual references. Technically, it requires proposal detection to identify all possible object instances, followed by instance-level matching to pinpoint the ones of interest. Its open-world nature supports its wide-ranging applications from robotics to AR/VR, but also presents significant challenges: methods must generalize to unknown testing data distributions because (1) the testing scene imagery is unseen during training, and (2) there are domain gaps between visual references and detected proposals. Existing methods attempt to tackle these challenges by synthesizing diverse training examples or utilizing off-the-shelf foundation models (FMs). However, they only partially capitalize the available open-world information. In this paper, we approach InsDet from an Open-World perspective, introducing our method IDOW. We find that, while pretrained FMs yield high recall in instance detection, they are not specifically optimized for instance-level feature matching. To address this, we adapt pretrained FMs for improved instance-level matching using open-world data. Our approach incorporates metric learning along with novel data augmentations, which sample distractors as negative examples and synthesize novel-view instances to enrich the visual references. Extensive experiments demonstrate that our method significantly outperforms prior works, achieving >10 AP over previous results on two recently released challenging benchmark datasets in both conventional and novel instance detection settings.
Authors: Wei Suo, Lijun Zhang, Mengyang Sun, Lin Yuanbo Wu, Peng Wang, Yanning Zhang
Abstract: Large Vision-Language Models (LVLMs) have obtained impressive performance in visual content understanding and multi-modal reasoning. Unfortunately, these large models suffer from serious hallucination problems and tend to generate fabricated responses. Recently, several Contrastive Decoding (CD) strategies have been proposed to alleviate hallucination by introducing disturbed inputs. Although great progress has been made, these CD strategies mostly apply a one-size-fits-all approach for all input conditions. In this paper, we revisit this process through extensive experiments. Related results show that hallucination causes are hybrid and each generative step faces a unique hallucination challenge. Leveraging these meaningful insights, we introduce a simple yet effective Octopus-like framework that enables the model to adaptively identify hallucination types and create a dynamic CD workflow. Our Octopus framework not only outperforms existing methods across four benchmarks but also demonstrates excellent deployability and expansibility. Code is available at https://github.com/LijunZhang01/Octopus.
Authors: Yaowei Guo, Jiazheng Xing, Xiaojun Hou, Shuo Xin, Juntao Jiang, Demetri Terzopoulos, Chenfanfu Jiang, Yong Liu
Abstract: Video summarization, by selecting the most informative and/or user-relevant parts of original videos to create concise summary videos, has high research value and consumer demand in today's video proliferation era. Multi-modal video summarization that accomodates user input has become a research hotspot. However, current multi-modal video summarization methods suffer from two limitations. First, existing methods inadequately fuse information from different modalities and cannot effectively utilize modality-unique features. Second, most multi-modal methods focus on video and text modalities, neglecting the audio modality, despite the fact that audio information can be very useful in certain types of videos. In this paper we propose CFSum, a transformer-based multi-modal video summarization framework with coarse-fine fusion. CFSum exploits video, text, and audio modal features as input, and incorporates a two-stage transformer-based feature fusion framework to fully utilize modality-unique information. In the first stage, multi-modal features are fused simultaneously to perform initial coarse-grained feature fusion, then, in the second stage, video and audio features are explicitly attended with the text representation yielding more fine-grained information interaction. The CFSum architecture gives equal importance to each modality, ensuring that each modal feature interacts deeply with the other modalities. Our extensive comparative experiments against prior methods and ablation studies on various datasets confirm the effectiveness and superiority of CFSum.
Authors: Xuehao Gao, Yang Yang, Shaoyi Du, Guo-Jun Qi, Junwei Han
Abstract: As two intimate reciprocal tasks, scene-aware human motion synthesis and analysis require a joint understanding between multiple modalities, including 3D body motions, 3D scenes, and textual descriptions. In this paper, we integrate these two paired processes into a Co-Evolving Synthesis-Analysis (CESA) pipeline and mutually benefit their learning. Specifically, scene-aware text-to-human synthesis generates diverse indoor motion samples from the same textual description to enrich human-scene interaction intra-class diversity, thus significantly benefiting training a robust human motion analysis system. Reciprocally, human motion analysis would enforce semantic scrutiny on each synthesized motion sample to ensure its semantic consistency with the given textual description, thus improving realistic motion synthesis. Considering that real-world indoor human motions are goal-oriented and path-guided, we propose a cascaded generation strategy that factorizes text-driven scene-specific human motion generation into three stages: goal inferring, path planning, and pose synthesizing. Coupling CESA with this powerful cascaded motion synthesis model, we jointly improve realistic human motion synthesis and robust human motion analysis in 3D scenes.
Authors: Tianyi Wang, Jianan Fan, Dingxin Zhang, Dongnan Liu, Yong Xia, Heng Huang, Weidong Cai
Abstract: Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease. Multi-modal self-supervised learning has demonstrated remarkable potential in learning pathological representations by integrating diverse data sources. Conventional multi-modal integration methods primarily emphasize modality alignment, while paying insufficient attention to retaining the modality-specific structures. However, unlike conventional scenarios where multi-modal inputs share highly overlapping features, histopathology and transcriptomics exhibit pronounced heterogeneity, offering orthogonal yet complementary insights. Histopathology provides morphological and spatial context, elucidating tissue architecture and cellular topology, whereas transcriptomics delineates molecular signatures through gene expression patterns. This inherent disparity introduces a major challenge in aligning them while maintaining modality-specific fidelity. To address these challenges, we present MIRROR, a novel multi-modal representation learning method designed to foster both modality alignment and retention. MIRROR employs dedicated encoders to extract comprehensive features for each modality, which is further complemented by a modality alignment module to achieve seamless integration between phenotype patterns and molecular profiles. Furthermore, a modality retention module safeguards unique attributes from each modality, while a style clustering module mitigates redundancy and enhances disease-relevant information by modeling and aligning consistent pathological signatures within a clustering space. Extensive evaluations on TCGA cohorts for cancer subtyping and survival analysis highlight MIRROR's superior performance, demonstrating its effectiveness in constructing comprehensive oncological feature representations and benefiting the cancer diagnosis.
Authors: Yingchao Zhang, Cheng Liu
Abstract: This study proposes a novel few-shot crack image classification model based on CLIP and Bayesian optimization. By combining multimodal information and Bayesian approach, the model achieves efficient classification of crack images in a small number of training samples. The CLIP model employs its robust feature extraction capabilities to facilitate precise classification with a limited number of samples. In contrast, Bayesian optimisation enhances the robustness and generalization of the model, while reducing the reliance on extensive labelled data. The results demonstrate that the model exhibits robust performance across a diverse range of dataset scales, particularly in the context of small sample sets. The study validates the potential of the method in civil engineering crack classification.
Authors: Guixu Lin, Muyao Niu, Qingtian Zhu, Zhengwei Yin, Zhuoxiao Li, Shengfeng He, Yinqiang Zheng
Abstract: Event cameras, known for their low latency and high dynamic range, show great potential in pedestrian detection applications. However, while recent research has primarily focused on improving detection accuracy, the robustness of event-based visual models against physical adversarial attacks has received limited attention. For example, adversarial physical objects, such as specific clothing patterns or accessories, can exploit inherent vulnerabilities in these systems, leading to misdetections or misclassifications. This study is the first to explore physical adversarial attacks on event-driven pedestrian detectors, specifically investigating whether certain clothing patterns worn by pedestrians can cause these detectors to fail, effectively rendering them unable to detect the person. To address this, we developed an end-to-end adversarial framework in the digital domain, framing the design of adversarial clothing textures as a 2D texture optimization problem. By crafting an effective adversarial loss function, the framework iteratively generates optimal textures through backpropagation. Our results demonstrate that the textures identified in the digital domain possess strong adversarial properties. Furthermore, we translated these digitally optimized textures into physical clothing and tested them in real-world scenarios, successfully demonstrating that the designed textures significantly degrade the performance of event-based pedestrian detection models. This work highlights the vulnerability of such models to physical adversarial attacks.
Authors: Xuehao Gao, Yang Yang, Shaoyi Du, Yang Wu, Yebin Liu, Guo-Jun Qi
Abstract: This paper explores a cross-modality synthesis task that infers 3D human-object interactions (HOIs) from a given text-based instruction. Existing text-to-HOI synthesis methods mainly deploy a direct mapping from texts to object-specific 3D body motions, which may encounter a performance bottleneck since the huge cross-modality gap. In this paper, we observe that those HOI samples with the same interaction intention toward different targets, e.g., "lift a chair" and "lift a cup", always encapsulate similar action-specific body motion patterns while characterizing different object-specific interaction styles. Thus, learning effective action-specific motion priors and object-specific interaction priors is crucial for a text-to-HOI model and dominates its performances on text-HOI semantic consistency and body-object interaction realism. In light of this, we propose a novel body pose generation strategy for the text-to-HOI task: infer object-agnostic canonical body action first and then enrich object-specific interaction styles. Specifically, the first canonical body action inference stage focuses on learning intra-class shareable body motion priors and mapping given text-based semantics to action-specific canonical 3D body motions. Then, in the object-specific interaction inference stage, we focus on object affordance learning and enrich object-specific interaction styles on an inferred action-specific body motion basis. Extensive experiments verify that our proposed text-to-HOI synthesis system significantly outperforms other SOTA methods on three large-scale datasets with better semantic consistency and interaction realism performances.
Authors: Nandish Chattopadhyay, Abdul Basit, Bassem Ouni, Muhammad Shafique
Abstract: Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white box and black box approaches. Practical attacks include methods to manipulate the physical world and enforce adversarial behaviour by the corresponding target neural network models. Multiple different approaches to mitigate different kinds of such attacks are available in the literature, each with their own advantages and limitations. In this survey, we present a comprehensive systematization of knowledge on adversarial defenses, focusing on two key computer vision tasks: image classification and object detection. We review the state-of-the-art adversarial defense techniques and categorize them for easier comparison. In addition, we provide a schematic representation of these categories within the context of the overall machine learning pipeline, facilitating clearer understanding and benchmarking of defenses. Furthermore, we map these defenses to the types of adversarial attacks and datasets where they are most effective, offering practical insights for researchers and practitioners. This study is necessary for understanding the scope of how the available defenses are able to address the adversarial threats, and their shortcomings as well, which is necessary for driving the research in this area in the most appropriate direction, with the aim of building trustworthy AI systems for regular practical use-cases.
Authors: Yuto Shibata, Yusuke Oumi, Go Irie, Akisato Kimura, Yoshimitsu Aoki, Mariko Isogawa
Abstract: We propose BGM2Pose, a non-invasive 3D human pose estimation method using arbitrary music (e.g., background music) as active sensing signals. Unlike existing approaches that significantly limit practicality by employing intrusive chirp signals within the audible range, our method utilizes natural music that causes minimal discomfort to humans. Estimating human poses from standard music presents significant challenges. In contrast to sound sources specifically designed for measurement, regular music varies in both volume and pitch. These dynamic changes in signals caused by music are inevitably mixed with alterations in the sound field resulting from human motion, making it hard to extract reliable cues for pose estimation. To address these challenges, BGM2Pose introduces a Contrastive Pose Extraction Module that employs contrastive learning and hard negative sampling to eliminate musical components from the recorded data, isolating the pose information. Additionally, we propose a Frequency-wise Attention Module that enables the model to focus on subtle acoustic variations attributable to human movement by dynamically computing attention across frequency bands. Experiments suggest that our method outperforms the existing methods, demonstrating substantial potential for real-world applications. Our datasets and code will be made publicly available.
Authors: Juan Song, Lijie Yang, Mingtao Feng
Abstract: It remains a significant challenge to compress images at ultra-low bitrate while achieving both semantic consistency and high perceptual quality. We propose a novel image compression framework, Semantically Disentangled Image Compression (SEDIC) in this paper. Our proposed SEDIC leverages large multimodal models (LMMs) to disentangle the image into several essential semantic information, including an extremely compressed reference image, overall and object-level text descriptions, and the semantic masks. A multi-stage semantic decoder is designed to progressively restore the transmitted reference image object-by-object, ultimately producing high-quality and perceptually consistent reconstructions. In each decoding stage, a pre-trained controllable diffusion model is utilized to restore the object details on the reference image conditioned by the text descriptions and semantic masks. Experimental results demonstrate that SEDIC significantly outperforms state-of-the-art approaches, achieving superior perceptual quality and semantic consistency at ultra-low bitrates ($\le$ 0.05 bpp). Our code is available at https://github.com/yang-xidian/SEDIC.
Authors: Xiang Zheng, Haodong Jiang, Junfeng Wu
Abstract: This report presents a comprehensive interval analysis of two spherical functions derived from the robust Perspective-n-Lines (PnL) problem. The study is motivated by the application of a dimension-reduction technique to achieve global solutions for the robust PnL problem. We establish rigorous theoretical results, supported by detailed proofs, and validate our findings through extensive numerical simulations.
Authors: Zhaoyi Tian, Feifeng Wang, Shiwei Wang, Zihao Zhou, Yao Zhu, Liquan Shen
Abstract: Recently, learned video compression (LVC) is undergoing a period of rapid development. However, due to absence of large and high-quality high dynamic range (HDR) video training data, LVC on HDR video is still unexplored. In this paper, we are the first to collect a large-scale HDR video benchmark dataset, named HDRVD2K, featuring huge quantity, diverse scenes and multiple motion types. HDRVD2K fills gaps of video training data and facilitate the development of LVC on HDR videos. Based on HDRVD2K, we further propose the first learned bit-depth scalable video compression (LBSVC) network for HDR videos by effectively exploiting bit-depth redundancy between videos of multiple dynamic ranges. To achieve this, we first propose a compression-friendly bit-depth enhancement module (BEM) to effectively predict original HDR videos based on compressed tone-mapped low dynamic range (LDR) videos and dynamic range prior, instead of reducing redundancy only through spatio-temporal predictions. Our method greatly improves the reconstruction quality and compression performance on HDR videos. Extensive experiments demonstrate the effectiveness of HDRVD2K on learned HDR video compression and great compression performance of our proposed LBSVC network. Code and dataset will be released in https://github.com/sdkinda/HDR-Learned-Video-Coding.
Authors: Tianyu Huai, Jie Zhou, Xingjiao Wu, Qin Chen, Qingchun Bai, Ze Zhou, Liang He
Abstract: Multimodal large language models (MLLMs) have garnered widespread attention from researchers due to their remarkable understanding and generation capabilities in visual language tasks (e.g., visual question answering). However, the rapid pace of knowledge updates in the real world makes offline training of MLLMs costly, and when faced with non-stationary data streams, MLLMs suffer from catastrophic forgetting during learning. In this paper, we propose an MLLMs-based dual momentum Mixture-of-Experts (CL-MoE) framework for continual visual question answering (VQA). We integrate MLLMs with continual learning to utilize the rich commonsense knowledge in LLMs. We introduce a Dual-Router MoE (RMoE) strategy to select the global and local experts using task-level and instance-level routers, to robustly assign weights to the experts most appropriate for the task. Then, we design a dynamic Momentum MoE (MMoE) to update the parameters of experts dynamically based on the relationships between the experts and tasks/instances, so that the model can absorb new knowledge while maintaining existing knowledge. The extensive experimental results indicate that our method achieves state-of-the-art performance on 10 VQA tasks, proving the effectiveness of our approach.
Authors: Xin Lin, Chong Shi, Zuopeng Yang, Haojin Tang, Zhili Zhou
Abstract: Recent open-vocabulary human-object interaction (OV-HOI) detection methods primarily rely on large language model (LLM) for generating auxiliary descriptions and leverage knowledge distilled from CLIP to detect unseen interaction categories. Despite their effectiveness, these methods face two challenges: (1) feature granularity deficiency, due to reliance on last layer visual features for text alignment, leading to the neglect of crucial object-level details from intermediate layers; (2) semantic similarity confusion, resulting from CLIP's inherent biases toward certain classes, while LLM-generated descriptions based solely on labels fail to adequately capture inter-class similarities. To address these challenges, we propose a stratified granular comparison network. First, we introduce a granularity sensing alignment module that aggregates global semantic features with local details, refining interaction representations and ensuring robust alignment between intermediate visual features and text embeddings. Second, we develop a hierarchical group comparison module that recursively compares and groups classes using LLMs, generating fine-grained and discriminative descriptions for each interaction category. Experimental results on two widely-used benchmark datasets, SWIG-HOI and HICO-DET, demonstrate that our method achieves state-of-the-art results in OV-HOI detection. Codes will be released on https://github.com/Phil0212/SGC-Net.
Authors: Deepti Rawat, Keshav Gupta, Aryamaan Basu Roy, Ravi Kiran Sarvadevabhatla
Abstract: Motorized two-wheelers are a prevalent and economical means of transportation, particularly in the Asia-Pacific region. However, hazardous driving practices such as triple riding and non-compliance with helmet regulations contribute significantly to accident rates. Addressing these violations through automated enforcement mechanisms can enhance traffic safety. In this paper, we propose DashCop, an end-to-end system for automated E-ticket generation. The system processes vehicle-mounted dashcam videos to detect two-wheeler traffic violations. Our contributions include: (1) a novel Segmentation and Cross-Association (SAC) module to accurately associate riders with their motorcycles, (2) a robust cross-association-based tracking algorithm optimized for the simultaneous presence of riders and motorcycles, and (3) the RideSafe-400 dataset, a comprehensive annotated dashcam video dataset for triple riding and helmet rule violations. Our system demonstrates significant improvements in violation detection, validated through extensive evaluations on the RideSafe-400 dataset.
Authors: Jingyi Yang, Xun Lin, Zitong Yu, Liepiao Zhang, Xin Liu, Hui Li, Xiaochen Yuan, Xiaochun Cao
Abstract: With the availability of diverse sensor modalities (i.e., RGB, Depth, Infrared) and the success of multi-modal learning, multi-modal face anti-spoofing (FAS) has emerged as a prominent research focus. The intuition behind it is that leveraging multiple modalities can uncover more intrinsic spoofing traces. However, this approach presents more risk of misalignment. We identify two main types of misalignment: (1) \textbf{Intra-domain modality misalignment}, where the importance of each modality varies across different attacks. For instance, certain modalities (e.g., Depth) may be non-defensive against specific attacks (e.g., 3D mask), indicating that each modality has unique strengths and weaknesses in countering particular attacks. Consequently, simple fusion strategies may fall short. (2) \textbf{Inter-domain modality misalignment}, where the introduction of additional modalities exacerbates domain shifts, potentially overshadowing the benefits of complementary fusion. To tackle (1), we propose a alignment module between modalities based on mutual information, which adaptively enhances favorable modalities while suppressing unfavorable ones. To address (2), we employ a dual alignment optimization method that aligns both sub-domain hyperplanes and modality angle margins, thereby mitigating domain gaps. Our method, dubbed \textbf{D}ual \textbf{A}lignment of \textbf{D}omain and \textbf{M}odality (DADM), achieves state-of-the-art performance in extensive experiments across four challenging protocols demonstrating its robustness in multi-modal domain generalization scenarios. The codes will be released soon.
Authors: Maria Lymperaiou, Giorgos FIlandrianos, Angeliki Dimitriou, Athanasios Voulodimos, Giorgos Stamou
Abstract: In the dynamic landscape of artificial intelligence, the exploration of hallucinations within vision-language (VL) models emerges as a critical frontier. This work delves into the intricacies of hallucinatory phenomena exhibited by widely used image captioners, unraveling interesting patterns. Specifically, we step upon previously introduced techniques of conceptual counterfactual explanations to address VL hallucinations. The deterministic and efficient nature of the employed conceptual counterfactuals backbone is able to suggest semantically minimal edits driven by hierarchical knowledge, so that the transition from a hallucinated caption to a non-hallucinated one is performed in a black-box manner. HalCECE, our proposed hallucination detection framework is highly interpretable, by providing semantically meaningful edits apart from standalone numbers, while the hierarchical decomposition of hallucinated concepts leads to a thorough hallucination analysis. Another novelty tied to the current work is the investigation of role hallucinations, being one of the first works to involve interconnections between visual concepts in hallucination detection. Overall, HalCECE recommends an explainable direction to the crucial field of VL hallucination detection, thus fostering trustworthy evaluation of current and future VL systems.
Authors: Lixu Wang, Bingqi Shang, Yi Li, Payal Mohapatra, Wei Dong, Xiao Wang, Qi Zhu
Abstract: Vision Transformers (ViTs), extensively pre-trained on large-scale datasets, have become essential to foundation models, allowing excellent performance on diverse downstream tasks with minimal adaptation. Consequently, there is growing interest in adapting pre-trained ViTs across various fields, including privacy-sensitive domains where clients are often reluctant to share their data. Existing adaptation methods typically require direct data access, rendering them infeasible under these constraints. A straightforward solution may be sending the pre-trained ViT to clients for local adaptation, which poses issues of model intellectual property protection and incurs heavy client computation overhead. To address these issues, we propose a novel split adaptation (SA) method that enables effective downstream adaptation while protecting data and models. SA, inspired by split learning (SL), segments the pre-trained ViT into a frontend and a backend, with only the frontend shared with the client for data representation extraction. But unlike regular SL, SA replaces frontend parameters with low-bit quantized values, preventing direct exposure of the model. SA allows the client to add bi-level noise to the frontend and the extracted data representations, ensuring data protection. Accordingly, SA incorporates data-level and model-level out-of-distribution enhancements to mitigate noise injection's impact on adaptation performance. Our SA focuses on the challenging few-shot adaptation and adopts patch retrieval augmentation for overfitting alleviation. Extensive experiments on multiple datasets validate SA's superiority over state-of-the-art methods and demonstrate its defense against advanced data reconstruction attacks while preventing model leakage with minimal computation cost on the client side. The source codes can be found at https://github.com/conditionWang/Split_Adaptation.
Authors: Earnest Paul Ijjina, Aniruddha Srinivas Joshi, Goutham Kanahasabai
Abstract: One of the basic requirements of humans is clothing and this approach aims to identify the garments selected by customer during shopping, from surveillance video. The existing approaches to detect garments were developed on western wear using datasets of western clothing. They do not address Indian garments due to the increased complexity. In this work, we propose a computer vision based framework to address this problem through video surveillance. The proposed framework uses the Mixture of Gaussians background subtraction algorithm to identify the foreground present in a video frame. The visual information present in this foreground is analysed using computer vision techniques such as image segmentation to detect the various garments, the customer is interested in. The framework was tested on a dataset, that comprises of CCTV videos from a garments store. When presented with raw surveillance footage, the proposed framework demonstrated its effectiveness in detecting the interest of customer in choosing their garments by achieving a high precision and recall.
Authors: Joshua Talks, Anna Kreshuk
Abstract: Model transfer presents a solution to the challenges of segmentation in the microscopy community, where the immense cost of labelling sufficient training data is a major bottleneck in the use of deep learning. With large quantities of imaging data produced across a wide range of imaging conditions, institutes also produce many bespoke models trained on specific source data which then get collected in model banks or zoos. As the number of available models grows, so does the need for an efficient and reliable model selection method for a specific target dataset of interest. We focus on the unsupervised regime where no labels are available for the target dataset. Building on previous work linking model generalisation and consistency under perturbation, we propose the first unsupervised transferability estimator for semantic and instance segmentation tasks which doesn't require access to source training data or target domain labels. We evaluate the method on multiple segmentation problems across microscopy modalities, finding a strong correlation between the rankings based on our estimator and rankings based on target dataset performance.
Authors: Earnest Paul Ijjina, Goutham Kanahasabai, Aniruddha Srinivas Joshi
Abstract: In the current information era, customer analytics play a key role in the success of any business. Since customer demographics primarily dictate their preferences, identification and utilization of age & gender information of customers in sales forecasting, may maximize retail sales. In this work, we propose a computer vision based approach to age and gender prediction in surveillance video. The proposed approach leverage the effectiveness of Wide Residual Networks and Xception deep learning models to predict age and gender demographics of the consumers. The proposed approach is designed to work with raw video captured in a typical CCTV video surveillance system. The effectiveness of the proposed approach is evaluated on real-life garment store surveillance video, which is captured by low resolution camera, under non-uniform illumination, with occlusions due to crowding, and environmental noise. The system can also detect customer facial expressions during purchase in addition to demographics, that can be utilized to devise effective marketing strategies for their customer base, to maximize sales.
Authors: Xueyang Wang, Zhixin Zheng, Jiandong Shao, Yule Duan, Liang-Jian Deng
Abstract: Recent advancements in convolutional neural network (CNN)-based techniques for remote sensing pansharpening have markedly enhanced image quality. However, conventional convolutional modules in these methods have two critical drawbacks. First, the sampling positions in convolution operations are confined to a fixed square window. Second, the number of sampling points is preset and remains unchanged. Given the diverse object sizes in remote sensing images, these rigid parameters lead to suboptimal feature extraction. To overcome these limitations, we introduce an innovative convolutional module, Adaptive Rectangular Convolution (ARConv). ARConv adaptively learns both the height and width of the convolutional kernel and dynamically adjusts the number of sampling points based on the learned scale. This approach enables ARConv to effectively capture scale-specific features of various objects within an image, optimizing kernel sizes and sampling locations. Additionally, we propose ARNet, a network architecture in which ARConv is the primary convolutional module. Extensive evaluations across multiple datasets reveal the superiority of our method in enhancing pansharpening performance over previous techniques. Ablation studies and visualization further confirm the efficacy of ARConv.
Authors: Ruiqi He, Zihan Wang, Xiang Zhou
Abstract: Cloth-Changing Person Re-identification (CC-ReID) aims to solve the challenge of identifying individuals across different temporal-spatial scenarios, viewpoints, and clothing variations. This field is gaining increasing attention in big data research and public security domains. Existing ReID research primarily relies on face recognition, gait semantic recognition, and clothing-irrelevant feature identification, which perform relatively well in scenarios with high-quality clothing change videos and images. However, these approaches depend on either single features or simple combinations of multiple features, making further performance improvements difficult. Additionally, limitations such as missing facial information, challenges in gait extraction, and inconsistent camera parameters restrict the broader application of CC-ReID. To address the above limitations, we innovatively propose a Tri-Stream Dynamic Weight Network (TSDW) that requires only images. This dynamic weighting network consists of three parallel feature streams: facial features, head-limb features, and global features. Each stream specializes in extracting its designated features, after which a gating network dynamically fuses confidence levels. The three parallel feature streams enhance recognition performance and reduce the impact of any single feature failure, thereby improving model robustness. Extensive experiments on benchmark datasets (e.g., PRCC, Celeb-reID, VC-Clothes) demonstrate that our method significantly outperforms existing state-of-the-art approaches.
Authors: Xuanchen Li, Jianyu Wang, Yuhao Cheng, Yikun Zeng, Xingyu Ren, Wenhan Zhu, Weiming Zhao, Yichao Yan
Abstract: Significant progress has been made for speech-driven 3D face animation, but most works focus on learning the motion of mesh/geometry, ignoring the impact of dynamic texture. In this work, we reveal that dynamic texture plays a key role in rendering high-fidelity talking avatars, and introduce a high-resolution 4D dataset \textbf{TexTalk4D}, consisting of 100 minutes of audio-synced scan-level meshes with detailed 8K dynamic textures from 100 subjects. Based on the dataset, we explore the inherent correlation between motion and texture, and propose a diffusion-based framework \textbf{TexTalker} to simultaneously generate facial motions and dynamic textures from speech. Furthermore, we propose a novel pivot-based style injection strategy to capture the complicity of different texture and motion styles, which allows disentangled control. TexTalker, as the first method to generate audio-synced facial motion with dynamic texture, not only outperforms the prior arts in synthesising facial motions, but also produces realistic textures that are consistent with the underlying facial movements. Project page: https://xuanchenli.github.io/TexTalk/.
Authors: Hanxun Yu, Wentong Li, Song Wang, Junbo Chen, Jianke Zhu
Abstract: Despite encouraging progress in 3D scene understanding, it remains challenging to develop an effective Large Multi-modal Model (LMM) that is capable of understanding and reasoning in complex 3D environments. Most previous methods typically encode 3D point and 2D image features separately, neglecting interactions between 2D semantics and 3D object properties, as well as the spatial relationships within the 3D environment. This limitation not only hinders comprehensive representations of 3D scene, but also compromises training and inference efficiency. To address these challenges, we propose a unified Instance-aware 3D Large Multi-modal Model (Inst3D-LMM) to deal with multiple 3D scene understanding tasks simultaneously. To obtain the fine-grained instance-level visual tokens, we first introduce a novel Multi-view Cross-Modal Fusion (MCMF) module to inject the multi-view 2D semantics into their corresponding 3D geometric features. For scene-level relation-aware tokens, we further present a 3D Instance Spatial Relation (3D-ISR) module to capture the intricate pairwise spatial relationships among objects. Additionally, we perform end-to-end multi-task instruction tuning simultaneously without the subsequent task-specific fine-tuning. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods across 3D scene understanding, reasoning and grounding tasks. Source code is available at https://github.com/hanxunyu/Inst3D-LMM
Authors: Songlin Dong, Yuhang He, Zhengdong Zhou, Haoyu Luo, Xing Wei, Alex C. Kot, Yihong Gong
Abstract: Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper focuses on the challenging yet practical multi-label class-incremental learning (MLCIL) problem. In addition to the challenge of catastrophic forgetting, MLCIL encounters issues related to feature confusion, encompassing inter-session and intra-feature confusion. To address these problems, we propose a novel MLCIL approach called class-independent increment (CLIN). Specifically, in contrast to existing methods that extract image-level features, we propose a class-independent incremental network (CINet) to extract multiple class-level embeddings for multi-label samples. It learns and preserves the knowledge of different classes by constructing class-specific tokens. On this basis, we develop two novel loss functions, optimizing the learning of class-specific tokens and class-level embeddings, respectively. These losses aim to distinguish between new and old classes, further alleviating the problem of feature confusion. Extensive experiments on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting on various MLCIL tasks.
Authors: Jiawen Zhu, Huayi Tang, Xin Chen, Xinying Wang, Dong Wang, Huchuan Lu
Abstract: Efficient tracking has garnered attention for its ability to operate on resource-constrained platforms for real-world deployment beyond desktop GPUs. Current efficient trackers mainly follow precision-oriented trackers, adopting a one-stream framework with lightweight modules. However, blindly adhering to the one-stream paradigm may not be optimal, as incorporating template computation in every frame leads to redundancy, and pervasive semantic interaction between template and search region places stress on edge devices. In this work, we propose a novel asymmetric Siamese tracker named \textbf{AsymTrack} for efficient tracking. AsymTrack disentangles template and search streams into separate branches, with template computing only once during initialization to generate modulation signals. Building on this architecture, we devise an efficient template modulation mechanism to unidirectional inject crucial cues into the search features, and design an object perception enhancement module that integrates abstract semantics and local details to overcome the limited representation in lightweight tracker. Extensive experiments demonstrate that AsymTrack offers superior speed-precision trade-offs across different platforms compared to the current state-of-the-arts. For instance, AsymTrack-T achieves 60.8\% AUC on LaSOT and 224/81/84 FPS on GPU/CPU/AGX, surpassing HiT-Tiny by 6.0\% AUC with higher speeds. The code is available at https://github.com/jiawen-zhu/AsymTrack.
Authors: Zhan Qu, Shuzhou Yuan, Michael F\"arber, Marius Brennfleck, Niklas Wartha, Anton Stephan
Abstract: Wake vortices - strong, coherent air turbulences created by aircraft - pose a significant risk to aviation safety and therefore require accurate and reliable detection methods. In this paper, we present an advanced, explainable machine learning method that utilizes Light Detection and Ranging (LiDAR) data for effective wake vortex detection. Our method leverages a dynamic graph CNN (DGCNN) with semantic segmentation to partition a 3D LiDAR point cloud into meaningful segments. Further refinement is achieved through clustering techniques. A novel feature of our research is the use of a perturbation-based explanation technique, which clarifies the model's decision-making processes for air traffic regulators and controllers, increasing transparency and building trust. Our experimental results, based on measured and simulated LiDAR scans compared against four baseline methods, underscore the effectiveness and reliability of our approach. This combination of semantic segmentation and clustering for real-time wake vortex tracking significantly advances aviation safety measures, ensuring that these are both effective and comprehensible.
Authors: JunYao Kaung, HongWei Ge
Abstract: Remote sensing change detection (CD) has made significant advancements with the adoption of Convolutional Neural Networks (CNNs) and Transformers. While CNNs offer powerful feature extraction, they are constrained by receptive field limitations, and Transformers suffer from quadratic complexity when processing long sequences, restricting scalability. The Mamba architecture provides an appealing alternative, offering linear complexity and high parallelism. However, its inherent 1D processing structure causes a loss of spatial information in 2D vision tasks. This paper addresses this limitation by proposing an efficient framework based on a Vision Mamba variant that enhances its ability to capture 2D spatial information while maintaining the linear complexity characteristic of Mamba. The framework employs a 2DMamba encoder to effectively learn global spatial contextual information from multi-temporal images. For feature fusion, we introduce a 2D scan-based, channel-parallel scanning strategy combined with a spatio-temporal feature fusion method, which adeptly captures both local and global change information, alleviating spatial discontinuity issues during fusion. In the decoding stage, we present a feature change flow-based decoding method that improves the mapping of feature change information from low-resolution to high-resolution feature maps, mitigating feature shift and misalignment. Extensive experiments on benchmark datasets such as LEVIR-CD+ and WHU-CD demonstrate the superior performance of our framework compared to state-of-the-art methods, showcasing the potential of Vision Mamba for efficient and accurate remote sensing change detection.
Authors: Runyi Li, Xuanyu Zhang, Chuhan Tong, Zhipei Xu, Jian Zhang
Abstract: With the advancement of AIGC technologies, the modalities generated by models have expanded from images and videos to 3D objects, leading to an increasing number of works focused on 3D Gaussian Splatting (3DGS) generative models. Existing research on copyright protection for generative models has primarily concentrated on watermarking in image and text modalities, with little exploration into the copyright protection of 3D object generative models. In this paper, we propose the first bit watermarking framework for 3DGS generative models, named GaussianSeal, to enable the decoding of bits as copyright identifiers from the rendered outputs of generated 3DGS. By incorporating adaptive bit modulation modules into the generative model and embedding them into the network blocks in an adaptive way, we achieve high-precision bit decoding with minimal training overhead while maintaining the fidelity of the model's outputs. Experiments demonstrate that our method outperforms post-processing watermarking approaches for 3DGS objects, achieving superior performance of watermark decoding accuracy and preserving the quality of the generated results.
Authors: Shangzhe Di, Zhelun Yu, Guanghao Zhang, Haoyuan Li, Tao Zhong, Hao Cheng, Bolin Li, Wanggui He, Fangxun Shu, Hao Jiang
Abstract: We propose ReKV, a novel training-free approach that enables efficient streaming video question-answering (StreamingVQA), by seamlessly integrating with existing Video Large Language Models (Video-LLMs). Traditional VideoQA systems struggle with long videos, as they must process entire videos before responding to queries, and repeat this process for each new question. In contrast, our approach analyzes long videos in a streaming manner, allowing for prompt responses as soon as user queries are received. Building on a common Video-LLM, we first incorporate a sliding-window attention mechanism, ensuring that input frames attend to a limited number of preceding frames, thereby reducing computational overhead. To prevent information loss, we store processed video key-value caches (KV-Caches) in RAM and disk, reloading them into GPU memory as needed. Additionally, we introduce a retrieval method that leverages an external retriever or the parameters within Video-LLMs to retrieve only query-relevant KV-Caches, ensuring both efficiency and accuracy in question answering. ReKV enables the separation of video encoding and question-answering across different processes and GPUs, significantly enhancing the efficiency of StreamingVQA. Through comprehensive experimentation, we validate the efficacy and practicality of our approach, which significantly boosts efficiency and enhances applicability over existing VideoQA models.
Authors: Yujie Lei, Wenjie Sun, Sen Jia, Qingquan Li, Jie Zhang
Abstract: Challenges in remote sensing object detection (RSOD), such as high inter-class similarity, imbalanced foreground-background distribution, and the small size of objects in remote sensing images significantly hinder detection accuracy. Moreo-ver, the trade-off between model accuracy and computational complexity poses additional constraints on the application of RSOD algorithms. To address these issues, this study proposes an efficient and lightweight RSOD algorithm integrat-ing multi-scale receptive fields and foreground focus mechanism, named RFWNet. Specifically, we proposed a lightweight backbone network Receptive Field Adaptive Selection Network (RFASNet), leveraging the rich context infor-mation of remote sensing images to enhance class separability. Additionally, we developed a Foreground Background Separation Module (FBSM) consisting of a background redundant information filtering module and a foreground information enhancement module to emphasize critical regions within images while filtering redundant background information. Finally, we designed a loss function, the Weighted CIoU-Wasserstein (WCW) loss, which weights the IoU-based loss by using the Normalized Wasserstein Distance to mitigate model sensitivity to small object position deviations. Experimental evaluations on the DOTA V1.0 and NWPU VHR-10 datasets demonstrate that RFWNet achieves advanced perfor-mance with 6.0M parameters and can achieves 52 FPS.
Authors: Yanjun Li, Zhaoyang Li, Honghui Chen, Lizhi Xu
Abstract: Video Scene Graph Generation (VidSGG) aims to capture dynamic relationships among entities by sequentially analyzing video frames and integrating visual and semantic information. However, VidSGG is challenged by significant biases that skew predictions. To mitigate these biases, we propose a VIsual and Semantic Awareness (VISA) framework for unbiased VidSGG. VISA addresses visual bias through memory-enhanced temporal integration that enhances object representations and concurrently reduces semantic bias by iteratively integrating object features with comprehensive semantic information derived from triplet relationships. This visual-semantics dual debiasing approach results in more unbiased representations of complex scene dynamics. Extensive experiments demonstrate the effectiveness of our method, where VISA outperforms existing unbiased VidSGG approaches by a substantial margin (e.g., +13.1% improvement in mR@20 and mR@50 for the SGCLS task under Semi Constraint).
Authors: Sohan Patnaik, Rishabh Jain, Balaji Krishnamurthy, Mausoom Sarkar
Abstract: Visual layouts are essential in graphic design fields such as advertising, posters, and web interfaces. The application of generative models for content-aware layout generation has recently gained traction. However, these models fail to understand the contextual aesthetic requirements of layout design and do not align with human-like preferences, primarily treating it as a prediction task without considering the final rendered output. To overcome these problems, we offer Aesthetic-Aware Preference Alignment(AAPA), a novel technique to train a Multi-modal Large Language Model (MLLM) for layout prediction that uses MLLM's aesthetic preferences for Direct Preference Optimization over graphic layouts. We propose a data filtering protocol utilizing our layout-quality heuristics for AAPA to ensure training happens on high-quality layouts. Additionally, we introduce a novel evaluation metric that uses another MLLM to compute the win rate of the generated layout against the ground-truth layout based on aesthetics criteria. We also demonstrate the applicability of AAPA for MLLMs of varying scales (1B to 8B parameters) and LLM families (Qwen, Phi, InternLM). By conducting thorough qualitative and quantitative analyses, we verify the efficacy of our approach on two challenging benchmarks - Crello and Webui, showcasing 17%, and 16 improvement over current State-of-The-Art methods, thereby highlighting the potential of MLLMs in aesthetic-aware layout generation.
Authors: Siddhartha Gairola, Moritz B\"ohle, Francesco Locatello, Bernt Schiele
Abstract: Post-hoc importance attribution methods are a popular tool for "explaining" Deep Neural Networks (DNNs) and are inherently based on the assumption that the explanations can be applied independently of how the models were trained. Contrarily, in this work we bring forward empirical evidence that challenges this very notion. Surprisingly, we discover a strong dependency on and demonstrate that the training details of a pre-trained model's classification layer (less than 10 percent of model parameters) play a crucial role, much more than the pre-training scheme itself. This is of high practical relevance: (1) as techniques for pre-training models are becoming increasingly diverse, understanding the interplay between these techniques and attribution methods is critical; (2) it sheds light on an important yet overlooked assumption of post-hoc attribution methods which can drastically impact model explanations and how they are interpreted eventually. With this finding we also present simple yet effective adjustments to the classification layers, that can significantly enhance the quality of model explanations. We validate our findings across several visual pre-training frameworks (fully-supervised, self-supervised, contrastive vision-language training) and analyse how they impact explanations for a wide range of attribution methods on a diverse set of evaluation metrics.
Authors: Aupendu Kar, Sobhan K. Dhara, Debashis Sen, Prabir K. Biswas
Abstract: Real-world low-light images captured by imaging devices suffer from poor visibility and require a domain-specific enhancement to produce artifact-free outputs that reveal details. In this paper, we propose an unpaired low-light image enhancement network leveraging novel controlled transformation-based self-supervision and unpaired self-conditioning strategies. The model determines the required degrees of enhancement at the input image pixels, which are learned from the unpaired low-lit and well-lit images without any direct supervision. The self-supervision is based on a controlled transformation of the input image and subsequent maintenance of its enhancement in spite of the transformation. The self-conditioning performs training of the model on unpaired images such that it does not enhance an already-enhanced image or a well-lit input image. The inherent noise in the input low-light images is handled by employing low gradient magnitude suppression in a detail-preserving manner. In addition, our noise handling is self-conditioned by preventing the denoising of noise-free well-lit images. The training based on low-light image enhancement-specific attributes allows our model to avoid paired supervision without compromising significantly in performance. While our proposed self-supervision aids consistent enhancement, our novel self-conditioning facilitates adequate enhancement. Extensive experiments on multiple standard datasets demonstrate that our model, in general, outperforms the state-of-the-art both quantitatively and subjectively. Ablation studies show the effectiveness of our self-supervision and self-conditioning strategies, and the related loss functions.
Authors: Yante Li, Hanwen Qi, Haoyu Chen, Xinlian Liang, Guoying Zhao
Abstract: In environmental protection, tree monitoring plays an essential role in maintaining and improving ecosystem health. However, precise monitoring is challenging because existing datasets fail to capture continuous fine-grained changes in trees due to low-resolution images and high acquisition costs. In this paper, we introduce UAVTC, a large-scale, long-term, high-resolution dataset collected using UAVs equipped with cameras, specifically designed to detect individual Tree Changes (TCs). UAVTC includes rich annotations and statistics based on biological knowledge, offering a fine-grained view for tree monitoring. To address environmental influences and effectively model the hierarchical diversity of physiological TCs, we propose a novel Hyperbolic Siamese Network (HSN) for TC detection, enabling compact and hierarchical representations of dynamic tree changes. Extensive experiments show that HSN can effectively capture complex hierarchical changes and provide a robust solution for fine-grained TC detection. In addition, HSN generalizes well to cross-domain face anti-spoofing task, highlighting its broader significance in AI. We believe our work, combining ecological insights and interdisciplinary expertise, will benefit the community by offering a new benchmark and innovative AI technologies.
Authors: Chisako Hayashi, Shinichiro Mori, Yasukuni Mori, Lim Taehyeung, Hiroki Suyari, Hitoshi Ishikawa
Abstract: Purpose The purpose of this study was to develop and evaluate a deep neural network (DNN) capable of generating flat-panel detector (FPD) images from digitally reconstructed radiography (DRR) images in lung cancer treatment, with the aim of improving clinical workflows in image-guided radiotherapy. Methods A modified CycleGAN architecture was trained on paired DRR-FPD image data obtained from patients with lung tumors. The training dataset consisted of over 400 DRR-FPD image pairs, and the final model was evaluated on an independent set of 100 FPD images. Mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Kernel Inception Distance (KID) were used to quantify the similarity between synthetic and ground-truth FPD images. Computation time for generating synthetic images was also measured. Results Despite some positional mismatches in the DRR-FPD pairs, the synthetic FPD images closely resembled the ground-truth FPD images. The proposed DNN achieved notable improvements over both input DRR images and a U-Net-based method in terms of MAE, PSNR, SSIM, and KID. The average image generation time was on the order of milliseconds per image, indicating its potential for real-time application. Qualitative evaluations showed that the DNN successfully reproduced image noise patterns akin to real FPD images, reducing the need for manual noise adjustments. Conclusions The proposed DNN effectively converted DRR images into realistic FPD images for thoracic cases, offering a fast and practical method that could streamline patient setup verification and enhance overall clinical workflow. Future work should validate the model across different imaging systems and address remaining challenges in marker visualization, thereby fostering broader clinical adoption.
Authors: Gargi V. Pillai, Ashish Verma, Debashis Sen
Abstract: Anomaly detection in videos is a challenging task as anomalies in different videos are of different kinds. Therefore, a promising way to approach video anomaly detection is by learning the non-anomalous nature of the video at hand. To this end, we propose a one-class few-shot learning driven transformer based approach for anomaly detection in videos that is self-context aware. Features from the first few consecutive non-anomalous frames in a video are used to train the transformer in predicting the non-anomalous feature of the subsequent frame. This takes place under the attention of a self-context learned from the input features themselves. After the learning, given a few previous frames, the video-specific transformer is used to infer if a frame is anomalous or not by comparing the feature predicted by it with the actual. The effectiveness of the proposed method with respect to the state-of-the-art is demonstrated through qualitative and quantitative results on different standard datasets. We also study the positive effect of the self-context used in our approach.
Authors: Wenke E, Chao Yuan, Li Li, Yixin Sun, Yona Falinie A. Gaus, Amir Atapour-Abarghouei, Toby P. Breckon
Abstract: We present Dur360BEV, a novel spherical camera autonomous driving dataset equipped with a high-resolution 128-channel 3D LiDAR and a RTK-refined GNSS/INS system, along with a benchmark architecture designed to generate Bird-Eye-View (BEV) maps using only a single spherical camera. This dataset and benchmark address the challenges of BEV generation in autonomous driving, particularly by reducing hardware complexity through the use of a single 360-degree camera instead of multiple perspective cameras. Within our benchmark architecture, we propose a novel spherical-image-to-BEV (SI2BEV) module that leverages spherical imagery and a refined sampling strategy to project features from 2D to 3D. Our approach also includes an innovative application of Focal Loss, specifically adapted to address the extreme class imbalance often encountered in BEV segmentation tasks. Through extensive experiments, we demonstrate that this application of Focal Loss significantly improves segmentation performance on the Dur360BEV dataset. The results show that our benchmark not only simplifies the sensor setup but also achieves competitive performance.
Authors: Zhiqi Kang, Liyuan Wang, Xingxing Zhang, Karteek Alahari
Abstract: General continual learning (GCL) is a broad concept to describe real-world continual learning (CL) problems, which are often characterized by online data streams without distinct transitions between tasks, i.e., blurry task boundaries. Such requirements result in poor initial performance, limited generalizability, and severe catastrophic forgetting, heavily impacting the effectiveness of mainstream GCL models trained from scratch. While the use of a frozen pretrained backbone with appropriate prompt tuning can partially address these challenges, such prompt-based methods remain suboptimal for CL of remaining tunable parameters on the fly. In this regard, we propose an innovative approach named MISA (Mask and Initial Session Adaption) to advance prompt-based methods in GCL. It includes a forgetting-aware initial session adaption that employs pretraining data to initialize prompt parameters and improve generalizability, as well as a non-parametric logit mask of the output layers to mitigate catastrophic forgetting. Empirical results demonstrate substantial performance gains of our approach compared to recent competitors, especially without a replay buffer (e.g., up to 18.39%, 22.06%, and 11.96% performance lead on CIFAR-100, Tiny-ImageNet, and ImageNet-R, respectively). Moreover, our approach features the plug-in nature for prompt-based methods, independence of replay, ease of implementation, and avoidance of CL-relevant hyperparameters, serving as a strong baseline for GCL research. Our source code is publicly available at https://github.com/kangzhiq/MISA
Authors: Hao Ding, Xu Lian, Mathias Unberath
Abstract: Surgical phase recognition from video enables various downstream applications. Transformer-based sliding window approaches have set the state-of-the-art by capturing rich spatial-temporal features. However, while transformers can theoretically handle arbitrary-length sequences, in practice they are limited by memory and compute constraints, resulting in fixed context windows that struggle with maintaining temporal consistency across lengthy surgical procedures. This often leads to fragmented predictions and limited procedure-level understanding. To address these challenges, we propose Memory of Surgery (MoS), a framework that enriches temporal modeling by incorporating both semantic interpretable long-term surgical history and short-term impressions. MoSFormer, our enhanced transformer architecture, integrates MoS using a carefully designed encoding and fusion mechanism. We further introduce step filtering to refine history representation and develop a memory caching pipeline to improve training and inference stability, mitigating shortcut learning and overfitting. MoSFormer demonstrates state-of-the-art performance on multiple benchmarks. On the Challenging BernBypass70 benchmark, it attains 88.0 video-level accuracy and phase-level metrics of 70.7 precision, 68.7 recall, and 66.3 F1 score, outperforming its baseline with 2.1 video-level accuracy and phase-level metrics of 4.6 precision, 3.6 recall, and 3.8 F1 score. Further studies confirms the individual and combined benefits of long-term and short-term memory components through ablation and counterfactual inference. Qualitative results shows improved temporal consistency. The augmented temporal context enables procedure-level understanding, paving the way for more comprehensive surgical video analysis.
Authors: Yiyang Lin, Danling Jiang, Xinyu Liu, Yun Miao, Yixuan Yuan
Abstract: In the immunohistochemical (IHC) analysis during surgery, frozen-section (FS) images are used to determine the benignity or malignancy of the tumor. However, FS image faces problems such as image contamination and poor nuclear detail, which may disturb the pathologist's diagnosis. In contrast, formalin-fixed and paraffin-embedded (FFPE) image has a higher staining quality, but it requires quite a long time to prepare and thus is not feasible during surgery. To help pathologists observe IHC images with high quality in surgery, this paper proposes a Cross-REsolution compensATed and multi-frequency Enhanced FS-to-FFPE (CREATE-FFPE) stain transfer framework, which is the first FS-to-FFPE method for the intraoperative IHC images. To solve the slide contamination and poor nuclear detail mentioned above, we propose the cross-resolution compensation module (CRCM) and the wavelet detail guidance module (WDGM). Specifically, CRCM compensates for information loss due to contamination by providing more tissue information across multiple resolutions, while WDGM produces the desirable details in a wavelet way, and the details can be used to guide the stain transfer to be more precise. Experiments show our method can beat all the competing methods on our dataset. In addition, the FID has decreased by 44.4%, and KID*100 has decreased by 71.2% by adding the proposed CRCM and WDGM in ablation studies, and the performance of a downstream microsatellite instability prediction task with public dataset can be greatly improved by performing our FS-to-FFPE stain transfer.
Authors: Yang Ding, Can Han, Sijia Du, Yaqi Wang, Dahong Qian
Abstract: Real-time acquisition of accurate depth of scene is essential for automated robotic minimally invasive surgery, and stereo matching with binocular endoscopy can generate such depth. However, existing algorithms struggle with ambiguous tissue boundaries and real-time performance in prevalent high-resolution endoscopic scenes. We propose LightEndoStereo, a lightweight real-time stereo matching method for endoscopic images. We introduce a 3D Mamba Coordinate Attention module to streamline the cost aggregation process by generating position-sensitive attention maps and capturing long-range dependencies across spatial dimensions using the Mamba block. Additionally, we introduce a High-Frequency Disparity Optimization module to refine disparity estimates at tissue boundaries by enhancing high-frequency information in the wavelet domain. Our method is evaluated on the SCARED and SERV-CT datasets, achieving state-of-the-art matching accuracy and a real-time inference speed of 42 FPS. The code is available at https://github.com/Sonne-Ding/LightEndoStereo.
Authors: Wenhui Lei, Anqi Li, Yusheng Tan, Hanyu Chen, Xiaofan Zhang
Abstract: Foundation Models (FMs) in computational pathology (CPath) have significantly advanced the extraction of meaningful features from histopathology image datasets, achieving strong performance across various clinical tasks. Despite their impressive performance, these models often exhibit variability when applied to different tasks, prompting the need for a unified framework capable of consistently excelling across various applications. In this work, we propose Shazam, a novel framework designed to efficiently combine multiple CPath models. Unlike previous approaches that train a fixed-parameter FM, Shazam dynamically extracts and refines information from diverse FMs for each specific task. To ensure that each FM contributes effectively without dominance, a novel distillation strategy is applied, guiding the student model with features from all teacher models, which enhances its generalization ability. Experimental results on two pathology patch classification datasets demonstrate that Shazam outperforms existing CPath models and other fusion methods. Its lightweight, flexible design makes it a promising solution for improving CPath analysis in real-world settings. Code will be available at https://github.com/Tuner12/Shazam.
Authors: Jinjiang You, Hewei Wang, Yijie Li, Mingxiao Huo, Long Van Tran Ha, Mingyuan Ma, Jinfeng Xu, Puzhen Wu, Shubham Garg, Wei Pu
Abstract: Calibrating large-scale camera arrays, such as those in dome-based setups, is time-intensive and typically requires dedicated captures of known patterns. While extrinsics in such arrays are fixed due to the physical setup, intrinsics often vary across sessions due to factors like lens adjustments or temperature changes. In this paper, we propose a dense-feature-driven multi-frame calibration method that refines intrinsics directly from scene data, eliminating the necessity for additional calibration captures. Our approach enhances traditional Structure-from-Motion (SfM) pipelines by introducing an extrinsics regularization term to progressively align estimated extrinsics with ground-truth values, a dense feature reprojection term to reduce keypoint errors by minimizing reprojection loss in the feature space, and an intrinsics variance term for joint optimization across multiple frames. Experiments on the Multiface dataset show that our method achieves nearly the same precision as dedicated calibration processes, and significantly enhances intrinsics and 3D reconstruction accuracy. Fully compatible with existing SfM pipelines, our method provides an efficient and practical plug-and-play solution for large-scale camera setups. Our code is publicly available at: https://github.com/YJJfish/Multi-Cali-Anything
Authors: Junyao Gao, Yanan Sun, Fei Shen, Xin Jiang, Zhening Xing, Kai Chen, Cairong Zhao
Abstract: In this paper, we present FaceShot, a novel training-free portrait animation framework designed to bring any character into life from any driven video without fine-tuning or retraining. We achieve this by offering precise and robust reposed landmark sequences from an appearance-guided landmark matching module and a coordinate-based landmark retargeting module. Together, these components harness the robust semantic correspondences of latent diffusion models to produce facial motion sequence across a wide range of character types. After that, we input the landmark sequences into a pre-trained landmark-driven animation model to generate animated video. With this powerful generalization capability, FaceShot can significantly extend the application of portrait animation by breaking the limitation of realistic portrait landmark detection for any stylized character and driven video. Also, FaceShot is compatible with any landmark-driven animation model, significantly improving overall performance. Extensive experiments on our newly constructed character benchmark CharacBench confirm that FaceShot consistently surpasses state-of-the-art (SOTA) approaches across any character domain. More results are available at our project website https://faceshot2024.github.io/faceshot/.
Authors: Dilxat Muhtar, Enzhuo Zhang, Zhenshi Li, Feng Gu, Yanglangxing He, Pengfeng Xiao, Xueliang Zhang
Abstract: Vision-Language Models (VLMs) have demonstrated great potential in interpreting remote sensing (RS) images through language-guided semantic understanding. However, the effectiveness of these VLMs critically depends on high-quality image-text training data that captures rich semantic relationships between visual content and language descriptions. Unlike natural images, RS lacks large-scale interleaved image-text pairs from web data, making data collection challenging. While current approaches rely primarily on rule-based methods or flagship VLMs for data synthesis, a systematic framework for automated quality assessment of such synthetically generated RS visionlanguage data is notably absent. To fill this gap, we propose a novel score model trained on large-scale RS visionlanguage preference data for automated quality assessment. Our empirical results demonstrate that fine-tuning CLIP or advanced VLMs (e.g., Qwen2-VL) with the top 30% of data ranked by our score model achieves superior interpretation accuracy compared to both full-data fine-tuning and CLIP-score-based ranking approaches. Furthermore, we demonstrate applications of our scoring model for reinforcement learning (RL) training and best-of-N (BoN) testtime scaling, enabling significant improvements in VLM performance for RS tasks.
Authors: Anyang Ji, Qingbo Kang, Wei Xu, Changfan Wang, Kang Li, Qicheng Lao
Abstract: The emergence of large-scale pre-trained vision foundation models has greatly advanced the medical imaging field through the pre-training and fine-tuning paradigm. However, selecting appropriate medical data for downstream fine-tuning remains a significant challenge considering its annotation cost, privacy concerns, and the detrimental effects of confounding variables. In this work, we present a confounder-aware medical data selection approach for medical dataset curation aiming to select minimal representative data by strategically mitigating the undesirable impact of confounding variables while preserving the natural distribution of the dataset. Our approach first identifies confounding variables within data and then develops a distance-based data selection strategy for confounder-aware sampling with a constrained budget in the data size. We validate the superiority of our approach through extensive experiments across diverse medical imaging modalities, highlighting its effectiveness in addressing the substantial impact of confounding variables and enhancing the fine-tuning efficiency in the medical imaging domain, compared to other data selection approaches.
Authors: Liao Shen, Tianqi Liu, Huiqiang Sun, Jiaqi Li, Zhiguo Cao, Wei Li, Chen Change Loy
Abstract: Recent advances in 3D Gaussian Splatting (3D-GS) have shown remarkable success in representing 3D scenes and generating high-quality, novel views in real-time. However, 3D-GS and its variants assume that input images are captured based on pinhole imaging and are fully in focus. This assumption limits their applicability, as real-world images often feature shallow depth-of-field (DoF). In this paper, we introduce DoF-Gaussian, a controllable depth-of-field method for 3D-GS. We develop a lens-based imaging model based on geometric optics principles to control DoF effects. To ensure accurate scene geometry, we incorporate depth priors adjusted per scene, and we apply defocus-to-focus adaptation to minimize the gap in the circle of confusion. We also introduce a synthetic dataset to assess refocusing capabilities and the model's ability to learn precise lens parameters. Our framework is customizable and supports various interactive applications. Extensive experiments confirm the effectiveness of our method. Our project is available at https://dof-gaussian.github.io.
Authors: Fei Teng, Buyin Deng, Boyuan Zheng, Kai Luo, Kunyu Peng, Jiaming Zhang, Kailun Yang
Abstract: Field of Parallax (FoP)}, a spatial field that distills the common features from different LF representations to provide flexible and consistent support for multi-task learning. FoP is built upon three core features--projection difference, adjacency divergence, and contextual consistency--which are essential for cross-task adaptability. To implement FoP, we design a two-step angular adapter: the first step captures angular-specific differences, while the second step consolidates contextual consistency to ensure robust representation. Leveraging the FoP-based representation, we introduce the LFX framework, the first to handle arbitrary LF representations seamlessly, unifying LF multi-task vision. We evaluated LFX across three different tasks, achieving new state-of-the-art results, compared with previous task-specific architectures: 84.74% in mIoU for semantic segmentation on UrbanLF, 0.84% in AP for object detection on PKU, and 0.030 in MAE and 0.026 in MAE for salient object detection on Duftv2 and PKU, respectively. The source code will be made publicly available at https://github.com/warriordby/LFX.
Authors: Zihao Luo, Zijun Gao, Wenjun Liao, Shichuan Zhang, Guotai Wang, Xiangde Luo
Abstract: Accurate lymph node (LN) segmentation is critical in radiotherapy treatment and prognosis analysis, but is limited by the need for large annotated datasets. While deep learning-based segmentation foundation models show potential in developing high-performing models with fewer samples, their medical adaptation faces LN domain-specific prior deficiencies and inefficient few-shot fine-tuning for complex clinical practices, highlighting the necessity of an LN segmentation foundation model. In this work, we annotated 36,106 visible LNs from 3,346 publicly available head-and-neck CT scans to establish a robust LN segmentation model (nnUNetv2). Building on this, we propose Dynamic Gradient Sparsification Training (DGST), a few-shot fine-tuning approach that preserves foundational knowledge while dynamically updating the most critical parameters of the LN segmentation model with few annotations. We validate it on two publicly available LN segmentation datasets: SegRap2023 and LNQ2023. The results show that DGST outperforms existing few-shot fine-tuning methods, achieving satisfactory performance with limited labeled data. We release the dataset, models and all implementations to facilitate relevant research: https://github.com/Zihaoluoh/LN-Seg-FM.
Authors: Fangming Shi, Jinzhen Liu, Xiangqian Meng, Yapeng Zhou, Hui Xiong
Abstract: This paper presents a multi-resolution reconstruction method for Electrical Impedance Tomography (EIT), referred to as MR-EIT, which is capable of operating in both supervised and unsupervised learning modes. MR-EIT integrates an ordered feature extraction module and an unordered coordinate feature expression module. The former achieves the mapping from voltage to two-dimensional conductivity features through pre-training, while the latter realizes multi-resolution reconstruction independent of the order and size of the input sequence by utilizing symmetric functions and local feature extraction mechanisms. In the data-driven mode, MR-EIT reconstructs high-resolution images from low-resolution data of finite element meshes through two stages of pre-training and joint training, and demonstrates excellent performance in simulation experiments. In the unsupervised learning mode, MR-EIT does not require pre-training data and performs iterative optimization solely based on measured voltages to rapidly achieve image reconstruction from low to high resolution. It shows robustness to noise and efficient super-resolution reconstruction capabilities in both simulation and real water tank experiments. Experimental results indicate that MR-EIT outperforms the comparison methods in terms of Structural Similarity (SSIM) and Relative Image Error (RIE), especially in the unsupervised learning mode, where it can significantly reduce the number of iterations and improve image reconstruction quality.
Authors: Astitva Kamble, Vani Bandodkar, Saakshi Dharmadhikary, Veena Anand, Pradyut Kumar Sanki, Mei X. Wu, Biswabandhu Jana
Abstract: Endoscopy serves as an essential procedure for evaluating the gastrointestinal (GI) tract and plays a pivotal role in identifying GI-related disorders. Recent advancements in deep learning have demonstrated substantial progress in detecting abnormalities through intricate models and data augmentation methods.This research introduces a novel approach to enhance classification accuracy using 8,000 labeled endoscopic images from the Kvasir dataset, categorized into eight distinct classes. Leveraging EfficientNetB3 as the backbone, the proposed architecture eliminates reliance on data augmentation while preserving moderate model complexity. The model achieves a test accuracy of 94.25%, alongside precision and recall of 94.29% and 94.24% respectively. Furthermore, Local Interpretable Model-agnostic Explanation (LIME) saliency maps are employed to enhance interpretability by defining critical regions in the images that influenced model predictions. Overall, this work highlights the importance of AI in advancing medical imaging by combining high classification accuracy with interpretability.
Authors: Wenzhao Xiang, Chang Liu, Hongyang Yu, Xilin Chen
Abstract: Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain abundant redundant information, leading the pixel-based MIM reconstruction process to focus excessively on finer details such as textures, thus prolonging training times unnecessarily. Addressing this challenge requires a shift towards a compact representation of features during MIM reconstruction. Frequency domain analysis provides a promising avenue for achieving compact image feature representation. In contrast to the commonly used Fourier transform, wavelet transform not only offers frequency information but also preserves spatial characteristics and multi-level features of the image. Additionally, the multi-level decomposition process of wavelet transformation aligns well with the hierarchical architecture of modern neural networks. In this study, we leverage wavelet transform as a tool for efficient representation learning to expedite the training process of MIM. Specifically, we conduct multi-level decomposition of images using wavelet transform, utilizing wavelet coefficients from different levels to construct distinct reconstruction targets representing various frequencies and scales. These reconstruction targets are then integrated into the MIM process, with adjustable weights assigned to prioritize the most crucial information. Extensive experiments demonstrate that our method achieves comparable or superior performance across various downstream tasks while exhibiting higher training efficiency.
Authors: Ukcheol Shin, Kyunghyun Lee, Jean Oh
Abstract: Deploying depth estimation networks in the real world requires high-level robustness against various adverse conditions to ensure safe and reliable autonomy. For this purpose, many autonomous vehicles employ multi-modal sensor systems, including an RGB camera, NIR camera, thermal camera, LiDAR, or Radar. They mainly adopt two strategies to use multiple sensors: modality-wise and multi-modal fused inference. The former method is flexible but memory-inefficient, unreliable, and vulnerable. Multi-modal fusion can provide high-level reliability, yet it needs a specialized architecture. In this paper, we propose an effective solution, named align-and-fuse strategy, for the depth estimation from multi-spectral images. In the align stage, we align embedding spaces between multiple spectrum bands to learn shareable representation across multi-spectral images by minimizing contrastive loss of global and spatially aligned local features with geometry cue. After that, in the fuse stage, we train an attachable feature fusion module that can selectively aggregate the multi-spectral features for reliable and robust prediction results. Based on the proposed method, a single-depth network can achieve both spectral-invariant and multi-spectral fused depth estimation while preserving reliability, memory efficiency, and flexibility.
Authors: Zhe Wang, Xulei Yang
Abstract: There has been huge progress on video action recognition in recent years. However, many works focus on tweaking existing 2D backbones due to the reliance of ImageNet pretraining, which restrains the models from achieving higher efficiency for video recognition. In this work we introduce a simple and very efficient 3D convolutional neural network for video action recognition. The design of the building block consists of a channel-wise convolution, followed by a spatial group convolution, and finally a temporal convolution. We evaluate the performance and efficiency of our proposed network on several video action recognition datasets by directly training on the target dataset without relying on pertaining. On Something-Something-V1&V2, Kinetics-400 and Multi-Moments in Time, our network can match or even surpass the performance of other models which are several times larger. On the fine-grained action recognition dataset FineGym, we beat the previous state-of-the-art accuracy achieved with 2-stream methods by more than 5% using only RGB input.
Authors: Zikuan Li, Honghua Chen, Yuecheng Wang, Sibo Wu, Mingqiang Wei, Jun Wang
Abstract: Extracting geometric edges from unstructured point clouds remains a significant challenge, particularly in thin-walled structures that are commonly found in everyday objects. Traditional geometric methods and recent learning-based approaches frequently struggle with these structures, as both rely heavily on sufficient contextual information from local point neighborhoods. However, 3D measurement data of thin-walled structures often lack the accurate, dense, and regular neighborhood sampling required for reliable edge extraction, resulting in degraded performance. In this work, we introduce STAR-Edge, a novel approach designed for detecting and refining edge points in thin-walled structures. Our method leverages a unique representation-the local spherical curve-to create structure-aware neighborhoods that emphasize co-planar points while reducing interference from close-by, non-co-planar surfaces. This representation is transformed into a rotation-invariant descriptor, which, combined with a lightweight multi-layer perceptron, enables robust edge point classification even in the presence of noise and sparse or irregular sampling. Besides, we also use the local spherical curve representation to estimate more precise normals and introduce an optimization function to project initially identified edge points exactly on the true edges. Experiments conducted on the ABC dataset and thin-walled structure-specific datasets demonstrate that STAR-Edge outperforms existing edge detection methods, showcasing better robustness under various challenging conditions.
Authors: Jia-Xuan Jiang, Wenhui Lei, Yifeng Wu, Hongtao Wu, Furong Li, Yining Xie, Xiaofan Zhang, Zhong Wang
Abstract: Medical Foundation Models (MFMs), trained on large-scale datasets, have demonstrated superior performance across various tasks. However, these models still struggle with domain gaps in practical applications. Specifically, even after fine-tuning on source-domain data, task-adapted foundation models often perform poorly in the target domain. To address this challenge, we propose a few-shot unsupervised domain adaptation (UDA) framework for MFMs, named MFM-DA, which only leverages a limited number of unlabeled target-domain images. Our approach begins by training a Denoising Diffusion Probabilistic Model (DDPM), which is then adapted to the target domain using a proposed dynamic instance-aware adaptor and a distribution direction loss, enabling the DDPM to translate source-domain images into the target domain style. The adapted images are subsequently processed through the MFM, where we introduce a designed channel-spatial alignment Low-Rank Adaptation (LoRA) to ensure effective feature alignment. Extensive experiments on optic cup and disc segmentation tasks demonstrate that MFM-DA outperforms state-of-the-art methods. Our work provides a practical solution to the domain gap issue in real-world MFM deployment. Code will be available at here.
Authors: Qingwen Zhang, Ajinkya Khoche, Yi Yang, Li Ling, Sina Sharif Mansouri, Olov Andersson, Patric Jensfelt
Abstract: LiDAR point clouds often contain motion-induced distortions, degrading the accuracy of object appearances in the captured data. In this paper, we first characterize the underlying reasons for the point cloud distortion and show that this is present in public datasets. We find that this distortion is more pronounced in high-speed environments such as highways, as well as in multi-LiDAR configurations, a common setup for heavy vehicles. Previous work has dealt with point cloud distortion from the ego-motion but fails to consider distortion from the motion of other objects. We therefore introduce a novel undistortion pipeline, HiMo, that leverages scene flow estimation for object motion compensation, correcting the depiction of dynamic objects. We further propose an extension of a state-of-the-art self-supervised scene flow method. Due to the lack of well-established motion distortion metrics in the literature, we also propose two metrics for compensation performance evaluation: compensation accuracy at a point level and shape similarity on objects. To demonstrate the efficacy of our method, we conduct extensive experiments on the Argoverse 2 dataset and a new real-world dataset. Our new dataset is collected from heavy vehicles equipped with multi-LiDARs and on highways as opposed to mostly urban settings in the existing datasets. The source code, including all methods and the evaluation data, will be provided upon publication. See https://kin-zhang.github.io/HiMo for more details.
Authors: Xulin Chen, Junzhou Huang
Abstract: Spatial transcriptomics (ST) maps gene expression within tissue at individual spots, making it a valuable resource for multimodal representation learning. Additionally, ST inherently contains rich hierarchical information both across and within modalities. For instance, different spots exhibit varying numbers of nonzero gene expressions, corresponding to different levels of cellular activity and semantic hierarchies. However, existing methods rely on contrastive alignment of image-gene pairs, failing to accurately capture the intricate hierarchical relationships in ST data. Here, we propose DELST, the first framework to embed hyperbolic representations while modeling hierarchy for image-gene pretraining at two levels: (1) Cross-modal entailment learning, which establishes an order relationship between genes and images to enhance image representation generalization; (2) Intra-modal entailment learning, which encodes gene expression patterns as hierarchical relationships, guiding hierarchical learning across different samples at a global scale and integrating biological insights into single-modal representations. Extensive experiments on ST benchmarks annotated by pathologists demonstrate the effectiveness of our framework, achieving improved predictive performance compared to existing methods. Our code and models are available at: https://github.com/XulinChen/DELST.
Authors: Lu Ma, Kaibo Cao, Hao Liang, Jiaxin Lin, Zhuang Li, Yuhong Liu, Jihong Zhang, Wentao Zhang, Bin Cui
Abstract: Recent advancements in text-to-image (T2I) models enable high-quality image synthesis, yet generating anatomically accurate human figures remains challenging. AI-generated images frequently exhibit distortions such as proliferated limbs, missing fingers, deformed extremities, or fused body parts. Existing evaluation metrics like Inception Score (IS) and Fr\'echet Inception Distance (FID) lack the granularity to detect these distortions, while human preference-based metrics focus on abstract quality assessments rather than anatomical fidelity. To address this gap, we establish the first standards for identifying human body distortions in AI-generated images and introduce Distortion-5K, a comprehensive dataset comprising 4,700 annotated images of normal and malformed human figures across diverse styles and distortion types. Based on this dataset, we propose ViT-HD, a Vision Transformer-based model tailored for detecting human body distortions in AI-generated images, which outperforms state-of-the-art segmentation models and visual language models, achieving an F1 score of 0.899 and IoU of 0.831 on distortion localization. Additionally, we construct the Human Distortion Benchmark with 500 human-centric prompts to evaluate four popular T2I models using trained ViT-HD, revealing that nearly 50\% of generated images contain distortions. This work pioneers a systematic approach to evaluating anatomical accuracy in AI-generated humans, offering tools to advance the fidelity of T2I models and their real-world applicability. The Distortion-5K dataset, trained ViT-HD will soon be released in our GitHub repository: \href{https://github.com/TheRoadQaQ/Predicting-Distortion}{https://github.com/TheRoadQaQ/Predicting-Distortion}.
URLs: https://github.com/TheRoadQaQ/Predicting-Distortion, https://github.com/TheRoadQaQ/Predicting-Distortion
Authors: Bowen Zheng, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan
Abstract: The ability to learn new concepts while preserve the learned knowledge is desirable for learning systems in Class-Incremental Learning (CIL). Recently, feature expansion of the model become a prevalent solution for CIL, where the old features are fixed during the training of the new task while new features are expanded for the new tasks. However, such task-specific features learned from the new task may collide with the old features, leading to misclassification between tasks. Therefore, the expanded model is often encouraged to capture diverse features from the new task, aiming to avoid such collision. However, the existing solution is largely restricted to the samples from the current task, because of the poor accessibility to previous samples. To promote the learning and transferring of diverse features across tasks, we propose a framework called Task-Agnostic Guided Feature Expansion (TagFex). Firstly, it captures task-agnostic features continually with a separate model, providing extra task-agnostic features for subsequent tasks. Secondly, to obtain useful features from the task-agnostic model for the current task, it aggregates the task-agnostic features with the task-specific feature using a merge attention. Then the aggregated feature is transferred back into the task-specific feature for inference, helping the task-specific model capture diverse features. Extensive experiments show the effectiveness and superiority of TagFex on various CIL settings. Code is available at https://github.com/bwnzheng/TagFex_CVPR2025.
Authors: Yalun Dai, Lingao Xiao, Ivor W. Tsang, Yang He
Abstract: Existing dataset pruning techniques primarily focus on classification tasks, limiting their applicability to more complex and practical tasks like instance segmentation. Instance segmentation presents three key challenges: pixel-level annotations, instance area variations, and class imbalances, which significantly complicate dataset pruning efforts. Directly adapting existing classification-based pruning methods proves ineffective due to their reliance on time-consuming model training process. To address this, we propose a novel Training-Free Dataset Pruning (TFDP) method for instance segmentation. Specifically, we leverage shape and class information from image annotations to design a Shape Complexity Score (SCS), refining it into a Scale-Invariant (SI-SCS) and Class-Balanced (CB-SCS) versions to address instance area variations and class imbalances, all without requiring model training. We achieve state-of-the-art results on VOC 2012, Cityscapes, and COCO datasets, generalizing well across CNN and Transformer architectures. Remarkably, our approach accelerates the pruning process by an average of 1349$\times$ on COCO compared to the adapted baselines. Source code is available at: https://github.com/he-y/dataset-pruning-for-instance-segmentation
URLs: https://github.com/he-y/dataset-pruning-for-instance-segmentation
Authors: BoCheng Li, WenJuan Zhang, Bing Zhang, YiLing Yao, YaNing Wang
Abstract: 3D Gaussian Splatting (3D GS) achieves impressive results in novel view synthesis for small, single-object scenes through Gaussian ellipsoid initialization and adaptive density control. However, when applied to large-scale remote sensing scenes, 3D GS faces challenges: the point clouds generated by Structure-from-Motion (SfM) are often sparse, and the inherent smoothing behavior of 3D GS leads to over-reconstruction in high-frequency regions, where have detailed textures and color variations. This results in the generation of large, opaque Gaussian ellipsoids that cause gradient artifacts. Moreover, the simultaneous optimization of both geometry and texture may lead to densification of Gaussian ellipsoids at incorrect geometric locations, resulting in artifacts in other views. To address these issues, we propose PSRGS, a progressive optimization scheme based on spectral residual maps. Specifically, we create a spectral residual significance map to separate low-frequency and high-frequency regions. In the low-frequency region, we apply depth-aware and depth-smooth losses to initialize the scene geometry with low threshold. For the high-frequency region, we use gradient features with higher threshold to split and clone ellipsoids, refining the scene. The sampling rate is determined by feature responses and gradient loss. Finally, we introduce a pre-trained network that jointly computes perceptual loss from multiple views, ensuring accurate restoration of high-frequency details in both Gaussian ellipsoids geometry and color. We conduct experiments on multiple datasets to assess the effectiveness of our method, which demonstrates competitive rendering quality, especially in recovering texture details in high-frequency regions.
Authors: Rui Yi Yong, Samuel Picosson, Arnold Wiliem
Abstract: This work tackles 3D scene reconstruction for a video fly-over perspective problem in the maritime domain, with a specific emphasis on geometrically and visually sound reconstructions. This will allow for downstream tasks such as segmentation, navigation, and localization. To our knowledge, there is no dataset available in this domain. As such, we propose a novel maritime 3D scene reconstruction benchmarking dataset, named as MTReD (Maritime Three-Dimensional Reconstruction Dataset). The MTReD comprises 19 fly-over videos curated from the Internet containing ships, islands, and coastlines. As the task is aimed towards geometrical consistency and visual completeness, the dataset uses two metrics: (1) Reprojection error; and (2) Perception based metrics. We find that existing perception-based metrics, such as Learned Perceptual Image Patch Similarity (LPIPS), do not appropriately measure the completeness of a reconstructed image. Thus, we propose a novel semantic similarity metric utilizing DINOv2 features coined DiFPS (DinoV2 Features Perception Similarity). We perform initial evaluation on two baselines: (1) Structured from Motion (SfM) through Colmap; and (2) the recent state-of-the-art MASt3R model. We find that the reconstructed scenes by MASt3R have higher reprojection errors, but superior perception based metric scores. To this end, some pre-processing methods are explored, and we find a pre-processing method which improves both the reprojection error and perception-based score. We envisage our proposed MTReD to stimulate further research in these directions. The dataset and all the code will be made available in https://github.com/RuiYiYong/MTReD.
Authors: Sohyun Jeong, Taewoong Kang, Hyojin Jang, Jaegul Choo
Abstract: With growing demand in media and social networks for personalized images, the need for advanced head-swapping techniques, integrating an entire head from the head image with the body from the body image, has increased. However, traditional head swapping methods heavily rely on face-centered cropped data with primarily frontal facing views, which limits their effectiveness in real world applications. Additionally, their masking methods, designed to indicate regions requiring editing, are optimized for these types of dataset but struggle to achieve seamless blending in complex situations, such as when the original data includes features like long hair extending beyond the masked area. To overcome these limitations and enhance adaptability in diverse and complex scenarios, we propose a novel head swapping method, HID, that is robust to images including the full head and the upper body, and handles from frontal to side views, while automatically generating context aware masks. For automatic mask generation, we introduce the IOMask, which enables seamless blending of the head and body, effectively addressing integration challenges. We further introduce the hair injection module to capture hair details with greater precision. Our experiments demonstrate that the proposed approach achieves state-of-the-art performance in head swapping, providing visually consistent and realistic results across a wide range of challenging conditions.
Authors: You Shen, Zhipeng Zhang, Xinyang Li, Yansong Qu, Yu Lin, Shengchuan Zhang, Liujuan Cao
Abstract: Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention for its high-quality rendering and fast inference speed. Yet, due to the unstructured and irregular nature of Gaussian point clouds, ensuring accurate geometry reconstruction remains difficult. Existing methods primarily focus on geometry regularization, with common approaches including primitive-based and dual-model frameworks. However, the former suffers from inherent conflicts between rendering and reconstruction, while the latter is computationally and storage-intensive. To address these challenges, we propose CarGS, a unified model leveraging Contribution-adaptive regularization to achieve simultaneous, high-quality rendering and surface reconstruction. The essence of our framework is learning adaptive contribution for Gaussian primitives by squeezing the knowledge from geometry regularization into a compact MLP. Additionally, we introduce a geometry-guided densification strategy with clues from both normals and Signed Distance Fields (SDF) to improve the capability of capturing high-frequency details. Our design improves the mutual learning of the two tasks, meanwhile its unified structure does not require separate models as in dual-model based approaches, guaranteeing efficiency. Extensive experiments demonstrate the ability to achieve state-of-the-art (SOTA) results in both rendering fidelity and reconstruction accuracy while maintaining real-time speed and minimal storage size.
Authors: Theodore Curran, Chengqian Ma, Xin Liu, Daniel McDuff, Girish Narayanswamy, George Stergiou, Shwetak Patel, Eugene Yang
Abstract: Hypertension is a leading cause of morbidity and mortality worldwide. The ability to diagnose and treat hypertension in the ambulatory population is hindered by limited access and poor adherence to current methods of monitoring blood pressure (BP), specifically, cuff-based devices. Remote photoplethysmography (rPPG) evaluates an individual's pulse waveform through a standard camera without physical contact. Cameras are readily available to the majority of the global population via embedded technologies such as smartphones, thus rPPG is a scalable and promising non-invasive method of BP monitoring. The few studies investigating rPPG for BP measurement have excluded high-risk populations, including those with cardiovascular disease (CVD) or its risk factors, as well as subjects in active cardiac arrhythmia. The impact of arrhythmia, like atrial fibrillation, on the prediction of BP using rPPG is currently uncertain. We performed a study to better understand the relationship between rPPG and BP in a real-world sample of ambulatory patients from a cardiology clinic with established CVD or risk factors for CVD. We collected simultaneous rPPG, PPG, BP, ECG, and other vital signs data from 143 subjects while at rest, and used this data plus demographics to train a deep learning model to predict BP. We report that facial rPPG yields a signal that is comparable to finger PPG. Pulse wave analysis (PWA)-based BP estimates on this cohort performed comparably to studies on healthier subjects, and notably, the accuracy of BP prediction in subjects with atrial fibrillation was not inferior to subjects with normal sinus rhythm. In a binary classification task, the rPPG model identified subjects with systolic BP $\geq$ 130 mm Hg with a positive predictive value of 71% (baseline prevalence 48.3%), highlighting the potential of rPPG for hypertension monitoring.
Authors: Qijie Wei, Kaiheng Qian, Xirong Li
Abstract: Multimodal Large Language Models (MLLMs) have shown significant potential in medical image analysis. However, their capabilities in interpreting fundus images, a critical skill for ophthalmology, remain under-evaluated. Existing benchmarks lack fine-grained task divisions and fail to provide modular analysis of its two key modules, i.e., large language model (LLM) and vision encoder (VE). This paper introduces FunBench, a novel visual question answering (VQA) benchmark designed to comprehensively evaluate MLLMs' fundus reading skills. FunBench features a hierarchical task organization across four levels (modality perception, anatomy perception, lesion analysis, and disease diagnosis). It also offers three targeted evaluation modes: linear-probe based VE evaluation, knowledge-prompted LLM evaluation, and holistic evaluation. Experiments on nine open-source MLLMs plus GPT-4o reveal significant deficiencies in fundus reading skills, particularly in basic tasks such as laterality recognition. The results highlight the limitations of current MLLMs and emphasize the need for domain-specific training and improved LLMs and VEs.
Authors: Zhu Liu, Zijun Wang, Jinyuan Liu, Fanqi Meng, Long Ma, Risheng Liu
Abstract: Thermal imaging is often compromised by dynamic, complex degradations caused by hardware limitations and unpredictable environmental factors. The scarcity of high-quality infrared data, coupled with the challenges of dynamic, intricate degradations, makes it difficult to recover details using existing methods. In this paper, we introduce thermal degradation simulation integrated into the training process via a mini-max optimization, by modeling these degraded factors as adversarial attacks on thermal images. The simulation is dynamic to maximize objective functions, thus capturing a broad spectrum of degraded data distributions. This approach enables training with limited data, thereby improving model performance.Additionally, we introduce a dual-interaction network that combines the benefits of spiking neural networks with scale transformation to capture degraded features with sharp spike signal intensities. This architecture ensures compact model parameters while preserving efficient feature representation. Extensive experiments demonstrate that our method not only achieves superior visual quality under diverse single and composited degradation, but also delivers a significant reduction in processing when trained on only fifty clear images, outperforming existing techniques in efficiency and accuracy. The source code will be available at https://github.com/LiuZhu-CV/DEAL.
Authors: Xitong Ling, Yifeng Ping, Jiawen Li, Jing Peng, Yuxuan Chen, Minxi Ouyang, Yizhi Wang, Yonghong He, Tian Guan, Xiaoping Liu, Lianghui Zhu
Abstract: Multiple Instance Learning (MIL) plays a significant role in computational pathology, enabling weakly supervised analysis of Whole Slide Image (WSI) datasets. The field of WSI analysis is confronted with a severe long-tailed distribution problem, which significantly impacts the performance of classifiers. Long-tailed distributions lead to class imbalance, where some classes have sparse samples while others are abundant, making it difficult for classifiers to accurately identify minority class samples. To address this issue, we propose an ensemble learning method based on MIL, which employs expert decoders with shared aggregators and consistency constraints to learn diverse distributions and reduce the impact of class imbalance on classifier performance. Moreover, we introduce a multimodal distillation framework that leverages text encoders pre-trained on pathology-text pairs to distill knowledge and guide the MIL aggregator in capturing stronger semantic features relevant to class information. To ensure flexibility, we use learnable prompts to guide the distillation process of the pre-trained text encoder, avoiding limitations imposed by specific prompts. Our method, MDE-MIL, integrates multiple expert branches focusing on specific data distributions to address long-tailed issues. Consistency control ensures generalization across classes. Multimodal distillation enhances feature extraction. Experiments on Camelyon+-LT and PANDA-LT datasets show it outperforms state-of-the-art methods.
Authors: Daiki Nishiyama, Hiroaki Miyoshi, Noriaki Hashimoto, Koichi Ohshima, Hidekata Hontani, Ichiro Takeuchi, Jun Sakuma
Abstract: Malignant lymphoma subtype classification directly impacts treatment strategies and patient outcomes, necessitating classification models that achieve both high accuracy and sufficient explainability. This study proposes a novel explainable Multi-Instance Learning (MIL) framework that identifies subtype-specific Regions of Interest (ROIs) from Whole Slide Images (WSIs) while integrating cell distribution characteristics and image information. Our framework simultaneously addresses three objectives: (1) indicating appropriate ROIs for each subtype, (2) explaining the frequency and spatial distribution of characteristic cell types, and (3) achieving high-accuracy subtyping by leveraging both image and cell-distribution modalities. The proposed method fuses cell graph and image features extracted from each patch in the WSI using a Mixture-of-Experts (MoE) approach and classifies subtypes within an MIL framework. Experiments on a dataset of 1,233 WSIs demonstrate that our approach achieves state-of-the-art accuracy among ten comparative methods and provides region-level and cell-level explanations that align with a pathologist's perspectives.
Authors: Qing Wan, Shilong Deng, Xun Wang
Abstract: Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle perturbations applied to inputs that are often imperceptible to humans yet lead to incorrect model predictions. In black-box scenarios, however, existing adversarial examples exhibit limited transferability and struggle to effectively compromise multiple unseen DNN models. Previous strategies enhance the cross-model generalization of adversarial examples by introducing versatility into adversarial perturbations, thereby improving transferability. However, further refining perturbation versatility often demands intricate algorithm development and substantial computation consumption. In this work, we propose an input transpose method that requires almost no additional labor and computation costs but can significantly improve the transferability of existing adversarial strategies. Even without adding adversarial perturbations, our method demonstrates considerable effectiveness in cross-model attacks. Our exploration finds that on specific datasets, a mere $1^\circ$ left or right rotation might be sufficient for most adversarial examples to deceive unseen models. Our further analysis suggests that this transferability improvement triggered by rotating only $1^\circ$ may stem from visible pattern shifts in the DNN's low-level feature maps. Moreover, this transferability exhibits optimal angles that, when identified under unrestricted query conditions, could potentially yield even greater performance.
Authors: Yuji Wang, Jingchen Ni, Yong Liu, Chun Yuan, Yansong Tang
Abstract: Zero-shot Referring Image Segmentation (RIS) identifies the instance mask that best aligns with a specified referring expression without training and fine-tuning, significantly reducing the labor-intensive annotation process. Despite achieving commendable results, previous CLIP-based models have a critical drawback: the models exhibit a notable reduction in their capacity to discern relative spatial relationships of objects. This is because they generate all possible masks on an image and evaluate each masked region for similarity to the given expression, often resulting in decreased sensitivity to direct positional clues in text inputs. Moreover, most methods have weak abilities to manage relationships between primary words and their contexts, causing confusion and reduced accuracy in identifying the correct target region. To address these challenges, we propose IteRPrimE (Iterative Grad-CAM Refinement and Primary word Emphasis), which leverages a saliency heatmap through Grad-CAM from a Vision-Language Pre-trained (VLP) model for image-text matching. An iterative Grad-CAM refinement strategy is introduced to progressively enhance the model's focus on the target region and overcome positional insensitivity, creating a self-correcting effect. Additionally, we design the Primary Word Emphasis module to help the model handle complex semantic relations, enhancing its ability to attend to the intended object. Extensive experiments conducted on the RefCOCO/+/g, and PhraseCut benchmarks demonstrate that IteRPrimE outperforms previous state-of-the-art zero-shot methods, particularly excelling in out-of-domain scenarios.
Authors: Chao Yuan, Guiwei Zhang, Changxiao Ma, Tianyi Zhang, Guanglin Niu
Abstract: Person re-identification (ReID) aims to extract accurate identity representation features. However, during feature extraction, individual samples are inevitably affected by noise (background, occlusions, and model limitations). Considering that features from the same identity follow a normal distribution around identity centers after training, we propose a Training-Free Feature Centralization ReID framework (Pose2ID) by aggregating the same identity features to reduce individual noise and enhance the stability of identity representation, which preserves the feature's original distribution for following strategies such as re-ranking. Specifically, to obtain samples of the same identity, we introduce two components:Identity-Guided Pedestrian Generation: by leveraging identity features to guide the generation process, we obtain high-quality images with diverse poses, ensuring identity consistency even in complex scenarios such as infrared, and occlusion.Neighbor Feature Centralization: it explores each sample's potential positive samples from its neighborhood. Experiments demonstrate that our generative model exhibits strong generalization capabilities and maintains high identity consistency. With the Feature Centralization framework, we achieve impressive performance even with an ImageNet pre-trained model without ReID training, reaching mAP/Rank-1 of 52.81/78.92 on Market1501. Moreover, our method sets new state-of-the-art results across standard, cross-modality, and occluded ReID tasks, showcasing strong adaptability.
Authors: Jie Tian, Xiaoye Qu, Zhenyi Lu, Wei Wei, Sichen Liu, Yu Cheng
Abstract: Image-to-Video (I2V) generation aims to synthesize a video clip according to a given image and condition (e.g., text). The key challenge of this task lies in simultaneously generating natural motions while preserving the original appearance of the images. However, current I2V diffusion models (I2V-DMs) often produce videos with limited motion degrees or exhibit uncontrollable motion that conflicts with the textual condition. To address these limitations, we propose a novel Extrapolating and Decoupling framework, which introduces model merging techniques to the I2V domain for the first time. Specifically, our framework consists of three separate stages: (1) Starting with a base I2V-DM, we explicitly inject the textual condition into the temporal module using a lightweight, learnable adapter and fine-tune the integrated model to improve motion controllability. (2) We introduce a training-free extrapolation strategy to amplify the dynamic range of the motion, effectively reversing the fine-tuning process to enhance the motion degree significantly. (3) With the above two-stage models excelling in motion controllability and degree, we decouple the relevant parameters associated with each type of motion ability and inject them into the base I2V-DM. Since the I2V-DM handles different levels of motion controllability and dynamics at various denoising time steps, we adjust the motion-aware parameters accordingly over time. Extensive qualitative and quantitative experiments have been conducted to demonstrate the superiority of our framework over existing methods.
Authors: Jinhong Wang, Jintai Chen, Jian Liu, Dongqi Tang, Danny Z. Chen, Jian Wu
Abstract: Ordinal regression refers to classifying object instances into ordinal categories. Ordinal regression is crucial for applications in various areas like facial age estimation, image aesthetics assessment, and even cancer staging, due to its capability to utilize ordered information effectively. More importantly, it also enhances model interpretation by considering category order, aiding the understanding of data trends and causal relationships. Despite significant recent progress, challenges remain, and further investigation of ordinal regression techniques and applications is essential to guide future research. In this survey, we present a comprehensive examination of advances and applications of ordinal regression. By introducing a systematic taxonomy, we meticulously classify the pertinent techniques and applications into three well-defined categories based on different strategies and objectives: Continuous Space Discretization, Distribution Ordering Learning, and Ambiguous Instance Delving. This categorization enables a structured exploration of diverse insights in ordinal regression problems, providing a framework for a more comprehensive understanding and evaluation of this field and its related applications. To our best knowledge, this is the first systematic survey of ordinal regression, which lays a foundation for future research in this fundamental and generic domain.
Authors: Minh H. Vu, Lorenzo Tronchin, Tufve Nyholm, Tommy L\"ofstedt
Abstract: Recent years have witnessed a growing academic and industrial interest in deep learning (DL) for medical imaging. To perform well, DL models require very large labeled datasets. However, most medical imaging datasets are small, with a limited number of annotated samples. The reason they are small is usually because delineating medical images is time-consuming and demanding for oncologists. There are various techniques that can be used to augment a dataset, for example, to apply affine transformations or elastic transformations to available images, or to add synthetic images generated by a Generative Adversarial Network (GAN). In this work, we have developed a novel conditional variant of a current GAN method, the StyleGAN2, to generate multi-modal high-resolution medical images with the purpose to augment small medical imaging datasets with these synthetic images. We use the synthetic and real images from six datasets to train models for the downstream task of semantic segmentation. The quality of the generated medical images and the effect of this augmentation on the segmentation performance were evaluated afterward. Finally, the results indicate that the downstream segmentation models did not benefit from the generated images. Further work and analyses are required to establish how this augmentation affects the segmentation performance.
Authors: Wanwen Chen, Carson Studders, Jamie J. Y. Kwon, Emily H. T. Pang, Eitan Prisman, Septimiu E. Salcudean
Abstract: Point cloud registration is important in computer-aided interventions (CAI). While learning-based point cloud registration methods have been developed, their clinical application is hampered by issues of generalizability and explainability. Therefore, classical point cloud registration methods, such as Iterative Closest Point (ICP), are still widely applied in CAI. ICP methods fail to consider that: (1) the points have well-defined semantic meaning, in that each point can be related to a specific anatomical label; (2) the deformation needs to follow biomechanical energy constraints. In this paper, we present a novel semantic ICP (sem-ICP) method that handles multiple point labels and uses linear elastic energy regularization. We use semantic labels to improve the robustness of the closest point matching and propose a new point cloud deformation representation to apply explicit biomechanical energy regularization. Our experiments on the Learn2reg abdominal MR-CT registration dataset and a trans-oral robotic surgery ultrasound-CT registration dataset show that our method improves the Hausdorff distance compared with other state-of-the-art ICP-based registration methods. We also perform a sensitivity study to show that our rigid initialization achieves better convergence with different initializations and visible ratios.
Authors: Baoqi Pei, Yifei Huang, Jilan Xu, Guo Chen, Yuping He, Lijin Yang, Yali Wang, Weidi Xie, Yu Qiao, Fei Wu, Limin Wang
Abstract: In egocentric video understanding, the motion of hands and objects as well as their interactions play a significant role by nature. However, existing egocentric video representation learning methods mainly focus on aligning video representation with high-level narrations, overlooking the intricate dynamics between hands and objects. In this work, we aim to integrate the modeling of fine-grained hand-object dynamics into the video representation learning process. Since no suitable data is available, we introduce HOD, a novel pipeline employing a hand-object detector and a large language model to generate high-quality narrations with detailed descriptions of hand-object dynamics. To learn these fine-grained dynamics, we propose EgoVideo, a model with a new lightweight motion adapter to capture fine-grained hand-object motion information. Through our co-training strategy, EgoVideo effectively and efficiently leverages the fine-grained hand-object dynamics in the HOD data. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple egocentric downstream tasks, including improvements of 6.3% in EK-100 multi-instance retrieval, 5.7% in EK-100 classification, and 16.3% in EGTEA classification in zero-shot settings. Furthermore, our model exhibits robust generalization capabilities in hand-object interaction and robot manipulation tasks. Code and data are available at https://github.com/OpenRobotLab/EgoHOD/.
Authors: Ziyang Zhang, Yang Yu, Yucheng Chen, Xulei Yang, Si Yong Yeo
Abstract: Despite significant progress in Vision-Language Pre-training (VLP), current approaches predominantly emphasize feature extraction and cross-modal comprehension, with limited attention to generating or transforming visual content. This gap hinders the model's ability to synthesize coherent and novel visual representations from textual prompts, thereby reducing the effectiveness of multi-modal learning. In this work, we propose MedUnifier, a unified VLP framework tailored for medical data. MedUnifier seamlessly integrates text-grounded image generation capabilities with multi-modal learning strategies, including image-text contrastive alignment, image-text matching and image-grounded text generation. Unlike traditional methods that reply on continuous visual representations, our approach employs visual vector quantization, which not only facilitates a more cohesive learning strategy for cross-modal understanding but also enhances multi-modal generation quality by effectively leveraging discrete representations. Our framework's effectiveness is evidenced by the experiments on established benchmarks, including uni-modal tasks (supervised fine-tuning), cross-modal tasks (image-text retrieval and zero-shot image classification), and multi-modal tasks (medical report generation, image synthesis), where it achieves state-of-the-art performance across various tasks. MedUnifier also offers a highly adaptable tool for a wide range of language and vision tasks in healthcare, marking advancement toward the development of a generalizable AI model for medical applications.
Authors: Lie Ju, Sijin Zhou, Yukun Zhou, Huimin Lu, Zhuoting Zhu, Pearse A. Keane, Zongyuan Ge
Abstract: Recent advances in medical vision-language models (VLMs) demonstrate impressive performance in image classification tasks, driven by their strong zero-shot generalization capabilities. However, given the high variability and complexity inherent in medical imaging data, the ability of these models to detect out-of-distribution (OOD) data in this domain remains underexplored. In this work, we conduct the first systematic investigation into the OOD detection potential of medical VLMs. We evaluate state-of-the-art VLM-based OOD detection methods across a diverse set of medical VLMs, including both general and domain-specific purposes. To accurately reflect real-world challenges, we introduce a cross-modality evaluation pipeline for benchmarking full-spectrum OOD detection, rigorously assessing model robustness against both semantic shifts and covariate shifts. Furthermore, we propose a novel hierarchical prompt-based method that significantly enhances OOD detection performance. Extensive experiments are conducted to validate the effectiveness of our approach. The codes are available at https://github.com/PyJulie/Medical-VLMs-OOD-Detection.
URLs: https://github.com/PyJulie/Medical-VLMs-OOD-Detection.
Authors: Elham Ghelichkhan, Tolga Tasdizen
Abstract: Chest diseases rank among the most prevalent and dangerous global health issues. Object detection and phrase grounding deep learning models interpret complex radiology data to assist healthcare professionals in diagnosis. Object detection locates abnormalities for classes, while phrase grounding locates abnormalities for textual descriptions. This paper investigates how text enhances abnormality localization in chest X-rays by comparing the performance and explainability of these two tasks. To establish an explainability baseline, we proposed an automatic pipeline to generate image regions for report sentences using radiologists' eye-tracking data. The better performance - mIoU = 0.36 vs. 0.20 - and explainability - Containment ratio 0.48 vs. 0.26 - of the phrase grounding model infers the effectiveness of text in enhancing chest X-ray abnormality localization.
Authors: Mykola Kozlenko, Volodymyr Sendetskyi, Oleksiy Simkiv, Nazar Savchenko, Andy Bosyi
Abstract: Object recognition and detection are well-studied problems with a developed set of almost standard solutions. Identity documents recognition, classification, detection, and localization are the tasks required in a number of applications, particularly, in physical access control security systems at critical infrastructure premises. In this paper, we propose the new original architecture of a model based on an artificial convolutional neural network and semantic segmentation approach for the recognition and detection of identity documents in images. The challenge with the processing of such images is the limited computational performance and the limited amount of memory when such an application is running on industrial oneboard microcomputer hardware. The aim of this research is to prove the feasibility of the proposed technique and to obtain quality metrics. The methodology of the research is to evaluate the deep learning detection model trained on the mobile identity document video dataset. The dataset contains five hundred video clips for fifty different identity document types. The numerical results from simulations are used to evaluate the quality metrics. We present the results as accuracy versus threshold of the intersection over union value. The paper reports an accuracy above 0.75 for the intersection over union (IoU) threshold value of 0.8. Besides, we assessed the size of the model and proved the feasibility of running the model on an industrial one-board microcomputer or smartphone hardware.
Authors: Jon Donnelly, Zhicheng Guo, Alina Jade Barnett, Hayden McTavish, Chaofan Chen, Cynthia Rudin
Abstract: Interpretability is critical for machine learning models in high-stakes settings because it allows users to verify the model's reasoning. In computer vision, prototypical part models (ProtoPNets) have become the dominant model type to meet this need. Users can easily identify flaws in ProtoPNets, but fixing problems in a ProtoPNet requires slow, difficult retraining that is not guaranteed to resolve the issue. This problem is called the "interaction bottleneck." We solve the interaction bottleneck for ProtoPNets by simultaneously finding many equally good ProtoPNets (i.e., a draw from a "Rashomon set"). We show that our framework - called Proto-RSet - quickly produces many accurate, diverse ProtoPNets, allowing users to correct problems in real time while maintaining performance guarantees with respect to the training set. We demonstrate the utility of this method in two settings: 1) removing synthetic bias introduced to a bird identification model and 2) debugging a skin cancer identification model. This tool empowers non-machine-learning experts, such as clinicians or domain experts, to quickly refine and correct machine learning models without repeated retraining by machine learning experts.
Authors: Wanjun Jia, Fan Yang, Mengfei Duan, Xianchi Chen, Yinxi Wang, Yiming Jiang, Wenrui Chen, Kailun Yang, Zhiyong Li
Abstract: Deformable object manipulation in robotics presents significant challenges due to uncertainties in component properties, diverse configurations, visual interference, and ambiguous prompts. These factors complicate both perception and control tasks. To address these challenges, we propose a novel method for One-Shot Affordance Grounding of Deformable Objects (OS-AGDO) in egocentric organizing scenes, enabling robots to recognize previously unseen deformable objects with varying colors and shapes using minimal samples. Specifically, we first introduce the Deformable Object Semantic Enhancement Module (DefoSEM), which enhances hierarchical understanding of the internal structure and improves the ability to accurately identify local features, even under conditions of weak component information. Next, we propose the ORB-Enhanced Keypoint Fusion Module (OEKFM), which optimizes feature extraction of key components by leveraging geometric constraints and improves adaptability to diversity and visual interference. Additionally, we propose an instance-conditional prompt based on image data and task context, effectively mitigates the issue of region ambiguity caused by prompt words. To validate these methods, we construct a diverse real-world dataset, AGDDO15, which includes 15 common types of deformable objects and their associated organizational actions. Experimental results demonstrate that our approach significantly outperforms state-of-the-art methods, achieving improvements of 6.2%, 3.2%, and 2.9% in KLD, SIM, and NSS metrics, respectively, while exhibiting high generalization performance. Source code and benchmark dataset will be publicly available at https://github.com/Dikay1/OS-AGDO.
Authors: Hanzhe Liang, Jie Zhou, Xuanxin Chen, Tao Dai, Jinbao Wang, Can Gao
Abstract: 3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolator: (1) mitigating cross-semantic interference to the greatest extent feasible and (2) confining anomaly judgments to aligned semantic spaces wherever viable, thereby establishing intra-semantic comparability. Any preprocessing approach achieves this goal through a two-stage process of Emantic-Division and Spatial-Constraints stage. Through systematic deconstruction, we theoretically and experimentally subsume existing preprocessing methods under this theorem via tripartite evidence: qualitative analyses, quantitative studies, and mathematical proofs. Guided by the Fence Theorem, we implement Patch3D, consisting of Patch-Cutting and Patch-Matching modules, to segment semantic spaces and consolidate similar ones while independently modeling normal features within each space. Experiments on Anomaly-ShapeNet and Real3D-AD with different settings demonstrate that progressively finer-grained semantic alignment in preprocessing directly enhances point-level AD accuracy, providing inverse validation of the theorem's causal logic.
Authors: Kaiwen Zheng, Yongxin Chen, Huayu Chen, Guande He, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang
Abstract: While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective inherently suffers from a mode-covering tendency that limits the generation quality under limited model capacity. In this work, we propose Direct Discriminative Optimization (DDO) as a unified framework that bridges likelihood-based generative training and the GAN objective to bypass this fundamental constraint. Our key insight is to parameterize a discriminator implicitly using the likelihood ratio between a learnable target model and a fixed reference model, drawing parallels with the philosophy of Direct Preference Optimization (DPO). Unlike GANs, this parameterization eliminates the need for joint training of generator and discriminator networks, allowing for direct, efficient, and effective finetuning of a well-trained model to its full potential beyond the limits of MLE. DDO can be performed iteratively in a self-play manner for progressive model refinement, with each round requiring less than 1% of pretraining epochs. Our experiments demonstrate the effectiveness of DDO by significantly advancing the previous SOTA diffusion model EDM, reducing FID scores from 1.79/1.58 to new records of 1.30/0.97 on CIFAR-10/ImageNet-64 datasets, and by consistently improving both guidance-free and CFG-enhanced FIDs of visual autoregressive models on ImageNet 256$\times$256.
Authors: Juil Koo, Paul Guerrero, Chun-Hao Paul Huang, Duygu Ceylan, Minhyuk Sung
Abstract: Generative methods for image and video editing use generative models as priors to perform edits despite incomplete information, such as changing the composition of 3D objects shown in a single image. Recent methods have shown promising composition editing results in the image setting, but in the video setting, editing methods have focused on editing object's appearance and motion, or camera motion, and as a result, methods to edit object composition in videos are still missing. We propose \name as a method for editing 3D object compositions in videos of static scenes with camera motion. Our approach allows editing the 3D position of a 3D object across all frames of a video in a temporally consistent manner. This is achieved by lifting intermediate features of a generative model to a 3D reconstruction that is shared between all frames, editing the reconstruction, and projecting the features on the edited reconstruction back to each frame. To the best of our knowledge, this is the first generative approach to edit object compositions in videos. Our approach is simple and training-free, while outperforming state-of-the-art image editing baselines.
Authors: Yansong Xu, Junlin Li, Wei Zhang, Siyu Chen, Shengyong Zhang, Yuquan Leng, Weijia Zhou
Abstract: 3D gaussian splatting has advanced simultaneous localization and mapping (SLAM) technology by enabling real-time positioning and the construction of high-fidelity maps. However, the uncertainty in gaussian position and initialization parameters introduces challenges, often requiring extensive iterative convergence and resulting in redundant or insufficient gaussian representations. To address this, we introduce a novel adaptive densification method based on Fourier frequency domain analysis to establish gaussian priors for rapid convergence. Additionally, we propose constructing independent and unified sparse and dense maps, where a sparse map supports efficient tracking via Generalized Iterative Closest Point (GICP) and a dense map creates high-fidelity visual representations. This is the first SLAM system leveraging frequency domain analysis to achieve high-quality gaussian mapping in real-time. Experimental results demonstrate an average frame rate of 36 FPS on Replica and TUM RGB-D datasets, achieving competitive accuracy in both localization and mapping.
Authors: Hui Liu, Chen Jia, Fan Shi, Xu Cheng, Shengyong Chen
Abstract: Pixel-level segmentation of structural cracks across various scenarios remains a considerable challenge. Current methods encounter challenges in effectively modeling crack morphology and texture, facing challenges in balancing segmentation quality with low computational resource usage. To overcome these limitations, we propose a lightweight Structure-Aware Vision Mamba Network (SCSegamba), capable of generating high-quality pixel-level segmentation maps by leveraging both the morphological information and texture cues of crack pixels with minimal computational cost. Specifically, we developed a Structure-Aware Visual State Space module (SAVSS), which incorporates a lightweight Gated Bottleneck Convolution (GBC) and a Structure-Aware Scanning Strategy (SASS). The key insight of GBC lies in its effectiveness in modeling the morphological information of cracks, while the SASS enhances the perception of crack topology and texture by strengthening the continuity of semantic information between crack pixels. Experiments on crack benchmark datasets demonstrate that our method outperforms other state-of-the-art (SOTA) methods, achieving the highest performance with only 2.8M parameters. On the multi-scenario dataset, our method reached 0.8390 in F1 score and 0.8479 in mIoU. The code is available at https://github.com/Karl1109/SCSegamba.
Authors: Junsong Zhang, Chunyu Lin, Zhijie Shen, Lang Nie, Kang Liao, Yao Zhao
Abstract: The performance of existing supervised layout estimation methods heavily relies on the quality of data annotations. However, obtaining large-scale and high-quality datasets remains a laborious and time-consuming challenge. To solve this problem, semi-supervised approaches are introduced to relieve the demand for expensive data annotations by encouraging the consistent results of unlabeled data with different perturbations. However, existing solutions merely employ vanilla perturbations, ignoring the characteristics of panoramic layout estimation. In contrast, we propose a novel semi-supervised method named SemiLayout360, which incorporates the priors of the panoramic layout and distortion through collaborative perturbations. Specifically, we leverage the panoramic layout prior to enhance the model's focus on potential layout boundaries. Meanwhile, we introduce the panoramic distortion prior to strengthen distortion awareness. Furthermore, to prevent intense perturbations from hindering model convergence and ensure the effectiveness of prior-based perturbations, we divide and reorganize them as panoramic collaborative perturbations. Our experimental results on three mainstream benchmarks demonstrate that the proposed method offers significant advantages over existing state-of-the-art (SoTA) solutions.
Authors: Zhipeng Huang, Shaobin Zhuang, Canmiao Fu, Binxin Yang, Ying Zhang, Chong Sun, Zhizheng Zhang, Yali Wang, Chen Li, Zheng-Jun Zha
Abstract: Existing multimodal generative models fall short as qualified design copilots, as they often struggle to generate imaginative outputs once instructions are less detailed or lack the ability to maintain consistency with the provided references. In this work, we introduce WeGen, a model that unifies multimodal generation and understanding, and promotes their interplay in iterative generation. It can generate diverse results with high creativity for less detailed instructions. And it can progressively refine prior generation results or integrating specific contents from references following the instructions in its chat with users. During this process, it is capable of preserving consistency in the parts that the user is already satisfied with. To this end, we curate a large-scale dataset, extracted from Internet videos, containing rich object dynamics and auto-labeled dynamics descriptions by advanced foundation models to date. These two information are interleaved into a single sequence to enable WeGen to learn consistency-aware generation where the specified dynamics are generated while the consistency of unspecified content is preserved aligned with instructions. Besides, we introduce a prompt self-rewriting mechanism to enhance generation diversity. Extensive experiments demonstrate the effectiveness of unifying multimodal understanding and generation in WeGen and show it achieves state-of-the-art performance across various visual generation benchmarks. These also demonstrate the potential of WeGen as a user-friendly design copilot as desired. The code and models will be available at https://github.com/hzphzp/WeGen.
Authors: Shizhan Liu, Hao Zheng, Hang Yu, Jianguo Li
Abstract: Image personalization has garnered attention for its ability to customize Text-to-Image generation using only a few reference images. However, a key challenge in image personalization is the issue of conceptual coupling, where the limited number of reference images leads the model to form unwanted associations between the personalization target and other concepts. Current methods attempt to tackle this issue indirectly, leading to a suboptimal balance between text control and personalization fidelity. In this paper, we take a direct approach to the concept coupling problem through statistical analysis, revealing that it stems from two distinct sources of dependence discrepancies. We therefore propose two complementary plug-and-play loss functions: Denoising Decouple Loss and Prior Decouple loss, each designed to minimize one type of dependence discrepancy. Extensive experiments demonstrate that our approach achieves a superior trade-off between text control and personalization fidelity.
Authors: Shreyas S, Akshath M
Abstract: Vision Transformers (ViTs) have significantly advanced image classification by applying self-attention on patch embeddings. However, the standard MLP blocks in each Transformer layer may not capture complex nonlinear dependencies optimally. In this paper, we propose ViKANformer, a Vision Transformer where we replace the MLP sub-layers with Kolmogorov-Arnold Network (KAN) expansions, including Vanilla KAN, Efficient-KAN, Fast-KAN, SineKAN, and FourierKAN, while also examining a Flash Attention variant. By leveraging the Kolmogorov-Arnold theorem, which guarantees that multivariate continuous functions can be expressed via sums of univariate continuous functions, we aim to boost representational power. Experimental results on MNIST demonstrate that SineKAN, Fast-KAN, and a well-tuned Vanilla KAN can achieve over 97% accuracy, albeit with increased training overhead. This trade-off highlights that KAN expansions may be beneficial if computational cost is acceptable. We detail the expansions, present training/test accuracy and F1/ROC metrics, and provide pseudocode and hyperparameters for reproducibility. Finally, we compare ViKANformer to a simple MLP and a small CNN baseline on MNIST, illustrating the efficiency of Transformer-based methods even on a small-scale dataset.
Authors: Runmao Yao, Yi Du, Zhuoqun Chen, Haoze Zheng, Chen Wang
Abstract: Room reidentification (ReID) is a challenging yet essential task with numerous applications in fields such as augmented reality (AR) and homecare robotics. Existing visual place recognition (VPR) methods, which typically rely on global descriptors or aggregate local features, often struggle in cluttered indoor environments densely populated with man-made objects. These methods tend to overlook the crucial role of object-oriented information. To address this, we propose AirRoom, an object-aware pipeline that integrates multi-level object-oriented information-from global context to object patches, object segmentation, and keypoints-utilizing a coarse-to-fine retrieval approach. Extensive experiments on four newly constructed datasets-MPReID, HMReID, GibsonReID, and ReplicaReID-demonstrate that AirRoom outperforms state-of-the-art (SOTA) models across nearly all evaluation metrics, with improvements ranging from 6% to 80%. Moreover, AirRoom exhibits significant flexibility, allowing various modules within the pipeline to be substituted with different alternatives without compromising overall performance. It also shows robust and consistent performance under diverse viewpoint variations.
Authors: Xiongfei Su, Siyuan Li, Yuning Cui, Miao Cao, Yulun Zhang, Zheng Chen, Zongliang Wu, Zedong Wang, Yuanlong Zhang, Xin Yuan
Abstract: Image dehazing is a crucial task that involves the enhancement of degraded images to recover their sharpness and textures. While vision Transformers have exhibited impressive results in diverse dehazing tasks, their quadratic complexity and lack of dehazing priors pose significant drawbacks for real-world applications. In this paper, guided by triple priors, Bright Channel Prior (BCP), Dark Channel Prior (DCP), and Histogram Equalization (HE), we propose a \textit{P}rior-\textit{g}uided Hierarchical \textit{H}armonization Network (PGH$^2$Net) for image dehazing. PGH$^2$Net is built upon the UNet-like architecture with an efficient encoder and decoder, consisting of two module types: (1) Prior aggregation module that injects B/DCP and selects diverse contexts with gating attention. (2) Feature harmonization modules that subtract low-frequency components from spatial and channel aspects and learn more informative feature distributions to equalize the feature maps.
Authors: Zhenqi Dai, Ting Liu, Xingxing Zhang, Yunchao Wei, Yanning Zhang
Abstract: In this paper, we present the One-shot In-context Part Segmentation (OIParts) framework, designed to tackle the challenges of part segmentation by leveraging visual foundation models (VFMs). Existing training-based one-shot part segmentation methods that utilize VFMs encounter difficulties when faced with scenarios where the one-shot image and test image exhibit significant variance in appearance and perspective, or when the object in the test image is partially visible. We argue that training on the one-shot example often leads to overfitting, thereby compromising the model's generalization capability. Our framework offers a novel approach to part segmentation that is training-free, flexible, and data-efficient, requiring only a single in-context example for precise segmentation with superior generalization ability. By thoroughly exploring the complementary strengths of VFMs, specifically DINOv2 and Stable Diffusion, we introduce an adaptive channel selection approach by minimizing the intra-class distance for better exploiting these two features, thereby enhancing the discriminatory power of the extracted features for the fine-grained parts. We have achieved remarkable segmentation performance across diverse object categories. The OIParts framework not only eliminates the need for extensive labeled data but also demonstrates superior generalization ability. Through comprehensive experimentation on three benchmark datasets, we have demonstrated the superiority of our proposed method over existing part segmentation approaches in one-shot settings.
Authors: Suzhen Wang, Weijie Chen, Wei Zhang, Minda Zhao, Lincheng Li, Rongsheng Zhang, Zhipeng Hu, Xin Yu
Abstract: Character customization, or 'face crafting,' is a vital feature in role-playing games (RPGs), enhancing player engagement by enabling the creation of personalized avatars. Existing automated methods often struggle with generalizability across diverse game engines due to their reliance on the intermediate constraints of specific image domain and typically support only one type of input, either text or image. To overcome these challenges, we introduce EasyCraft, an innovative end-to-end feedforward framework that automates character crafting by uniquely supporting both text and image inputs. Our approach employs a translator capable of converting facial images of any style into crafting parameters. We first establish a unified feature distribution in the translator's image encoder through self-supervised learning on a large-scale dataset, enabling photos of any style to be embedded into a unified feature representation. Subsequently, we map this unified feature distribution to crafting parameters specific to a game engine, a process that can be easily adapted to most game engines and thus enhances EasyCraft's generalizability. By integrating text-to-image techniques with our translator, EasyCraft also facilitates precise, text-based character crafting. EasyCraft's ability to integrate diverse inputs significantly enhances the versatility and accuracy of avatar creation. Extensive experiments on two RPG games demonstrate the effectiveness of our method, achieving state-of-the-art results and facilitating adaptability across various avatar engines.
Authors: Yitao Zhu, Yuan Yin, Jiaming Li, Mengjie Xu, Zihao Zhao, Honglin Xiong, Sheng Wang, Qian Wang
Abstract: The adoption of visual foundation models has become a common practice in computer-aided diagnosis (CAD). While these foundation models provide a viable solution for creating generalist medical AI, privacy concerns make it difficult to pre-train or continuously update such models across multiple domains and datasets, leading many studies to focus on specialist models. To address this challenge, we propose Med-LEGO, a training-free framework that enables the seamless integration or updating of a generalist CAD model by combining multiple specialist models, similar to assembling LEGO bricks. Med-LEGO enhances LoRA (low-rank adaptation) by incorporating singular value decomposition (SVD) to efficiently capture the domain expertise of each specialist model with minimal additional parameters. By combining these adapted weights through simple operations, Med-LEGO allows for the easy integration or modification of specific diagnostic capabilities without the need for original data or retraining. Finally, the combined model can be further adapted to new diagnostic tasks, making it a versatile generalist model. Our extensive experiments demonstrate that Med-LEGO outperforms existing methods in both cross-domain and in-domain medical tasks while using only 0.18% of full model parameters. These merged models show better convergence and generalization to new tasks, providing an effective path toward generalist medical AI.
Authors: Haoxin Li, Boyang Li
Abstract: Despite impressive advancements in various multimodal tasks, vision-language models (VLMs) still struggle with compositional understanding due to limited exposure to training samples that contain subtle variations within paired examples. With advances in multimodal generative models, a natural solution is to generate synthetic samples with subtle variations for training VLMs. However, generating and training on synthetic samples with subtle variations presents two challenges: difficulty in accurately creating precise variations and inconsistency in cross-modal alignment quality. To address these challenges, we propose SVD-GT (Subtle Variation Data Generation and Training), which integrates image feature injection into a text-to-image generative model to enhance the quality of synthetic variations and employs an adaptive margin loss to differentiate samples using adaptive margins, which help filter out potentially incorrect synthetic samples and focus the learning on informative hard samples. Evaluations on four compositional understanding benchmarks demonstrate that SVD-GT significantly improves the compositionality of VLMs, boosting the average accuracy of CLIP by over 8% across all benchmarks and outperforming state-of-the-art methods by 2% on three benchmarks.
Authors: Seyed Mohamad Ali Tousi, Ramy Farag, Jacket Demby's, Gbenga Omotara, John A. Lory, G. N. DeSouza
Abstract: Ephemeral gullies are a primary cause of soil erosion and their reliable, accurate, and early detection will facilitate significant improvements in the sustainability of global agricultural systems. In our view, prior research has not successfully addressed automated detection of ephemeral gullies from remotely sensed images, so for the first time, we present and evaluate three successful pipelines for ephemeral gully detection. Our pipelines utilize remotely sensed images, acquired from specific agricultural areas over a period of time. The pipelines were tested with various choices of Visual Language Models (VLMs), and they classified the images based on the presence of ephemeral gullies with accuracy higher than 70% and a F1-score close to 80% for positive gully detection. Additionally, we developed the first public dataset for ephemeral gully detection, labeled by a team of soil- and plant-science experts. To evaluate the proposed pipelines, we employed a variety of zero-shot classification methods based on State-of-the-Art (SOTA) open-source Vision-Language Models (VLMs). In addition to that, we compare the same pipelines with a transfer learning approach. Extensive experiments were conducted to validate the detection pipelines and to analyze the impact of hyperparameter changes in their performance. The experimental results demonstrate that the proposed zero-shot classification pipelines are highly effective in detecting ephemeral gullies in a scenario where classification datasets are scarce.
Authors: Hongye Cheng, Tianyu Wang, Guangsi Shi, Zexing Zhao, Yanwei Fu
Abstract: Co-speech gestures are crucial non-verbal cues that enhance speech clarity and expressiveness in human communication, which have attracted increasing attention in multimodal research. While the existing methods have made strides in gesture accuracy, challenges remain in generating diverse and coherent gestures, as most approaches assume independence among multimodal inputs and lack explicit modeling of their interactions. In this work, we propose a novel multimodal learning method named HOP for co-speech gesture generation that captures the heterogeneous entanglement between gesture motion, audio rhythm, and text semantics, enabling the generation of coordinated gestures. By leveraging spatiotemporal graph modeling, we achieve the alignment of audio and action. Moreover, to enhance modality coherence, we build the audio-text semantic representation based on a reprogramming module, which is beneficial for cross-modality adaptation. Our approach enables the trimodal system to learn each other's features and represent them in the form of topological entanglement. Extensive experiments demonstrate that HOP achieves state-of-the-art performance, offering more natural and expressive co-speech gesture generation. More information, codes, and demos are available here: https://star-uu-wang.github.io/HOP/
Authors: Ali Caglayan, Nevrez Imamoglu, Toru Kouyama
Abstract: Foundation model approaches such as masked auto-encoders (MAE) or its variations are now being successfully applied to satellite imagery. Most of the ongoing technical validation of foundation models have been applied to optical images like RGB or multi-spectral images. Due to difficulty in semantic labeling to create datasets and higher noise content with respect to optical images, Synthetic Aperture Radar (SAR) data has not been explored a lot in the field for foundation models. Therefore, in this work as a pre-training approach, we explored masked auto-encoder, specifically MixMAE on Sentinel-1 SAR images and its impact on SAR image classification tasks. Moreover, we proposed to use the physical characteristic of SAR data for applying weighting parameter on the auto-encoder training loss (MSE) to reduce the effect of speckle noise and very high values on the SAR images. Proposed SAR intensity-based weighting of the reconstruction loss demonstrates promising results both on SAR pre-training and downstream tasks specifically on flood detection compared with the baseline model.
Authors: Xingyuan Li, Zirui Wang, Yang Zou, Zhixin Chen, Jun Ma, Zhiying Jiang, Long Ma, Jinyuan Liu
Abstract: Infrared imaging is essential for autonomous driving and robotic operations as a supportive modality due to its reliable performance in challenging environments. Despite its popularity, the limitations of infrared cameras, such as low spatial resolution and complex degradations, consistently challenge imaging quality and subsequent visual tasks. Hence, infrared image super-resolution (IISR) has been developed to address this challenge. While recent developments in diffusion models have greatly advanced this field, current methods to solve it either ignore the unique modal characteristics of infrared imaging or overlook the machine perception requirements. To bridge these gaps, we propose DifIISR, an infrared image super-resolution diffusion model optimized for visual quality and perceptual performance. Our approach achieves task-based guidance for diffusion by injecting gradients derived from visual and perceptual priors into the noise during the reverse process. Specifically, we introduce an infrared thermal spectrum distribution regulation to preserve visual fidelity, ensuring that the reconstructed infrared images closely align with high-resolution images by matching their frequency components. Subsequently, we incorporate various visual foundational models as the perceptual guidance for downstream visual tasks, infusing generalizable perceptual features beneficial for detection and segmentation. As a result, our approach gains superior visual results while attaining State-Of-The-Art downstream task performance. Code is available at https://github.com/zirui0625/DifIISR
Authors: Jonathan Fhima, Jan Van Eijgen, Lennert Beeckmans, Thomas Jacobs, Moti Freiman, Luis Filipe Nakayama, Ingeborg Stalmans, Chaim Baskin, Joachim A. Behar
Abstract: Generalization in medical segmentation models is challenging due to limited annotated datasets and imaging variability. To address this, we propose Retinal Layout-Aware Diffusion (RLAD), a novel diffusion-based framework for generating controllable layout-aware images. RLAD conditions image generation on multiple key layout components extracted from real images, ensuring high structural fidelity while enabling diversity in other components. Applied to retinal fundus imaging, we augmented the training datasets by synthesizing paired retinal images and vessel segmentations conditioned on extracted blood vessels from real images, while varying other layout components such as lesions and the optic disc. Experiments demonstrated that RLAD-generated data improved generalization in retinal vessel segmentation by up to 8.1%. Furthermore, we present REYIA, a comprehensive dataset comprising 586 manually segmented retinal images. To foster reproducibility and drive innovation, both our code and dataset will be made publicly accessible.
Authors: Chao Qu, Shuo Zhu, Yuhang Wang, Zongze Wu, Xiaoyu Chen, Edmund Y. Lam, Jing Han
Abstract: The fields of imaging in the nighttime dynamic and other extremely dark conditions have seen impressive and transformative advancements in recent years, partly driven by the rise of novel sensing approaches, e.g., near-infrared (NIR) cameras with high sensitivity and event cameras with minimal blur. However, inappropriate exposure ratios of near-infrared cameras make them susceptible to distortion and blur. Event cameras are also highly sensitive to weak signals at night yet prone to interference, often generating substantial noise and significantly degrading observations and analysis. Herein, we develop a new framework for low-light imaging combined with NIR imaging and event-based techniques, named synergistic neuromorphic imaging, which can jointly achieve NIR image deblurring and event denoising. Harnessing cross-modal features of NIR images and visible events via spectral consistency and higher-order interaction, the NIR images and events are simultaneously fused, enhanced, and bootstrapped. Experiments on real and realistically simulated sequences demonstrate the effectiveness of our method and indicate better accuracy and robustness than other methods in practical scenarios. This study gives impetus to enhance both NIR images and events, which paves the way for high-fidelity low-light imaging and neuromorphic reasoning.
Authors: Kaimin Liao
Abstract: Gaussian splatting has emerged as a powerful technique for reconstruction of 3D scenes in computer graphics and vision. However, conventional implementations often suffer from inefficiencies, limited flexibility, and high computational overhead, which constrain their adaptability to diverse applications. In this paper, we present LiteGS,a high-performance and modular framework that enhances both the efficiency and usability of Gaussian splatting. LiteGS achieves a 3.4x speedup over the original 3DGS implementation while reducing GPU memory usage by approximately 30%. Its modular design decomposes the splatting process into multiple highly optimized operators, and it provides dual API support via a script-based interface and a CUDA-based interface. The script-based interface, in combination with autograd, enables rapid prototyping and straightforward customization of new ideas, while the CUDA-based interface delivers optimal training speeds for performance-critical applications. LiteGS retains the core algorithm of 3DGS, ensuring compatibility. Comprehensive experiments on the Mip-NeRF 360 dataset demonstrate that LiteGS accelerates training without compromising accuracy, making it an ideal solution for both rapid prototyping and production environments.
Authors: Louis Mahon, Mirella Lapata
Abstract: The proliferation of creative video content has driven demand for adapting language models to handle video input and enable multimodal understanding. However, end-to-end models struggle to process long videos due to their size and complexity. An effective alternative is to divide them into smaller chunks to be processed separately, and this motivates a method for choosing where the chunk boundaries should be. In this paper, we propose an algorithm for segmenting videos into contiguous chunks, based on the minimum description length principle, coupled with a dynamic programming search. The algorithm is entirely parameter-free, given feature vectors, not requiring a set threshold or the number or size of chunks to be specified. We show empirically that the breakpoints it produces more accurately approximate scene boundaries in long videos, compared with existing methods for scene detection, even when such methods have access to the true number of scenes. We then showcase this algorithm in two tasks: long video summarization, and retrieval-augmented video question answering. In both cases, scene breaks produced by our algorithm lead to better downstream performance than existing methods for video segmentation.
Authors: Jialei He, Zhihao Zhan, Zhituo Tu, Xiang Zhu, Jie Yuan
Abstract: Rapid generation of large-scale orthoimages from Unmanned Aerial Vehicles (UAVs) has been a long-standing focus of research in the field of aerial mapping. A multi-sensor UAV system, integrating the Global Positioning System (GPS), Inertial Measurement Unit (IMU), 4D millimeter-wave radar and camera, can provide an effective solution to this problem. In this paper, we utilize multi-sensor data to overcome the limitations of conventional orthoimage generation methods in terms of temporal performance, system robustness, and geographic reference accuracy. A prior-pose-optimized feature matching method is introduced to enhance matching speed and accuracy, reducing the number of required features and providing precise references for the Structure from Motion (SfM) process. The proposed method exhibits robustness in low-texture scenes like farmlands, where feature matching is difficult. Experiments show that our approach achieves accurate feature matching orthoimage generation in a short time. The proposed drone system effectively aids in farmland detection and management.
Authors: Tianjie Ju, Yi Hua, Hao Fei, Zhenyu Shao, Yubin Zheng, Haodong Zhao, Mong-Li Lee, Wynne Hsu, Zhuosheng Zhang, Gongshen Liu
Abstract: Multi-Modal Large Language Models (MLLMs) have exhibited remarkable performance on various vision-language tasks such as Visual Question Answering (VQA). Despite accumulating evidence of privacy concerns associated with task-relevant content, it remains unclear whether MLLMs inadvertently memorize private content that is entirely irrelevant to the training tasks. In this paper, we investigate how randomly generated task-irrelevant private content can become spuriously correlated with downstream objectives due to partial mini-batch training dynamics, thus causing inadvertent memorization. Concretely, we randomly generate task-irrelevant watermarks into VQA fine-tuning images at varying probabilities and propose a novel probing framework to determine whether MLLMs have inadvertently encoded such content. Our experiments reveal that MLLMs exhibit notably different training behaviors in partial mini-batch settings with task-irrelevant watermarks embedded. Furthermore, through layer-wise probing, we demonstrate that MLLMs trigger distinct representational patterns when encountering previously seen task-irrelevant knowledge, even if this knowledge does not influence their output during prompting. Our code is available at https://github.com/illusionhi/ProbingPrivacy.
Authors: Guanyao Wu, Haoyu Liu, Hongming Fu, Yichuan Peng, Jinyuan Liu, Xin Fan, Risheng Liu
Abstract: Multi-modality image fusion, particularly infrared and visible image fusion, plays a crucial role in integrating diverse modalities to enhance scene understanding. Early research primarily focused on visual quality, yet challenges remain in preserving fine details, making it difficult to adapt to subsequent tasks. Recent approaches have shifted towards task-specific design, but struggle to achieve the ``The Best of Both Worlds'' due to inconsistent optimization goals. To address these issues, we propose a novel method that leverages the semantic knowledge from the Segment Anything Model (SAM) to Grow the quality of fusion results and Establish downstream task adaptability, namely SAGE. Specifically, we design a Semantic Persistent Attention (SPA) Module that efficiently maintains source information via the persistent repository while extracting high-level semantic priors from SAM. More importantly, to eliminate the impractical dependence on SAM during inference, we introduce a bi-level optimization-driven distillation mechanism with triplet losses, which allow the student network to effectively extract knowledge at the feature, pixel, and contrastive semantic levels, thereby removing reliance on the cumbersome SAM model. Extensive experiments show that our method achieves a balance between high-quality visual results and downstream task adaptability while maintaining practical deployment efficiency.
Authors: Deyu Bo, Songhua Liu, Xinchao Wang
Abstract: Dataset distillation (DD) has emerged as a promising approach to compress datasets and speed up model training. However, the underlying connections among various DD methods remain largely unexplored. In this paper, we introduce UniDD, a spectral filtering framework that unifies diverse DD objectives. UniDD interprets each DD objective as a specific filter function that affects the eigenvalues of the feature-feature correlation (FFC) matrix and modulates the frequency components of the feature-label correlation (FLC) matrix. In this way, UniDD reveals that the essence of DD fundamentally lies in matching frequency-specific features. Moreover, according to the filter behaviors, we classify existing methods into low-frequency matching and high-frequency matching, encoding global texture and local details, respectively. However, existing methods rely on fixed filter functions throughout distillation, which cannot capture the low- and high-frequency information simultaneously. To address this limitation, we further propose Curriculum Frequency Matching (CFM), which gradually adjusts the filter parameter to cover both low- and high-frequency information of the FFC and FLC matrices. Extensive experiments on small-scale datasets, such as CIFAR-10/100, and large-scale datasets, including ImageNet-1K, demonstrate the superior performance of CFM over existing baselines and validate the practicality of UniDD.
Authors: Yuhan Bao, Shaohua Gao, Wenyong Li, Kaiwei Wang
Abstract: High-speed autofocus in extreme scenes remains a significant challenge. Traditional methods rely on repeated sampling around the focus position, resulting in ``focus hunting''. Event-driven methods have advanced focusing speed and improved performance in low-light conditions; however, current approaches still require at least one lengthy round of ``focus hunting'', involving the collection of a complete focus stack. We introduce the Event Laplacian Product (ELP) focus detection function, which combines event data with grayscale Laplacian information, redefining focus search as a detection task. This innovation enables the first one-step event-driven autofocus, cutting focusing time by up to two-thirds and reducing focusing error by 24 times on the DAVIS346 dataset and 22 times on the EVK4 dataset. Additionally, we present an autofocus pipeline tailored for event-only cameras, achieving accurate results across a range of challenging motion and lighting conditions. All datasets and code will be made publicly available.
Authors: Jiqing Wu, Ingrid Berg, Yawei Li, Ender Konukoglu, Viktor H. Koelzer
Abstract: Holistic 3D modeling of molecularly defined brain structures is crucial for understanding complex brain functions. Emerging tissue profiling technologies enable the construction of a comprehensive atlas of the mammalian brain with sub-cellular resolution and spatially resolved gene expression data. However, such tera-scale volumetric datasets present significant computational challenges in understanding complex brain functions within their native 3D spatial context. Here, we propose the novel generative approach $\textbf{Tera-MIND}$, which can simulate $\textbf{Tera}$-scale $\textbf{M}$ouse bra$\textbf{IN}$s in 3D using a patch-based and boundary-aware $\textbf{D}$iffusion model. Taking spatial transcriptomic data as the conditional input, we generate virtual mouse brains with comprehensive cellular morphological detail at teravoxel scale. Through the lens of 3D $gene$-$gene$ self-attention, we identify spatial molecular interactions for key transcriptomic pathways in the murine brain, exemplified by glutamatergic and dopaminergic neuronal systems. Importantly, these $in$-$silico$ biological findings are consistent and reproducible across three tera-scale virtual mouse brains. Therefore, Tera-MIND showcases a promising path toward efficient and generative simulations of whole organ systems for biomedical research. Project website: https://musikisomorphie.github.io/Tera-MIND.html
Authors: Wenbin Wang, Yongcheng Jing, Liang Ding, Yingjie Wang, Li Shen, Yong Luo, Bo Du, Dacheng Tao
Abstract: High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To overcome the limitations of existing methods, this paper shifts away from prior dedicated heuristic approaches and revisits the most fundamental idea to HR perception by enhancing the long-context capability of MLLMs, driven by recent advances in long-context techniques like retrieval-augmented generation (RAG) for general LLMs. Towards this end, this paper presents the first study exploring the use of RAG to address HR perception challenges. Specifically, we propose Retrieval-Augmented Perception (RAP), a training-free framework that retrieves and fuses relevant image crops while preserving spatial context using the proposed Spatial-Awareness Layout. To accommodate different tasks, the proposed Retrieved-Exploration Search (RE-Search) dynamically selects the optimal number of crops based on model confidence and retrieval scores. Experimental results on HR benchmarks demonstrate the significant effectiveness of RAP, with LLaVA-v1.5-13B achieving a 43% improvement on $V^*$ Bench and 19% on HR-Bench.
Authors: Sijin Sun, Ming Deng, Xingrui Yu, Xinyu Xi, Liangbin Zhao
Abstract: Metal defect detection is critical in industrial quality assurance, yet existing methods struggle with grayscale variations and complex defect states, limiting its robustness. To address these challenges, this paper proposes a Self-Adaptive Gamma Context-Aware SSM-based model(GCM-DET). This advanced detection framework integrating a Dynamic Gamma Correction (GC) module to enhance grayscale representation and optimize feature extraction for precise defect reconstruction. A State-Space Search Management (SSM) architecture captures robust multi-scale features, effectively handling defects of varying shapes and scales. Focal Loss is employed to mitigate class imbalance and refine detection accuracy. Additionally, the CD5-DET dataset is introduced, specifically designed for port container maintenance, featuring significant grayscale variations and intricate defect patterns. Experimental results demonstrate that the proposed model achieves substantial improvements, with mAP@0.5 gains of 27.6\%, 6.6\%, and 2.6\% on the CD5-DET, NEU-DET, and GC10-DET datasets.
Authors: Xiaolong Yu, Junqiao Zhao, Shuangfu Song, Zhongyang Zhu, Zihan Yuan, Chen Ye, Tiantian Feng
Abstract: Using Quadrics as the object representation has the benefits of both generality and closed-form projection derivation between image and world spaces. Although numerous constraints have been proposed for dual quadric reconstruction, we found that many of them are imprecise and provide minimal improvements to localization.After scrutinizing the existing constraints, we introduce a concise yet more precise convex hull-based algebraic constraint for object landmarks, which is applied to object reconstruction, frontend pose estimation, and backend bundle adjustment.This constraint is designed to fully leverage precise semantic segmentation, effectively mitigating mismatches between complex-shaped object contours and dual quadrics.Experiments on public datasets demonstrate that our approach is applicable to both monocular and RGB-D SLAM and achieves improved object mapping and localization than existing quadric SLAM methods. The implementation of our method is available at https://github.com/tiev-tongji/convexhull-based-algebraic-constraint.
URLs: https://github.com/tiev-tongji/convexhull-based-algebraic-constraint.
Authors: Xuan Zhu, Jijun Xiang, Xianqi Wang, Longliang Liu, Yu Wang, Hong Zhang, Fei Guo, Xin Yang
Abstract: Lightweight direct Time-of-Flight (dToF) sensors are ideal for 3D sensing on mobile devices. However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth maps are sparse and noisy. In this paper, we propose a novel video depth completion method, called SVDC, by fusing the sparse dToF data with the corresponding RGB guidance. Our method employs a multi-frame fusion scheme to mitigate the spatial ambiguity resulting from the sparse dToF imaging. Misalignment between consecutive frames during multi-frame fusion could cause blending between object edges and the background, which results in a loss of detail. To address this, we introduce an adaptive frequency selective fusion (AFSF) module, which automatically selects convolution kernel sizes to fuse multi-frame features. Our AFSF utilizes a channel-spatial enhancement attention (CSEA) module to enhance features and generates an attention map as fusion weights. The AFSF ensures edge detail recovery while suppressing high-frequency noise in smooth regions. To further enhance temporal consistency, We propose a cross-window consistency loss to ensure consistent predictions across different windows, effectively reducing flickering. Our proposed SVDC achieves optimal accuracy and consistency on the TartanAir and Dynamic Replica datasets. Code is available at https://github.com/Lan1eve/SVDC.
Authors: Guotao Liang, Baoquan Zhang, Zhiyuan Wen, Junteng Zhao, Yunming Ye, Kola Ye, Yao He
Abstract: Image quantization is a crucial technique in image generation, aimed at learning a codebook that encodes an image into a discrete token sequence. Recent advancements have seen researchers exploring learning multi-modal codebook (i.e., text-aligned codebook) by utilizing image caption semantics, aiming to enhance codebook performance in cross-modal tasks. However, existing image-text paired datasets exhibit a notable flaw in that the text descriptions tend to be overly concise, failing to adequately describe the images and provide sufficient semantic knowledge, resulting in limited alignment of text and codebook at a fine-grained level. In this paper, we propose a novel Text-Augmented Codebook Learning framework, named TA-VQ, which generates longer text for each image using the visual-language model for improved text-aligned codebook learning. However, the long text presents two key challenges: how to encode text and how to align codebook and text. To tackle two challenges, we propose to split the long text into multiple granularities for encoding, i.e., word, phrase, and sentence, so that the long text can be fully encoded without losing any key semantic knowledge. Following this, a hierarchical encoder and novel sampling-based alignment strategy are designed to achieve fine-grained codebook-text alignment. Additionally, our method can be seamlessly integrated into existing VQ models. Extensive experiments in reconstruction and various downstream tasks demonstrate its effectiveness compared to previous state-of-the-art approaches.
Authors: Huayu Zhang, Dongyue Wu, Yuanjie Shao, Nong Sang, Changxin Gao
Abstract: Recently, trimap-free methods have drawn increasing attention in human video matting due to their promising performance. Nevertheless, these methods still suffer from the lack of deterministic foreground-background cues, which impairs their ability to consistently identify and locate foreground targets over time and mine fine-grained details. In this paper, we present a trimap-free Object-Aware Video Matting (OAVM) framework, which can perceive different objects, enabling joint recognition of foreground objects and refinement of edge details. Specifically, we propose an Object-Guided Correction and Refinement (OGCR) module, which employs cross-frame guidance to aggregate object-level instance information into pixel-level detail features, thereby promoting their synergy. Furthermore, we design a Sequential Foreground Merging augmentation strategy to diversify sequential scenarios and enhance capacity of the network for object discrimination. Extensive experiments on recent widely used synthetic and real-world benchmarks demonstrate the state-of-the-art performance of our OAVM with only an initial coarse mask. The code and model will be available.
Authors: Fangming Cui, Yonggang Zhang, Xuan Wang, Xule Wang, Liang Xiao
Abstract: Existing vision-language models (VLMs) such as CLIP have showcased an impressive capability to generalize well across various downstream tasks. These models leverage the synergy between visual and textual information, enabling them to understand and reason about the content present in images and text in a unified manner. This article provides a brief overview of CLIP based on few-shot prompt learning, including experimental data and technical characteristics of some methods. The purpose of this review is to provide a reference for researchers who have just started their research in generalizable prompting of CLIP through few-shot training for classification across 15 datasets and also to facilitate the integration of this field by researchers in other downstream tasks.
Authors: Md Abrar Jahin, Soudeep Shahriar, M. F. Mridha, Nilanjan Dey
Abstract: Soybean leaf disease detection is critical for agricultural productivity but faces challenges due to visually similar symptoms and limited interpretability in conventional methods. While Convolutional Neural Networks (CNNs) excel in spatial feature extraction, they often neglect inter-image relational dependencies, leading to misclassifications. This paper proposes an interpretable hybrid Sequential CNN-Graph Neural Network (GNN) framework that synergizes MobileNetV2 for localized feature extraction and GraphSAGE for relational modeling. The framework constructs a graph where nodes represent leaf images, with edges defined by cosine similarity-based adjacency matrices and adaptive neighborhood sampling. This design captures fine-grained lesion features and global symptom patterns, addressing inter-class similarity challenges. Cross-modal interpretability is achieved via Grad-CAM and Eigen-CAM visualizations, generating heatmaps to highlight disease-influential regions. Evaluated on a dataset of ten soybean leaf diseases, the model achieves $97.16\%$ accuracy, surpassing standalone CNNs ($\le95.04\%$) and traditional machine learning models ($\le77.05\%$). Ablation studies validate the sequential architecture's superiority over parallel or single-model configurations. With only 2.3 million parameters, the lightweight MobileNetV2-GraphSAGE combination ensures computational efficiency, enabling real-time deployment in resource-constrained environments. The proposed approach bridges the gap between accurate classification and practical applicability, offering a robust, interpretable tool for agricultural diagnostics while advancing CNN-GNN integration in plant pathology research.
Authors: Chong Wang, Lanqing Guo, Zixuan Fu, Siyuan Yang, Hao Cheng, Alex C. Kot, Bihan Wen
Abstract: Plug-and-play (PnP) methods offer an iterative strategy for solving image restoration (IR) problems in a zero-shot manner, using a learned \textit{discriminative denoiser} as the implicit prior. More recently, a sampling-based variant of this approach, which utilizes a pre-trained \textit{generative diffusion model}, has gained great popularity for solving IR problems through stochastic sampling. The IR results using PnP with a pre-trained diffusion model demonstrate distinct advantages compared to those using discriminative denoisers, \ie improved perceptual quality while sacrificing the data fidelity. The unsatisfactory results are due to the lack of integration of these strategies in the IR tasks. In this work, we propose a novel zero-shot IR scheme, dubbed Reconciling Diffusion Model in Dual (RDMD), which leverages only a \textbf{single} pre-trained diffusion model to construct \textbf{two} complementary regularizers. Specifically, the diffusion model in RDMD will iteratively perform deterministic denoising and stochastic sampling, aiming to achieve high-fidelity image restoration with appealing perceptual quality. RDMD also allows users to customize the distortion-perception tradeoff with a single hyperparameter, enhancing the adaptability of the restoration process in different practical scenarios. Extensive experiments on several IR tasks demonstrate that our proposed method could achieve superior results compared to existing approaches on both the FFHQ and ImageNet datasets.
Authors: Peishan Cong, Ziyi Wang, Yuexin Ma, Xiangyu Yue
Abstract: Generating reasonable and high-quality human interactive motions in a given dynamic environment is crucial for understanding, modeling, transferring, and applying human behaviors to both virtual and physical robots. In this paper, we introduce an effective method, SemGeoMo, for dynamic contextual human motion generation, which fully leverages the text-affordance-joint multi-level semantic and geometric guidance in the generation process, improving the semantic rationality and geometric correctness of generative motions. Our method achieves state-of-the-art performance on three datasets and demonstrates superior generalization capability for diverse interaction scenarios. The project page and code can be found at https://4dvlab.github.io/project_page/semgeomo/.
Authors: Yurui Pan, Lidong Wang, Yuchao Chen, Wenbing Zhu, Bo Peng, Mingmin Chi
Abstract: In industrial anomaly detection (IAD), accurately identifying defects amidst diverse anomalies and under varying imaging conditions remains a significant challenge. Traditional approaches often struggle with high false-positive rates, frequently misclassifying normal shadows and surface deformations as defects, an issue that becomes particularly pronounced in products with complex and intricate surface features. To address these challenges, we introduce PA-CLIP, a zero-shot anomaly detection method that reduces background noise and enhances defect detection through a pseudo-anomaly-based framework. The proposed method integrates a multiscale feature aggregation strategy for capturing detailed global and local information, two memory banks for distinguishing background information, including normal patterns and pseudo-anomalies, from true anomaly features, and a decision-making module designed to minimize false positives caused by environmental variations while maintaining high defect sensitivity. Demonstrated on the MVTec AD and VisA datasets, PA-CLIP outperforms existing zero-shot methods, providing a robust solution for industrial defect detection.
Authors: Rong Zhang, Jingnan Wang, Zhiwen Zuo, Jianfeng Dong, Wei Li, Chi Wang, Weiwei Xu, Xun Wang
Abstract: In this paper, we propose a novel garment-centric outpainting (GCO) framework based on the latent diffusion model (LDM) for fine-grained controllable apparel showcase image generation. The proposed framework aims at customizing a fashion model wearing a given garment via text prompts and facial images. Different from existing methods, our framework takes a garment image segmented from a dressed mannequin or a person as the input, eliminating the need for learning cloth deformation and ensuring faithful preservation of garment details. The proposed framework consists of two stages. In the first stage, we introduce a garment-adaptive pose prediction model that generates diverse poses given the garment. Then, in the next stage, we generate apparel showcase images, conditioned on the garment and the predicted poses, along with specified text prompts and facial images. Notably, a multi-scale appearance customization module (MS-ACM) is designed to allow both overall and fine-grained text-based control over the generated model's appearance. Moreover, we leverage a lightweight feature fusion operation without introducing any extra encoders or modules to integrate multiple conditions, which is more efficient. Extensive experiments validate the superior performance of our framework compared to state-of-the-art methods.
Authors: Yi Wang, Mushui Liu, Wanggui He, Longxiang Zhang, Ziwei Huang, Guanghao Zhang, Fangxun Shu, Zhong Tao, Dong She, Zhelun Yu, Haoyuan Li, Weilong Dai, Mingli Song, Jie Song, Hao Jiang
Abstract: Unified generative models have demonstrated extraordinary performance in both text and image generation. However, they tend to underperform when generating intricate images with various interwoven conditions, which is hard to solely rely on straightforward text-to-image generation. In response to this challenge, we introduce MINT, an innovative unified generative model, empowered with native multimodal chain of thought (MCoT) for enhanced image generation for the first time. Firstly, we design Mixture of Transformer Experts (MTXpert), an expert-parallel structure that effectively supports both natural language generation (NLG) and visual capabilities, while avoiding potential modality conflicts that could hinder the full potential of each modality. Building on this, we propose an innovative MCoT training paradigm, a step-by-step approach to multimodal thinking, reasoning, and reflection specifically designed to enhance image generation. This paradigm equips MINT with nuanced, element-wise decoupled alignment and a comprehensive understanding of textual and visual components. Furthermore, it fosters advanced multimodal reasoning and self-reflection, enabling the construction of images that are firmly grounded in the logical relationships between these elements. Notably, MINT has been validated to exhibit superior performance across multiple benchmarks for text-to-image (T2I) and image-to-text (I2T) tasks.
Authors: Yijie Tang, Jiazhao Zhang, Yuqing Lan, Yulan Guo, Dezun Dong, Chenyang Zhu, Kai Xu
Abstract: Online 3D open-vocabulary segmentation of a progressively reconstructed scene is both a critical and challenging task for embodied applications. With the success of visual foundation models (VFMs) in the image domain, leveraging 2D priors to address 3D online segmentation has become a prominent research focus. Since segmentation results provided by 2D priors often require spatial consistency to be lifted into final 3D segmentation, an efficient method for identifying spatial overlap among 2D masks is essential - yet existing methods rarely achieve this in real time, mainly limiting its use to offline approaches. To address this, we propose an efficient method that lifts 2D masks generated by VFMs into a unified 3D instance using a hashing technique. By employing voxel hashing for efficient 3D scene querying, our approach reduces the time complexity of costly spatial overlap queries from $O(n^2)$ to $O(n)$. Accurate spatial associations further enable 3D merging of 2D masks through simple similarity-based filtering in a zero-shot manner, making our approach more robust to incomplete and noisy data. Evaluated on the ScanNet and SceneNN benchmarks, our approach achieves state-of-the-art performance in online, open-vocabulary 3D instance segmentation with leading efficiency.
Authors: Xuewen Liu, Zhikai Li, Qingyi Gu
Abstract: Diffusion models have gradually gained prominence in the field of image synthesis, showcasing remarkable generative capabilities. Nevertheless, the slow inference and complex networks, resulting from redundancy at both temporal and structural levels, hinder their low-latency applications in real-world scenarios. Current acceleration methods for diffusion models focus separately on temporal and structural levels. However, independent optimization at each level to further push the acceleration limits results in significant performance degradation. On the other hand, integrating optimizations at both levels can compound the acceleration effects. Unfortunately, we find that the optimizations at these two levels are not entirely orthogonal. Performing separate optimizations and then simply integrating them results in unsatisfactory performance. To tackle this issue, we propose CacheQuant, a novel training-free paradigm that comprehensively accelerates diffusion models by jointly optimizing model caching and quantization techniques. Specifically, we employ a dynamic programming approach to determine the optimal cache schedule, in which the properties of caching and quantization are carefully considered to minimize errors. Additionally, we propose decoupled error correction to further mitigate the coupled and accumulated errors step by step. Experimental results show that CacheQuant achieves a 5.18 speedup and 4 compression for Stable Diffusion on MS-COCO, with only a 0.02 loss in CLIP score. Our code are open-sourced: https://github.com/BienLuky/CacheQuant .
Authors: Xu Liang
Abstract: Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (SCST) for reinforcement learning optimization. However, the SCST algorithm has certain defects. SCST relies only on a single greedy decoding result as a baseline. If the model itself is not stable enough, the greedy decoding result may be relatively worst, which will lead to a high variance of advantage estimation, further leading to unstable policy updates. In addition, SCST only compares one sampling result with the greedy decoding result, and the generation diversity is limited, which may fall into a local optimum. In this paper, we propose using the latest Group Relative Policy Optimization (GRPO) reinforcement learning algorithm as an optimization solution for the second stage. GRPO generates multiple candidate captions for the input image and then continuously optimizes the model through intragroup comparison. By constraining the amplitude of policy updates and KL divergence, the stability of the model during training is greatly guaranteed. In addition, compared to SCST, which only samples one answer, GRPO samples and generates multiple answers. Multiple candidate answers in the group cover a wider solution space. Combined with KL divergence constraints, GRPO can improve diversity while ensuring model stability. The code for this article is available at https://github.com/liangxu-one/ms-models/tree/image_caption_grpo/research/arxiv_papers/Image_Caption_GRPO.
Authors: Zihan Shen, Yu Xuan, Qingyu Yang
Abstract: Image restoration under adverse weather conditions refers to the process of removing degradation caused by weather particles while improving visual quality. Most existing deweathering methods rely on increasing the network scale and data volume to achieve better performance which requires more expensive computing power. Also, many methods lack generalization for specific applications. In the traffic surveillance screener, the main challenges are snow removal and veil effect elimination. In this paper, we propose a wavelet-enhanced snow removal method that use a Dual-Tree Complex Wavelet Transform feature enhancement module and a dynamic convolution acceleration module to address snow degradation in surveillance images. We also use a residual learning restoration module to remove veil effects caused by rain, snow, and fog. The proposed architecture extracts and analyzes information from snow-covered regions, significantly improving snow removal performance. And the residual learning restoration module removes veiling effects in images, enhancing clarity and detail. Experiments show that it performs better than some popular desnowing methods. Our approach also demonstrates effectiveness and accuracy when applied to real traffic surveillance images.
Authors: Hao Tang, Chenwei Xie, Haiyang Wang, Xiaoyi Bao, Tingyu Weng, Pandeng Li, Yun Zheng, Liwei Wang
Abstract: Generalist models have achieved remarkable success in both language and vision-language tasks, showcasing the potential of unified modeling. However, effectively integrating fine-grained perception tasks like detection and segmentation into these models remains a significant challenge. This is primarily because these tasks often rely heavily on task-specific designs and architectures that can complicate the modeling process. To address this challenge, we present \ours, a framework that \textbf{U}nifies \textbf{F}ine-grained visual perception tasks through an \textbf{O}pen-ended language interface. By transforming all perception targets into the language space, \ours unifies object-level detection, pixel-level segmentation, and image-level vision-language tasks into a single model. Additionally, we introduce a novel embedding retrieval approach that relies solely on the language interface to support segmentation tasks. Our framework bridges the gap between fine-grained perception and vision-language tasks, significantly simplifying architectural design and training strategies while achieving comparable or superior performance to methods with intricate task-specific designs. After multi-task training on five standard visual perception datasets, \ours outperforms the previous state-of-the-art generalist models by 12.3 mAP on COCO instance segmentation and 3.3 mIoU on ADE20K semantic segmentation. Furthermore, our method seamlessly integrates with existing MLLMs, effectively combining fine-grained perception capabilities with their advanced language abilities, thereby enabling more challenging tasks such as reasoning segmentation. Code and models are available at https://github.com/nnnth/UFO.
Authors: Ruikun Zhang, Yan Yang, Liyuan Pan
Abstract: Spatial transcriptomics (ST) measures gene expression at fine-grained spatial resolution, offering insights into tissue molecular landscapes. Previous methods for spatial gene expression prediction usually crop spots of interest from pathology tissue slide images, and learn a model that maps each spot to a single gene expression profile. However, it fundamentally loses spatial resolution of gene expression: 1) each spot often contains multiple cells with distinct gene expression; 2) spots are cropped at fixed resolutions, limiting the ability to predict gene expression at varying spatial scales. To address these limitations, this paper presents PixNet, a dense prediction network capable of predicting spatially resolved gene expression across spots of varying sizes and scales directly from pathology images. Different from previous methods that map individual spots to gene expression values, we generate a dense continuous gene expression map from the pathology image, and aggregate values within spots of interest to predict the gene expression. Our PixNet outperforms state-of-the-art methods on 3 common ST datasets, while showing superior performance in predicting gene expression across multiple spatial scales. The source code will be publicly available.
Authors: Siddhant Prakash, David R. Walton, Rafael K. dos Anjos, Anthony Steed, Tobias Ritschel
Abstract: Real camera footage is subject to noise, motion blur (MB) and depth of field (DoF). In some applications these might be considered distortions to be removed, but in others it is important to model them because it would be ineffective, or interfere with an aesthetic choice, to simply remove them. In augmented reality applications where virtual content is composed into a live video feed, we can model noise, MB and DoF to make the virtual content visually consistent with the video. Existing methods for this typically suffer two main limitations. First, they require a camera calibration step to relate a known calibration target to the specific cameras response. Second, existing work require methods that can be (differentiably) tuned to the calibration, such as slow and specialized neural networks. We propose a method which estimates parameters for noise, MB and DoF instantly, which allows using off-the-shelf real-time simulation methods from e.g., a game engine in compositing augmented content. Our main idea is to unlock both features by showing how to use modern computer vision methods that can remove noise, MB and DoF from the video stream, essentially providing self-calibration. This allows to auto-tune any black-box real-time noise+MB+DoF method to deliver fast and high-fidelity augmentation consistency.
Authors: Gaozheng Pei, Shaojie Lyu, Gong Chen, Ke Ma, Qianqian Xu, Yingfei Sun, Qingming Huang
Abstract: Existing diffusion-based purification methods aim to disrupt adversarial perturbations by introducing a certain amount of noise through a forward diffusion process, followed by a reverse process to recover clean examples. However, this approach is fundamentally flawed: the uniform operation of the forward process across all pixels compromises normal pixels while attempting to combat adversarial perturbations, resulting in the target model producing incorrect predictions. Simply relying on low-intensity noise is insufficient for effective defense. To address this critical issue, we implement a heterogeneous purification strategy grounded in the interpretability of neural networks. Our method decisively applies higher-intensity noise to specific pixels that the target model focuses on while the remaining pixels are subjected to only low-intensity noise. This requirement motivates us to redesign the sampling process of the diffusion model, allowing for the effective removal of varying noise levels. Furthermore, to evaluate our method against strong adaptative attack, our proposed method sharply reduces time cost and memory usage through a single-step resampling. The empirical evidence from extensive experiments across three datasets demonstrates that our method outperforms most current adversarial training and purification techniques by a substantial margin.
Authors: Ramanathan Rajendiran, Debaditya Roy, Basura Fernando
Abstract: Anticipating future events is crucial for various application domains such as healthcare, smart home technology, and surveillance. Narrative event descriptions provide context-rich information, enhancing a system's future planning and decision-making capabilities. We propose a novel task: $\textit{long-term future narration generation}$, which extends beyond traditional action anticipation by generating detailed narrations of future daily activities. We introduce a visual-language model, ViNa, specifically designed to address this challenging task. ViNa integrates long-term videos and corresponding narrations to generate a sequence of future narrations that predict subsequent events and actions over extended time horizons. ViNa extends existing multimodal models that perform only short-term predictions or describe observed videos by generating long-term future narrations for a broader range of daily activities. We also present a novel downstream application that leverages the generated narrations called future video retrieval to help users improve planning for a task by visualizing the future. We evaluate future narration generation on the largest egocentric dataset Ego4D.
Authors: Naifu Xue, Zhaoyang Jia, Jiahao Li, Bin Li, Yuan Zhang, Yan Lu
Abstract: Recent studies in extreme image compression have achieved remarkable performance by compressing the tokens from generative tokenizers. However, these methods often prioritize clustering common semantics within the dataset, while overlooking the diverse details of individual objects. Consequently, this results in suboptimal reconstruction fidelity, especially at low bitrates. To address this issue, we introduce a Dual-generative Latent Fusion (DLF) paradigm. DLF decomposes the latent into semantic and detail elements, compressing them through two distinct branches. The semantic branch clusters high-level information into compact tokens, while the detail branch encodes perceptually critical details to enhance the overall fidelity. Additionally, we propose a cross-branch interactive design to reduce redundancy between the two branches, thereby minimizing the overall bit cost. Experimental results demonstrate the impressive reconstruction quality of DLF even below 0.01 bits per pixel (bpp). On the CLIC2020 test set, our method achieves bitrate savings of up to 27.93% on LPIPS and 53.55% on DISTS compared to MS-ILLM. Furthermore, DLF surpasses recent diffusion-based codecs in visual fidelity while maintaining a comparable level of generative realism. Code will be available later.
Authors: Fatima Ahmed, Parag Biswas, Abdur Rashid, Md. Khaliluzzaman
Abstract: Falls are a common cause of fatal injuries and hospitalization. However, having fall detection on person, in particular for senior citizens can prove to be critical. Presently,there are handheld, ambient detector and vision-based detection techniques being utilized for fall detection. However, the approaches have issues with accuracy and cost. In this regard, in this research, an approach is proposed to detect falls in indoor environments utilizing the handcrafted features extracted from human body skeleton. The human body skeleton is formed using MediaPipe framework. Results on UR Fall detection show the superiority of our model, capable of detecting falls correctly in a wide number of settings involving people belonging to different ages and genders. This proposed model using MediaPipe for fall classification in daily activities achieves significant accuracy compare to the present existing approaches.
Authors: Xiangjun Tang, Biao Zhang, Peter Wonka
Abstract: Realistic human geometry generation is an important yet challenging task, requiring both the preservation of fine clothing details and the accurate modeling of clothing-pose interactions. Geometry distributions, which can model the geometry of a single human as a distribution, provide a promising representation for high-fidelity synthesis. However, applying geometry distributions for human generation requires learning a dataset-level distribution over numerous individual geometry distributions. To address the resulting challenges, we propose a novel 3D human generative framework that, for the first time, models the distribution of human geometry distributions. Our framework operates in two stages: first, generating the human geometry distribution, and second, synthesizing high-fidelity humans by sampling from this distribution. We validate our method on two tasks: pose-conditioned 3D human generation and single-view-based novel pose generation. Experimental results demonstrate that our approach achieves the best quantitative results in terms of realism and geometric fidelity, outperforming state-of-the-art generative methods.
Authors: Pankaj Choudhury, Yogesh Aggarwal, Prithwijit Guha, Sukumar Nandi
Abstract: Neural networks have significantly advanced AI applications, yet their real-world adoption remains constrained by high computational demands, hardware limitations, and accessibility challenges. In image captioning, many state-of-the-art models have achieved impressive performances while relying on resource-intensive architectures. This made them impractical for deployment on resource-constrained devices. This limitation is particularly noticeable for applications involving low-resource languages. We demonstrate the case of image captioning in Assamese language, where lack of effective, scalable systems can restrict the accessibility of AI-based solutions for native Assamese speakers. This work presents AC-Lite, a computationally efficient model for image captioning in low-resource Assamese language. AC-Lite reduces computational requirements by replacing computation-heavy visual feature extractors like FasterRCNN with lightweight ShuffleNetv2x1.5. Additionally, Gated Recurrent Units (GRUs) are used as the caption decoder to further reduce computational demands and model parameters. Furthermore, the integration of bilinear attention enhances the model's overall performance. AC-Lite can operate on edge devices, thereby eliminating the need for computation on remote servers. The proposed AC-Lite model achieves 82.3 CIDEr score on the COCO-AC dataset with 1.098 GFLOPs and 25.65M parameters.
Authors: Zhixiong Nan, Xianghong Li, Jifeng Dai, Tao Xiang
Abstract: Based on analyzing the character of cascaded decoder architecture commonly adopted in existing DETR-like models, this paper proposes a new decoder architecture. The cascaded decoder architecture constrains object queries to update in the cascaded direction, only enabling object queries to learn relatively-limited information from image features. However, the challenges for object detection in natural scenes (e.g., extremely-small, heavily-occluded, and confusingly mixed with the background) require an object detection model to fully utilize image features, which motivates us to propose a new decoder architecture with the parallel Multi-time Inquiries (MI) mechanism. MI enables object queries to learn more comprehensive information, and our MI based model, MI-DETR, outperforms all existing DETR-like models on COCO benchmark under different backbones and training epochs, achieving +2.3 AP and +0.6 AP improvements compared to the most representative model DINO and SOTA model Relation-DETR under ResNet-50 backbone. In addition, a series of diagnostic and visualization experiments demonstrate the effectiveness, rationality, and interpretability of MI.
Authors: Ramkrishna Acharya
Abstract: In this paper, we propose a novel approach for air drawing that uses image processing techniques to draw on the screen by moving fingers in the air. This approach benefits a wide range of applications such as sign language, in-air drawing, and 'writing' in the air as a new way of input. The approach starts with preparing ROI (Region of Interest) background images by taking a running average in initial camera frames and later subtracting it from the live camera frames to get a binary mask image. We calculate the pointer's position as the top of the contour on the binary image. When drawing a circle on the canvas in that position, it simulates the drawing. Furthermore, we combine the pre-trained Tesseract model for OCR purposes. To address the false contours, we perform hand detection based on the haar cascade before performing the background subtraction. In an experimental setup, we achieved a latency of only 100ms in air drawing. The code used to this research are available in GitHub as https://github.com/q-viper/Contour-Based-Writing
Authors: Songlin Dong, Zhengdong Zhou, Chenhao Ding, Xinyuan Gao, Alex Kot, Yihong Gong
Abstract: Prompt tuning can further enhance the performance of visual-language models across various downstream tasks (e.g., few-shot learning), enabling them to better adapt to specific applications and needs. In this paper, we present a Diversity Covariance-Aware framework that learns distributional information from the data to enhance the few-shot ability of the prompt model. First, we propose a covariance-aware method that models the covariance relationships between visual features and uses anisotropic Mahalanobis distance, instead of the suboptimal cosine distance, to measure the similarity between two modalities. We rigorously derive and prove the validity of this modeling process. Then, we propose the diversity-aware method, which learns multiple diverse soft prompts to capture different attributes of categories and aligns them independently with visual modalities. This method achieves multi-centered covariance modeling, leading to more diverse decision boundaries. Extensive experiments on 11 datasets in various tasks demonstrate the effectiveness of our method.
Authors: Arash Nasr Esfahani, Hamed Hosseini, Mehdi Tale Masouleh, Ahmad Kalhor, Hedieh Sajedi
Abstract: As smart homes become more prevalent in daily life, the ability to understand dynamic environments is essential which is increasingly dependent on AI systems. This study focuses on developing an intelligent algorithm which can navigate a robot through a kitchen, recognizing objects, and tracking their relocation. The kitchen was chosen as the testing ground due to its dynamic nature as objects are frequently moved, rearranged and replaced. Various techniques, such as SLAM feature-based tracking and deep learning-based object detection (e.g., Faster R-CNN), are commonly used for object tracking. Additionally, methods such as optical flow analysis and 3D reconstruction have also been used to track the relocation of objects. These approaches often face challenges when it comes to problems such as lighting variations and partial occlusions, where parts of the object are hidden in some frames but visible in others. The proposed method in this study leverages the YOLOv5 architecture, initialized with pre-trained weights and subsequently fine-tuned on a custom dataset. A novel method was developed, introducing a frame-scoring algorithm which calculates a score for each object based on its location and features within all frames. This scoring approach helps to identify changes by determining the best-associated frame for each object and comparing the results in each scene, overcoming limitations seen in other methods while maintaining simplicity in design. The experimental results demonstrate an accuracy of 97.72%, a precision of 95.83% and a recall of 96.84% for this algorithm, which highlights the efficacy of the model in detecting spatial changes.
Authors: Yuheng Xu, Shijie Yang, Xin Liu, Jie Liu, Jie Tang, Gangshan Wu
Abstract: In recent years, the increasing popularity of Hi-DPI screens has driven a rising demand for high-resolution images. However, the limited computational power of edge devices poses a challenge in deploying complex super-resolution neural networks, highlighting the need for efficient methods. While prior works have made significant progress, they have not fully exploited pixel-level information. Moreover, their reliance on fixed sampling patterns limits both accuracy and the ability to capture fine details in low-resolution images. To address these challenges, we introduce two plug-and-play modules designed to capture and leverage pixel information effectively in Look-Up Table (LUT) based super-resolution networks. Our method introduces Automatic Sampling (AutoSample), a flexible LUT sampling approach where sampling weights are automatically learned during training to adapt to pixel variations and expand the receptive field without added inference cost. We also incorporate Adaptive Residual Learning (AdaRL) to enhance inter-layer connections, enabling detailed information flow and improving the network's ability to reconstruct fine details. Our method achieves significant performance improvements on both MuLUT and SPF-LUT while maintaining similar storage sizes. Specifically, for MuLUT, we achieve a PSNR improvement of approximately +0.20 dB improvement on average across five datasets. For SPF-LUT, with more than a 50% reduction in storage space and about a 2/3 reduction in inference time, our method still maintains performance comparable to the original. The code is available at https://github.com/SuperKenVery/AutoLUT.
Authors: Muhammad Aqeel, Shakiba Sharifi, Marco Cristani, Francesco Setti
Abstract: This study investigates the performance of robust anomaly detection models in industrial inspection, focusing particularly on their ability to handle noisy data. We propose to leverage the adaptation ability of meta learning approaches to identify and reject noisy training data to improve the learning process. In our model, we employ Model Agnostic Meta Learning (MAML) and an iterative refinement process through an Inter-Quartile Range rejection scheme to enhance their adaptability and robustness. This approach significantly improves the models capability to distinguish between normal and defective conditions. Our results of experiments conducted on well known MVTec and KSDD2 datasets demonstrate that the proposed method not only excels in environments with substantial noise but can also contribute in case of a clear training set, isolating those samples that are relatively out of distribution, thus offering significant improvements over traditional models.
Authors: Mojtaba Safari, Shansong Wang, Zach Eidex, Qiang Li, Erik H. Middlebrooks, David S. Yu, Xiaofeng Yang
Abstract: Objective:This study introduces a residual error-shifting mechanism that drastically reduces sampling steps while preserving critical anatomical details, thus accelerating MRI reconstruction. Approach:We propose a novel diffusion-based SR framework called Res-SRDiff, which integrates residual error shifting into the forward diffusion process. This enables efficient HR image reconstruction by aligning the degraded HR and LR distributions.We evaluated Res-SRDiff on ultra-high-field brain T1 MP2RAGE maps and T2-weighted prostate images, comparing it with Bicubic, Pix2pix, CycleGAN, and a conventional denoising diffusion probabilistic model with vision transformer backbone (TM-DDPM), using quantitative metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), gradient magnitude similarity deviation (GMSD), and learned perceptual image patch similarity (LPIPS). Main results: Res-SRDiff significantly outperformed all comparative methods in terms of PSNR, SSIM, and GMSD across both datasets, with statistically significant improvements (p-values<<0.05). The model achieved high-fidelity image restoration with only four sampling steps, drastically reducing computational time to under one second per slice, which is substantially faster than conventional TM-DDPM with around 20 seconds per slice. Qualitative analyses further demonstrated that Res-SRDiff effectively preserved fine anatomical details and lesion morphology in both brain and pelvic MRI images. Significance: Our findings show that Res-SRDiff is an efficient and accurate MRI SR method, markedly improving computational efficiency and image quality. Integrating residual error shifting into the diffusion process allows for rapid and robust HR image reconstruction, enhancing clinical MRI workflows and advancing medical imaging research. The source at:https://github.com/mosaf/Res-SRDiff
Authors: Saad Ejaz, Hriday Bavle, Laura Ribeiro, Holger Voos, Jose Luis Sanchez-Lopez
Abstract: In 3D object mapping, category-level priors enable efficient object reconstruction and canonical pose estimation, requiring only a single prior per semantic category (e.g., chair, book, laptop). Recently, DeepSDF has predominantly been used as a category-level shape prior, but it struggles to reconstruct sharp geometry and is computationally expensive. In contrast, NeRFs capture fine details but have yet to be effectively integrated with category-level priors in a real-time multi-object mapping framework. To bridge this gap, we introduce PRENOM, a Prior-based Efficient Neural Object Mapper that integrates category-level priors with object-level NeRFs to enhance reconstruction efficiency while enabling canonical object pose estimation. PRENOM gets to know objects on a first-name basis by meta-learning on synthetic reconstruction tasks generated from open-source shape datasets. To account for object category variations, it employs a multi-objective genetic algorithm to optimize the NeRF architecture for each category, balancing reconstruction quality and training time. Additionally, prior-based probabilistic ray sampling directs sampling toward expected object regions, accelerating convergence and improving reconstruction quality under constrained resources. Experimental results on a low-end GPU highlight the ability of PRENOM to achieve high-quality reconstructions while maintaining computational feasibility. Specifically, comparisons with prior-free NeRF-based approaches on a synthetic dataset show a 21% lower Chamfer distance, demonstrating better reconstruction quality. Furthermore, evaluations against other approaches using shape priors on a noisy real-world dataset indicate a 13% improvement averaged across all reconstruction metrics, a boost in rotation estimation accuracy, and comparable translation and size estimation performance, while being trained for 5x less time.
Authors: Muhammad Musab Ansari
Abstract: Detecting stenosis in coronary angiography is vital for diagnosing and managing cardiovascular diseases. This study evaluates the performance of state-of-the-art object detection models on the ARCADE dataset using the MMDetection framework. The models are assessed using COCO evaluation metrics, including Intersection over Union (IoU), Average Precision (AP), and Average Recall (AR). Results indicate variations in detection accuracy across different models, attributed to differences in algorithmic design, transformer-based vs. convolutional architectures. Additionally, several challenges were encountered during implementation, such as compatibility issues between PyTorch, CUDA, and MMDetection, as well as dataset inconsistencies in ARCADE. The findings provide insights into model selection for stenosis detection and highlight areas for further improvement in deep learning-based coronary artery disease diagnosis.
Authors: Suleyman Burcin Suyun, Mustafa Yurdakul, Sakir Tasdemir, Serkan Bilic
Abstract: Hypertensive retinopathy (HR) is a severe eye disease that may cause permanent vision loss if not diagnosed early. Traditional diagnostic methods are time-consuming and subjective, highlighting the need for an automated, reliable system. Existing studies often use a single Deep Learning (DL) model, struggling to distinguish HR stages. This study introduces a three-stage approach to enhance HR diagnosis accuracy. Initially, 14 CNN models were tested, identifying DenseNet169, MobileNet, and ResNet152 as the most effective. DenseNet169 achieved 87.73% accuracy, 87.75% precision, 87.73% recall, 87.67% F1-score, and 0.8359 Cohen's Kappa. MobileNet followed with 86.40% accuracy, 86.60% precision, 86.40% recall, 86.31% F1-score, and 0.8180 Cohen's Kappa. ResNet152 ranked third with 85.87% accuracy, 86.01% precision, 85.87% recall, 85.83% F1-score, and 0.8188 Cohen's Kappa. In the second stage, deep features from these models were fused and classified using Machine Learning (ML) algorithms (SVM, RF, XGBoost). SVM (sigmoid kernel) performed best with 92.00% accuracy, 91.93% precision, 92.00% recall, 91.91% F1-score, and 0.8930 Cohen's Kappa. The third stage applied meta-heuristic optimization (GA, ABC, PSO, HHO) for feature selection. HHO yielded 94.66% accuracy, precision, and recall, 94.64% F1-score, and 0.9286 Cohen's Kappa. The proposed approach surpassed single CNN models and previous studies in HR diagnosis accuracy and generalization.
Authors: Thiago H. Segreto, Juliano Negri, Paulo H. Polegato, Jo\~ao Manoel Herrera Pinheiro, Ricardo Godoy, Marcelo Becker
Abstract: Soybean and cotton are major drivers of many countries' agricultural sectors, offering substantial economic returns but also facing persistent challenges from volunteer plants and weeds that hamper sustainable management. Effectively controlling volunteer plants and weeds demands advanced recognition strategies that can identify these amidst complex crop canopies. While deep learning methods have demonstrated promising results for leaf-level detection and segmentation, existing datasets often fail to capture the complexity of real-world agricultural fields. To address this, we collected 640 high-resolution images from a commercial farm spanning multiple growth stages, weed pressures, and lighting variations. Each image is annotated at the leaf-instance level, with 7,221 soybean and 5,190 cotton leaves labeled via bounding boxes and segmentation masks, capturing overlapping foliage, small leaf size, and morphological similarities. We validate this dataset using YOLOv11, demonstrating state-of-the-art performance in accurately identifying and segmenting overlapping foliage. Our publicly available dataset supports advanced applications such as selective herbicide spraying and pest monitoring and can foster more robust, data-driven strategies for soybean-cotton management.
Authors: Chen Guo, Junxuan Li, Yash Kant, Yaser Sheikh, Shunsuke Saito, Chen Cao
Abstract: We present Vid2Avatar-Pro, a method to create photorealistic and animatable 3D human avatars from monocular in-the-wild videos. Building a high-quality avatar that supports animation with diverse poses from a monocular video is challenging because the observation of pose diversity and view points is inherently limited. The lack of pose variations typically leads to poor generalization to novel poses, and avatars can easily overfit to limited input view points, producing artifacts and distortions from other views. In this work, we address these limitations by leveraging a universal prior model (UPM) learned from a large corpus of multi-view clothed human performance capture data. We build our representation on top of expressive 3D Gaussians with canonical front and back maps shared across identities. Once the UPM is learned to accurately reproduce the large-scale multi-view human images, we fine-tune the model with an in-the-wild video via inverse rendering to obtain a personalized photorealistic human avatar that can be faithfully animated to novel human motions and rendered from novel views. The experiments show that our approach based on the learned universal prior sets a new state-of-the-art in monocular avatar reconstruction by substantially outperforming existing approaches relying only on heuristic regularization or a shape prior of minimally clothed bodies (e.g., SMPL) on publicly available datasets.
Authors: Kaveen Perera, Fouad Khelifi, Ammar Belatreche
Abstract: A major challenge with palm vein images is that slight movements of the fingers and thumb, or variations in hand posture, can stretch the skin in different areas and alter the vein patterns. This can result in an infinite number of variations in palm vein images for a given individual. This paper introduces a novel filtering technique for SIFT-based feature matching, known as the Mean and Median Distance (MMD) Filter. This method evaluates the differences in keypoint coordinates and computes the mean and median in each direction to eliminate incorrect matches. Experiments conducted on the 850nm subset of the CASIA dataset indicate that the proposed MMD filter effectively preserves correct points while reducing false positives detected by other filtering methods. A comparison with existing SIFT-based palm vein recognition systems demonstrates that the proposed MMD filter delivers outstanding performance, achieving lower Equal Error Rate (EER) values. This article presents an extended author's version based on our previous work, A Keypoint Filtering Method for SIFT based Palm-Vein Recognition.
Authors: Tong Ge, Yashu Liu, Jieping Ye, Tianyi Li, Chao Wang
Abstract: Modern front-end (FE) development, especially when leveraging the unique features of frameworks like React and Vue, presents distinctive challenges. These include managing modular architectures, ensuring synchronization between data and visual outputs for declarative rendering, and adapting reusable components to various scenarios. Such complexities make it particularly difficult for state-of-the-art large vision-language models (VLMs) to generate accurate and functional code directly from design images. To address these challenges, we propose a reflective agentic workflow that synthesizes high-quality image-text data to capture the diverse characteristics of FE development. This workflow automates the extraction of self-contained\footnote{A \textbf{self-contained} code snippet is one that encapsulates all necessary logic, styling, and dependencies, ensuring it functions independently without requiring external imports or context.} code snippets from real-world projects, renders the corresponding visual outputs, and generates detailed descriptions that link design elements to functional code. To further expand the scope and utility of the synthesis, we introduce three data synthesis strategies: Evolution-based synthesis, which enables scalable and diverse dataset expansion; Waterfall-Model-based synthesis, which generates logically coherent code derived from system requirements; and Additive Development synthesis, which iteratively increases the complexity of human-authored components. We build a large vision-language model, Flame, trained on the synthesized datasets and demonstrate its effectiveness in generating React code via the $\text{pass}@k$ metric. Our results suggest that a code VLM trained to interpret images before code generation may achieve better performance.
Authors: William Michael Laprade, Jesper Cairo Westergaard, Svend Christensen, Mads Nielsen, Anders Bjorholm Dahl
Abstract: Spectral imaging data acquired via multispectral and hyperspectral cameras can have hundreds of channels, where each channel records the reflectance at a specific wavelength and bandwidth. Time and resource constraints limit our ability to collect large spectral datasets, making it difficult to build and train predictive models from scratch. In the RGB domain, we can often alleviate some of the limitations of smaller datasets by using pretrained foundational models as a starting point. However, most existing foundation models are pretrained on large datasets of 3-channel RGB images, severely limiting their effectiveness when used with spectral imaging data. The few spectral foundation models that do exist usually have one of two limitations: (1) they are built and trained only on remote sensing data limiting their application in proximal spectral imaging, (2) they utilize the more widely available multispectral imaging datasets with less than 15 channels restricting their use with hundred-channel hyperspectral images. To alleviate these issues, we propose a large-scale foundational model and dataset built upon the masked autoencoder architecture that takes advantage of spectral channel encoding, spatial-spectral masking and ImageNet pretraining for an adaptable and robust model for downstream spectral imaging tasks.
Authors: Luyi Qiu, Tristan Till, Xiaobao Guo, Adams Wai-Kin Kong
Abstract: Scribble annotations significantly reduce the cost and labor required for dense labeling in large medical datasets with complex anatomical structures. However, current scribble-supervised learning methods are limited in their ability to effectively propagate sparse annotation labels to dense segmentation masks and accurately segment object boundaries. To address these issues, we propose a Progressive Collaborative Learning framework that leverages novel algorithms and the Med-SAM foundation model to enhance information quality during training. (1) We enrich ground truth scribble segmentation labels through a new algorithm, propagating scribbles to estimate object boundaries. (2) We enhance feature representation by optimizing Med-SAM-guided training through the fusion of feature embeddings from Med-SAM and our proposed Sparse Mamba network. This enriched representation also facilitates the fine-tuning of the Med-SAM decoder with enriched scribbles. (3) For inference, we introduce a Sparse Mamba network, which is highly capable of capturing local and global dependencies by replacing the traditional sequential patch processing method with a skip-sampling procedure. Experiments on the ACDC, CHAOS, and MSCMRSeg datasets validate the effectiveness of our framework, outperforming nine state-of-the-art methods. Our code is available at \href{https://github.com/QLYCode/SparseMamba-PCL}{SparseMamba-PCL.git}.
Authors: Zhendong Wang, Jianmin Bao, Shuyang Gu, Dong Chen, Wengang Zhou, Houqiang Li
Abstract: In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions. A primary challenge lies in generating accurate and style-consistent textual and visual content. Existing works in a related task of visual text generation often focus on generating text within given specific regions, which limits the creativity of generation models, resulting in style or color inconsistencies between textual and visual elements if applied to design image generation. To address this issue, we propose an end-to-end, one-stage diffusion-based framework that avoids intricate components like position and layout modeling. Specifically, the proposed framework directly synthesizes textual and visual design elements from user prompts. It utilizes a distinctive character embedding derived from the visual text to enhance the input prompt, along with a character localization loss for enhanced supervision during text generation. Furthermore, we employ a self-play Direct Preference Optimization fine-tuning strategy to improve the quality and accuracy of the synthesized visual text. Extensive experiments demonstrate that DesignDiffusion achieves state-of-the-art performance in design image generation.
Authors: Dianyi Yang, Yu Gao, Xihan Wang, Yufeng Yue, Yi Yang, Mengyin Fu
Abstract: Recent advancements in 3D Gaussian Splatting have significantly improved the efficiency and quality of dense semantic SLAM. However, previous methods are generally constrained by limited-category pre-trained classifiers and implicit semantic representation, which hinder their performance in open-set scenarios and restrict 3D object-level scene understanding. To address these issues, we propose OpenGS-SLAM, an innovative framework that utilizes 3D Gaussian representation to perform dense semantic SLAM in open-set environments. Our system integrates explicit semantic labels derived from 2D foundational models into the 3D Gaussian framework, facilitating robust 3D object-level scene understanding. We introduce Gaussian Voting Splatting to enable fast 2D label map rendering and scene updating. Additionally, we propose a Confidence-based 2D Label Consensus method to ensure consistent labeling across multiple views. Furthermore, we employ a Segmentation Counter Pruning strategy to improve the accuracy of semantic scene representation. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of our method in scene understanding, tracking, and mapping, achieving 10 times faster semantic rendering and 2 times lower storage costs compared to existing methods. Project page: https://young-bit.github.io/opengs-github.github.io/.
Authors: Shuvendu Roy, Franklin Ogidi, Ali Etemad, Elham Dolatabadi, Arash Afkanpour
Abstract: Multimodal representation learning has demonstrated remarkable potential in enabling models to process and integrate diverse data modalities, such as text and images, for improved understanding and performance. While the medical domain can benefit significantly from this paradigm, the scarcity of paired multimodal data and reliance on proprietary or pretrained encoders pose significant challenges. In this work, we present a shared encoder framework for multimodal representation learning tailored to the medical domain. Our approach employs a single set of encoder parameters shared across modalities, augmented with learnable modality features. Empirical results demonstrate that our shared encoder idea achieves superior performance compared to separate modality-specific encoders, demonstrating improved generalization in data-constrained settings. Notably, the performance gains are more pronounced with fewer training examples, underscoring the efficiency of our shared encoder framework for real-world medical applications with limited data. Our code and experiment setup are available at https://github.com/VectorInstitute/shared_encoder.
Authors: Ziyu Wang (Xidian University), Tao Xue (Xidian University), Yanbin Wang (Xidian University), Jingyuan Li (Xidian University), Haibin Zhang (Xidian University), Zhiqiang Xu (Jiangxi University of Science and Technology), Gaofei Xu (Institute of Deep-sea Science and Engineering)
Abstract: Sonar image object detection is crucial for underwater robotics and other applications. However, various types of noise in sonar images can affect the accuracy of object detection. Denoising, as a critical preprocessing step, aims to remove noise while retaining useful information to improve detection accuracy. Although deep learning-based denoising algorithms perform well on optical images, their application to underwater sonar images remains underexplored. This paper systematically evaluates the effectiveness of several deep learning-based denoising algorithms, originally designed for optical images, in the context of underwater sonar image object detection. We apply nine trained denoising models to images from five open-source sonar datasets, each processing different types of noise. We then test the denoised images using four object detection algorithms. The results show that different denoising models have varying effects on detection performance. By combining the strengths of multiple denoising models, the detection results can be optimized, thus more effectively suppressing noise. Additionally, we adopt a multi-frame denoising technique, using different outputs generated by multiple denoising models as multiple frames of the same scene for further processing to enhance detection accuracy. This method, originally designed for optical images, leverages complementary noise-reduction effects. Experimental results show that denoised sonar images improve the performance of object detection algorithms compared to the original sonar images.
Authors: Yohann Cabon, Lucas Stoffl, Leonid Antsfeld, Gabriela Csurka, Boris Chidlovskii, Jerome Revaud, Vincent Leroy
Abstract: DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior information about camera calibration nor viewpoint poses. Under the hood, however, DUSt3R processes image pairs, regressing local 3D reconstructions that need to be aligned in a global coordinate system. The number of pairs, growing quadratically, is an inherent limitation that becomes especially concerning for robust and fast optimization in the case of large image collections. In this paper, we propose an extension of DUSt3R from pairs to multiple views, that addresses all aforementioned concerns. Indeed, we propose a Multi-view Network for Stereo 3D Reconstruction, or MUSt3R, that modifies the DUSt3R architecture by making it symmetric and extending it to directly predict 3D structure for all views in a common coordinate frame. Second, we entail the model with a multi-layer memory mechanism which allows to reduce the computational complexity and to scale the reconstruction to large collections, inferring thousands of 3D pointmaps at high frame-rates with limited added complexity. The framework is designed to perform 3D reconstruction both offline and online, and hence can be seamlessly applied to SfM and visual SLAM scenarios showing state-of-the-art performance on various 3D downstream tasks, including uncalibrated Visual Odometry, relative camera pose, scale and focal estimation, 3D reconstruction and multi-view depth estimation.
Authors: Linhao Huang, Jing Yu
Abstract: Recent training-free layout-to-image diffusion models have demonstrated remarkable performance in generating high-quality images with controllable layouts. These models follow a one-stage framework: Encouraging the model to focus the attention map of each concept on its corresponding region by defining attention map-based losses. However, these models still struggle to accurately follow layouts with significant overlap, often leading to issues like attribute leakage and missing entities. In this paper, we propose ToLo, a two-stage, training-free layout-to-image generation framework for high-overlap layouts. Our framework consists of two stages: the aggregation stage and the separation stage, each with its own loss function based on the attention map. To provide a more effective evaluation, we partition the HRS dataset based on the Intersection over Union (IoU) of the input layouts, creating a new dataset for layout-to-image generation with varying levels of overlap. Through extensive experiments on this dataset, we demonstrate that ToLo significantly enhances the performance of existing methods when dealing with high-overlap layouts. Our code and dataset are available here: https://github.com/misaka12435/ToLo.
Authors: Yuyan Chen, Nico Lang, B. Christian Schmidt, Aditya Jain, Yves Basset, Sara Beery, Maxim Larriv\'ee, David Rolnick
Abstract: Machine learning is increasingly being applied to facilitate long-term, large-scale biodiversity monitoring. With most species on Earth still undiscovered or poorly documented, species-recognition models are expected to encounter new species during deployment. We introduce Open-Insects, a fine-grained image recognition benchmark dataset for open-set recognition and out-of-distribution detection in biodiversity monitoring. Open-Insects makes it possible to evaluate algorithms for new species detection on several geographical open-set splits with varying difficulty. Furthermore, we present a test set recently collected in the wild with 59 species that are likely new to science. We evaluate a variety of open-set recognition algorithms, including post-hoc methods, training-time regularization, and training with auxiliary data, finding that the simple post-hoc approach of utilizing softmax scores remains a strong baseline. We also demonstrate how to leverage auxiliary data to improve the detection performance when the training dataset is limited. Our results provide timely insights to guide the development of computer vision methods for biodiversity monitoring and species discovery.
Authors: Antoni Bigata, Micha{\l} Stypu{\l}kowski, Rodrigo Mira, Stella Bounareli, Konstantinos Vougioukas, Zoe Landgraf, Nikita Drobyshev, Maciej Zieba, Stavros Petridis, Maja Pantic
Abstract: Current audio-driven facial animation methods achieve impressive results for short videos but suffer from error accumulation and identity drift when extended to longer durations. Existing methods attempt to mitigate this through external spatial control, increasing long-term consistency but compromising the naturalness of motion. We propose KeyFace, a novel two-stage diffusion-based framework, to address these issues. In the first stage, keyframes are generated at a low frame rate, conditioned on audio input and an identity frame, to capture essential facial expressions and movements over extended periods of time. In the second stage, an interpolation model fills in the gaps between keyframes, ensuring smooth transitions and temporal coherence. To further enhance realism, we incorporate continuous emotion representations and handle a wide range of non-speech vocalizations (NSVs), such as laughter and sighs. We also introduce two new evaluation metrics for assessing lip synchronization and NSV generation. Experimental results show that KeyFace outperforms state-of-the-art methods in generating natural, coherent facial animations over extended durations, successfully encompassing NSVs and continuous emotions.
Authors: Zitang Zhou, Ke Mei, Yu Lu, Tianyi Wang, Fengyun Rao
Abstract: This paper introduces HarmonySet, a comprehensive dataset designed to advance video-music understanding. HarmonySet consists of 48,328 diverse video-music pairs, annotated with detailed information on rhythmic synchronization, emotional alignment, thematic coherence, and cultural relevance. We propose a multi-step human-machine collaborative framework for efficient annotation, combining human insights with machine-generated descriptions to identify key transitions and assess alignment across multiple dimensions. Additionally, we introduce a novel evaluation framework with tasks and metrics to assess the multi-dimensional alignment of video and music, including rhythm, emotion, theme, and cultural context. Our extensive experiments demonstrate that HarmonySet, along with the proposed evaluation framework, significantly improves the ability of multimodal models to capture and analyze the intricate relationships between video and music.
Authors: Wenhao Wang, Yi Yang
Abstract: Text-to-video generative models convert textual prompts into dynamic visual content, offering wide-ranging applications in film production, gaming, and education. However, their real-world performance often falls short of user expectations. One key reason is that these models have not been trained on videos related to some topics users want to create. In this paper, we propose VideoUFO, the first Video dataset specifically curated to align with Users' FOcus in real-world scenarios. Beyond this, our VideoUFO also features: (1) minimal ($0.29\%$) overlap with existing video datasets, and (2) videos searched exclusively via YouTube's official API under the Creative Commons license. These two attributes provide future researchers with greater freedom to broaden their training sources. The VideoUFO comprises over $1.09$ million video clips, each paired with both a brief and a detailed caption (description). Specifically, through clustering, we first identify $1,291$ user-focused topics from the million-scale real text-to-video prompt dataset, VidProM. Then, we use these topics to retrieve videos from YouTube, split the retrieved videos into clips, and generate both brief and detailed captions for each clip. After verifying the clips with specified topics, we are left with about $1.09$ million video clips. Our experiments reveal that (1) current $16$ text-to-video models do not achieve consistent performance across all user-focused topics; and (2) a simple model trained on VideoUFO outperforms others on worst-performing topics. The dataset is publicly available at https://huggingface.co/datasets/WenhaoWang/VideoUFO under the CC BY 4.0 License.
Authors: Guande Wu, Huan Song, Yawei Wang, Qiaojing Yan, Yijun Tian, Lin Lee Cheong, Panpan Xu
Abstract: Multi-modal large language models have seen rapid advancement alongside large language models. However, while language models can effectively leverage chain-of-thought prompting for zero or few-shot learning, similar prompting strategies are less effective for multi-modal LLMs due to modality gaps and task complexity. To address this challenge, we explore two prompting approaches: a dual-query method that separates multi-modal input analysis and answer generation into two prompting steps, and an ensemble prompting method that combines multiple prompt variations to arrive at the final answer. Although these approaches enhance the model's reasoning capabilities without fine-tuning, they introduce significant inference overhead. Therefore, building on top of these two prompting techniques, we propose a self-distillation framework such that the model can improve itself without any annotated data. Our self-distillation framework learns representation intervention modules from the reasoning traces collected from ensembled dual-query prompts, in the form of hidden representations. The lightweight intervention modules operate in parallel with the frozen original model, which makes it possible to maintain computational efficiency while significantly improving model capability. We evaluate our method on five widely-used VQA benchmarks, demonstrating its effectiveness in performing multi-hop reasoning for complex tasks.
Authors: Jay Zhangjie Wu, Yuxuan Zhang, Haithem Turki, Xuanchi Ren, Jun Gao, Mike Zheng Shou, Sanja Fidler, Zan Gojcic, Huan Ling
Abstract: Neural Radiance Fields and 3D Gaussian Splatting have revolutionized 3D reconstruction and novel-view synthesis task. However, achieving photorealistic rendering from extreme novel viewpoints remains challenging, as artifacts persist across representations. In this work, we introduce Difix3D+, a novel pipeline designed to enhance 3D reconstruction and novel-view synthesis through single-step diffusion models. At the core of our approach is Difix, a single-step image diffusion model trained to enhance and remove artifacts in rendered novel views caused by underconstrained regions of the 3D representation. Difix serves two critical roles in our pipeline. First, it is used during the reconstruction phase to clean up pseudo-training views that are rendered from the reconstruction and then distilled back into 3D. This greatly enhances underconstrained regions and improves the overall 3D representation quality. More importantly, Difix also acts as a neural enhancer during inference, effectively removing residual artifacts arising from imperfect 3D supervision and the limited capacity of current reconstruction models. Difix3D+ is a general solution, a single model compatible with both NeRF and 3DGS representations, and it achieves an average 2$\times$ improvement in FID score over baselines while maintaining 3D consistency.
Authors: Ziyu Liu, Zeyi Sun, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Haodong Duan, Dahua Lin, Jiaqi Wang
Abstract: Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce. Recent open-source work like DeepSeek-R1 demonstrates that reinforcement learning with verifiable reward is one key direction in reproducing o1. While the R1-style model has demonstrated success in language models, its application in multi-modal domains remains under-explored. This work introduces Visual Reinforcement Fine-Tuning (Visual-RFT), which further extends the application areas of RFT on visual tasks. Specifically, Visual-RFT first uses Large Vision-Language Models (LVLMs) to generate multiple responses containing reasoning tokens and final answers for each input, and then uses our proposed visual perception verifiable reward functions to update the model via the policy optimization algorithm such as Group Relative Policy Optimization (GRPO). We design different verifiable reward functions for different perception tasks, such as the Intersection over Union (IoU) reward for object detection. Experimental results on fine-grained image classification, few-shot object detection, reasoning grounding, as well as open-vocabulary object detection benchmarks show the competitive performance and advanced generalization ability of Visual-RFT compared with Supervised Fine-tuning (SFT). For example, Visual-RFT improves accuracy by $24.3\%$ over the baseline in one-shot fine-grained image classification with around 100 samples. In few-shot object detection, Visual-RFT also exceeds the baseline by $21.9$ on COCO's two-shot setting and $15.4$ on LVIS. Our Visual-RFT represents a paradigm shift in fine-tuning LVLMs, offering a data-efficient, reward-driven approach that enhances reasoning and adaptability for domain-specific tasks.
Authors: Junhyun Park, Chanyu Moon, Donghwan Lee, Kyungsu Kim, Minho Hwang
Abstract: Contrastive Language-Image Pre-Training (CLIP) has enabled zero-shot classification in radiology, reducing reliance on manual annotations. However, conventional contrastive learning struggles with normal case detection due to its strict intra-sample alignment, which disrupts normal sample clustering and leads to high false positives (FPs) and false negatives (FNs). To address these issues, we propose OFF-CLIP, a contrastive learning refinement that improves normal detection by introducing an off-diagonal term loss to enhance normal sample clustering and applying sentence-level text filtering to mitigate FNs by removing misaligned normal statements from abnormal reports. OFF-CLIP can be applied to radiology CLIP models without requiring any architectural modifications. Experimental results show that OFF-CLIP significantly improves normal classification, achieving a 0.61 Area under the curve (AUC) increase on VinDr-CXR over CARZero, the state-of-the-art zero-shot classification baseline, while maintaining or improving abnormal classification performance. Additionally, OFF-CLIP enhances zero-shot grounding by improving pointing game accuracy, confirming better anomaly localization. These results demonstrate OFF-CLIP's effectiveness as a robust and efficient enhancement for medical vision-language models.
Authors: Tassilo Wald, Saikat Roy, Fabian Isensee, Constantin Ulrich, Sebastian Ziegler, Dasha Trofimova, Raphael Stock, Michael Baumgartner, Gregor K\"ohler, Klaus Maier-Hein
Abstract: Transformers have achieved remarkable success across multiple fields, yet their impact on 3D medical image segmentation remains limited with convolutional networks still dominating major benchmarks. In this work, we a) analyze current Transformer-based segmentation models and identify critical shortcomings, particularly their over-reliance on convolutional blocks. Further, we demonstrate that in some architectures, performance is unaffected by the absence of the Transformer, thereby demonstrating their limited effectiveness. To address these challenges, we move away from hybrid architectures and b) introduce a fully Transformer-based segmentation architecture, termed Primus. Primus leverages high-resolution tokens, combined with advances in positional embeddings and block design, to maximally leverage its Transformer blocks. Through these adaptations Primus surpasses current Transformer-based methods and competes with state-of-the-art convolutional models on multiple public datasets. By doing so, we create the first pure Transformer architecture and take a significant step towards making Transformers state-of-the-art for 3D medical image segmentation.
Authors: Aleksei Zhuravlev, Zorah L\"ahner, Vladislav Golyanik
Abstract: Estimating correspondences between pairs of deformable shapes remains a challenging problem. Despite substantial progress, existing methods lack broad generalization capabilities and require category-specific training data. To address these limitations, we propose a fundamentally new approach to shape correspondence based on denoising diffusion models. In our method, a diffusion model learns to directly predict the functional map, a low-dimensional representation of a point-wise map between shapes. We use a large dataset of synthetic human meshes for training and employ two steps to reduce the number of functional maps that need to be learned. First, the maps refer to a template rather than shape pairs. Second, the functional map is defined in a basis of eigenvectors of the Laplacian, which is not unique due to sign ambiguity. Therefore, we introduce an unsupervised approach to select a specific basis by correcting the signs of eigenvectors based on surface features. Our approach achieves competitive performance on standard human datasets, meshes with anisotropic connectivity, non-isometric humanoid shapes, as well as animals compared to existing descriptor-based and large-scale shape deformation methods.
Authors: Rakeen Rouf, Trupti Bavalatti, Osama Ahmed, Dhaval Potdar, Faraz Jawed
Abstract: Novel research aimed at text-to-image (T2I) generative AI safety often relies on publicly available datasets for training and evaluation, making the quality and composition of these datasets crucial. This paper presents a comprehensive review of the key datasets used in the T2I research, detailing their collection methods, compositions, semantic and syntactic diversity of prompts and the quality, coverage, and distribution of harm types in the datasets. By highlighting the strengths and limitations of the datasets, this study enables researchers to find the most relevant datasets for a use case, critically assess the downstream impacts of their work given the dataset distribution, particularly regarding model safety and ethical considerations, and also identify the gaps in dataset coverage and quality that future research may address.
Authors: Junlin Song, Antoine Richard, Miguel Olivares-Mendez
Abstract: Online extrinsic calibration is crucial for building "power-on-and-go" moving platforms, like robots and AR devices. However, blindly performing online calibration for unobservable parameter may lead to unpredictable results. In the literature, extensive studies have been conducted on the extrinsic calibration between IMU and camera, from theory to practice. It is well-known that the observability of extrinsic parameter can be guaranteed under sufficient motion excitation. Furthermore, the impacts of degenerate motions are also investigated. Despite these successful analyses, we identify an issue regarding the existing observability conclusion. This paper focuses on the observability investigation for straight line motion, which is a common-seen and fundamental degenerate motion in applications. We analytically prove that pure translational straight line motion can lead to the unobservability of the rotational extrinsic parameter between IMU and camera (at least one degree of freedom). By correcting observability conclusion, our novel theoretical finding disseminate more precise principle to the research community and provide explainable calibration guideline for practitioners. Our analysis is validated by rigorous theory and experiments.
Authors: Wei Zhao, Zhe Li, Yige Li, Jun Sun
Abstract: Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. However, despite their robust textual safety mechanisms, they remain vulnerable to harmful visual inputs. Existing safeguards-typically relying on pre-filtering or fine-tuning-incur high costs and diminish overall utility. To address this critical vulnerability, we introduce SafeCLIP, a lightweight method that leverages LVLMs inherent multimodal alignment for zero-shot toxic image detection. By projecting CLIPs discarded CLS token into its text space and matching it with toxic descriptors, SafeCLIP detects harmful content without any architectural changes-adding minimal latency and enabling dynamic safety corrections during inference and fine-tuning.Experiments show that SafeCLIP achieves a 66.9% defense success rate with only 3.2% false positive rate and 7.2% overhead. In contrast, state-of-the-art methods achieve 52.9% success but have a 10.7% false positive rate and 210% overhead. Our work demonstrates that leveraging inherent multimodal alignment can yield efficient, low-cost LVLM safety. Code is available at anonymous.4open.science/r/safeclip-2C01.
Authors: Dehao Zhang, Shuai Wang, Yichen Xiao, Wenjie Wei, Yimeng Shan, Malu Zhang, Yang Yang
Abstract: Quantized Spiking Neural Networks (QSNNs) offer superior energy efficiency and are well-suited for deployment on resource-limited edge devices. However, limited bit-width weight and membrane potential result in a notable performance decline. In this study, we first identify a new underlying cause for this decline: the loss of historical information due to the quantized membrane potential. To tackle this issue, we introduce a memory-free quantization method that captures all historical information without directly storing membrane potentials, resulting in better performance with less memory requirements. To further improve the computational efficiency, we propose a parallel training and asynchronous inference framework that greatly increases training speed and energy efficiency. We combine the proposed memory-free quantization and parallel computation methods to develop a high-performance and efficient QSNN, named MFP-QSNN. Extensive experiments show that our MFP-QSNN achieves state-of-the-art performance on various static and neuromorphic image datasets, requiring less memory and faster training speeds. The efficiency and efficacy of the MFP-QSNN highlight its potential for energy-efficient neuromorphic computing.
Authors: Clayton Bromley, Alexander Moore, Amar Saini, Doug Poland, Carmen Carrano
Abstract: Video object segmentation (VOS) is a critical task in the development of video perception and understanding. The Segment-Anything Model 2 (SAM 2), released by Meta AI, is the current state-of-the-art architecture for end-to-end VOS. SAM 2 performs very well on both clean video data and augmented data, and completely intelligent video perception requires an understanding of how this architecture is capable of achieving such quality results. To better understand how each step within the SAM 2 architecture permits high-quality video segmentation, we pass a variety of complex video transformations through the architecture and measure the impact at each stage of the process. We observe that each progressive stage enables the filtering of complex transformation noise and the emphasis of the object of interest. Our contributions include the creation of complex transformation video datasets, an analysis of how each stage of the SAM 2 architecture interprets these transformations, and visualizations of segmented objects through each stage. By better understanding how each model structure impacts overall video understanding, VOS development can work to improve real-world applicability and performance tracking, localizing, and segmenting objects despite complex cluttered scenes and obscurations.
Authors: Tian Guo, Hui Yuan, Qi Liu, Honglei Su, Raouf Hamzaoui, Sam Kwong
Abstract: Point cloud compression significantly reduces data volume but sacrifices reconstruction quality, highlighting the need for advanced quality enhancement techniques. Most existing approaches focus primarily on point-to-point fidelity, often neglecting the importance of perceptual quality as interpreted by the human visual system. To address this issue, we propose a generative adversarial network for point cloud quality enhancement (PCE-GAN), grounded in optimal transport theory, with the goal of simultaneously optimizing both data fidelity and perceptual quality. The generator consists of a local feature extraction (LFE) unit, a global spatial correlation (GSC) unit and a feature squeeze unit. The LFE unit uses dynamic graph construction and a graph attention mechanism to efficiently extract local features, placing greater emphasis on points with severe distortion. The GSC unit uses the geometry information of neighboring patches to construct an extended local neighborhood and introduces a transformer-style structure to capture long-range global correlations. The discriminator computes the deviation between the probability distributions of the enhanced point cloud and the original point cloud, guiding the generator to achieve high quality reconstruction. Experimental results show that the proposed method achieves state-of-the-art performance. Specifically, when applying PCE-GAN to the latest geometry-based point cloud compression (G-PCC) test model, it achieves an average BD-rate of -19.2% compared with the PredLift coding configuration and -18.3% compared with the RAHT coding configuration. Subjective comparisons show a significant improvement in texture clarity and color transitions, revealing finer details and more natural color gradients.
Authors: Aakash Patel, Tianqing Zhang, Camille Avestruz, Jeffrey Regier, the LSST Dark Energy Science Collaboration
Abstract: Neural posterior estimation (NPE), a type of amortized variational inference, is a computationally efficient means of constructing probabilistic catalogs of light sources from astronomical images. To date, NPE has not been used to perform inference in models with spatially varying covariates. However, ground-based astronomical images have spatially varying sky backgrounds and point spread functions (PSFs), and accounting for this variation is essential for constructing accurate catalogs of imaged light sources. In this work, we introduce a method of performing NPE with spatially varying backgrounds and PSFs. In this method, we generate synthetic catalogs and semi-synthetic images for these catalogs using randomly sampled PSF and background estimates from existing surveys. Using this data, we train a neural network, which takes an astronomical image and representations of its background and PSF as input, to output a probabilistic catalog. Our experiments with Sloan Digital Sky Survey data demonstrate the effectiveness of NPE in the presence of spatially varying backgrounds and PSFs for light source detection, star/galaxy separation, and flux measurement.
Authors: Shashwat Gupta, Sarthak Gupta, Akshan Agrawal, Mahim Naaz, Rajanikanth Yadav, Priyanka Bagade
Abstract: Crohn's disease and intestinal tuberculosis share many overlapping features such as clinical, radiological, endoscopic, and histological features - particularly granulomas, making it challenging to clinically differentiate them. Our research leverages 3D CTE scans, computer vision, and machine learning to improve this differentiation to avoid harmful treatment mismanagement such as unnecessary anti-tuberculosis therapy for Crohn's disease or exacerbation of tuberculosis with immunosuppressants. Our study proposes a novel method to identify radiologist - identified biomarkers such as VF to SF ratio, necrosis, calcifications, comb sign and pulmonary TB to enhance accuracy. We demonstrate the effectiveness by using different ML techniques on the features extracted from these biomarkers, computing SHAP on XGBoost for understanding feature importance towards predictions, and comparing against SOTA methods such as pretrained ResNet and CTFoundation.
Authors: Shuang Li, Yihuai Gao, Dorsa Sadigh, Shuran Song
Abstract: A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video generation and action prediction remains challenging, and current video generation-based methods struggle to match the performance of direct policy learning in action accuracy and inference speed. To bridge this gap, we introduce the Unified Video Action model (UVA), which jointly optimizes video and action predictions to achieve both high accuracy and efficient action inference. The key lies in learning a joint video-action latent representation and decoupling video-action decoding. The joint latent representation bridges the visual and action domains, effectively modeling the relationship between video and action sequences. Meanwhile, the decoupled decoding, powered by two lightweight diffusion heads, enables high-speed action inference by bypassing video generation during inference. Such a unified framework further enables versatile functionality through masked input training. By selectively masking actions or videos, a single model can tackle diverse tasks beyond policy learning, such as forward and inverse dynamics modeling and video generation. Via an extensive set of experiments, we demonstrate that UVA can serve as a general-purpose solution for a wide range of robotics tasks, such as policy learning, forward/inverse dynamics and video observation prediction, without compromising performance compared to methods tailored for specific applications. Results are best viewed on https://unified-video-action-model.github.io/.
Authors: Wenrui Fan, L. M. Riza Rizky, Jiayang Zhang, Chen Chen, Haiping Lu, Kevin Teh, Dinesh Selvarajah, Shuo Zhou
Abstract: Neuropathic pain, affecting up to 10% of adults, remains difficult to treat due to limited therapeutic efficacy and tolerability. Although resting-state functional MRI (rs-fMRI) is a promising non-invasive measurement of brain biomarkers to predict drug response in therapeutic development, the complexity of fMRI demands machine learning models with substantial capacity. However, extreme data scarcity in neuropathic pain research limits the application of high-capacity models. To address the challenge of data scarcity, we propose FMM$_{TC}$, a Foundation-Model-boosted Multimodal learning framework for fMRI-based neuropathic pain drug response prediction, which leverages both internal multimodal information in pain-specific data and external knowledge from large pain-agnostic data. Specifically, to maximize the value of limited pain-specific data, FMM$_{TC}$ integrates complementary information from two rs-fMRI modalities: Time series and functional Connectivity. FMM$_{TC}$ is further boosted by an fMRI foundation model with its external knowledge from extensive pain-agnostic fMRI datasets enriching limited pain-specific information. Evaluations with an in-house dataset and a public dataset from OpenNeuro demonstrate FMM$_{TC}$'s superior representation ability, generalizability, and cross-dataset adaptability over existing unimodal fMRI models that only consider one of the rs-fMRI modalities. The ablation study validates the effectiveness of multimodal learning and foundation-model-powered external knowledge transfer in FMM$_{TC}$. An integrated gradient-based interpretation study explains how FMM$_{TC}$'s cross-dataset dynamic behaviors enhance its adaptability. In conclusion, FMM$_{TC}$ boosts clinical trials in neuropathic pain therapeutic development by accurately predicting drug responses to improve the participant stratification efficiency.
Authors: Ali Keshavarzi, Elsa Angelini
Abstract: Automated airway segmentation from lung CT scans is vital for diagnosing and monitoring pulmonary diseases. Despite advancements, challenges like leakage, breakage, and class imbalance persist, particularly in capturing small airways and preserving topology. We propose the Boundary-Emphasized Loss (BEL), which enhances boundary preservation using a boundary-based weight map and an adaptive weight refinement strategy. Unlike centerline-based approaches, BEL prioritizes boundary voxels to reduce misclassification, improve topology, and enhance structural consistency, especially on distal airway branches. Evaluated on ATM22 and AIIB23, BEL outperforms baseline loss functions, achieving higher topology-related metrics and comparable overall-based measures. Qualitative results further highlight BEL's ability to capture fine anatomical details and reduce segmentation errors, particularly in small airways. These findings establish BEL as a promising solution for accurate and topology-enhancing airway segmentation in medical imaging.
Authors: Xinwei Luo, Songlin Zhao, Yun Zong, Yong Chen, Gui-shuang Ying, Lifang He
Abstract: Retinal image plays a crucial role in diagnosing various diseases, as retinal structures provide essential diagnostic information. However, effectively capturing structural features while integrating them with contextual information from retinal images remains a challenge. In this work, we propose segmentation-guided dual-branch network for retinal disease diagnosis using retinal images and their segmentation maps, named SegImgNet. SegImgNet incorporates a segmentation module to generate multi-scale retinal structural feature maps from retinal images. The classification module employs two encoders to independently extract features from segmented images and retinal images for disease classification. To further enhance feature extraction, we introduce the Segmentation-Guided Attention (SGA) block, which leverages feature maps from the segmentation module to refine the classification process. We evaluate SegImgNet on the public AIROGS dataset and the private e-ROP dataset. Experimental results demonstrate that SegImgNet consistently outperforms existing methods, underscoring its effectiveness in retinal disease diagnosis. The code is publicly available at https://github.com/hawk-sudo/SegImgNet.
Authors: Maziar Sabouri, Ghasem Hajianfar, Alireza Rafiei Sardouei, Milad Yazdani, Azin Asadzadeh, Soroush Bagheri, Mohsen Arabi, Seyed Rasoul Zakavi, Emran Askari, Atena Aghaee, Dena Shahriari, Habib Zaidi, Arman Rahmim
Abstract: Thyroid scintigraphy is a key imaging modality for diagnosing thyroid disorders. Deep learning models for thyroid scintigraphy classification often face challenges due to limited and imbalanced datasets, leading to suboptimal generalization. In this study, we investigate the effectiveness of different data augmentation techniques including Stable Diffusion (SD), Flow Matching (FM), and Conventional Augmentation (CA) to enhance the performance of a ResNet18 classifier for thyroid condition classification. Our results showed that FM-based augmentation consistently outperforms SD-based approaches, particularly when combined with original (O) data and CA (O+FM+CA), achieving both high accuracy and fair classification across Diffuse Goiter (DG), Nodular Goiter (NG), Normal (NL), and Thyroiditis (TI) cases. The Wilcoxon statistical analysis further validated the superiority of O+FM and its variants (O+FM+CA) over SD-based augmentations in most scenarios. These findings highlight the potential of FM-based augmentation as a superior approach for generating high-quality synthetic thyroid scintigraphy images and improving model generalization in medical image classification.
Authors: Haolin Wang, Zeren Lv, Hao Wei, Haijiang Zhu, Yihong Wu
Abstract: Floorplan reconstruction provides structural priors essential for reliable indoor robot navigation and high-level scene understanding. However, existing approaches either require time-consuming offline processing with a complete map, or rely on expensive sensors and substantial computational resources. To address the problems, we propose Floorplan-SLAM, which incorporates floorplan reconstruction tightly into a multi-session SLAM system by seamlessly interacting with plane extraction, pose estimation, and back-end optimization, achieving real-time, high-accuracy, and long-term floorplan reconstruction using only a stereo camera. Specifically, we present a robust plane extraction algorithm that operates in a compact plane parameter space and leverages spatially complementary features to accurately detect planar structures, even in weakly textured scenes. Furthermore, we propose a floorplan reconstruction module tightly coupled with the SLAM system, which uses continuously optimized plane landmarks and poses to formulate and solve a novel optimization problem, thereby enabling real-time incremental floorplan reconstruction. Note that by leveraging the map merging capability of multi-session SLAM, our method supports long-term floorplan reconstruction across multiple sessions without redundant data collection. Experiments on the VECtor and the self-collected datasets indicate that Floorplan-SLAM significantly outperforms state-of-the-art methods in terms of plane extraction robustness, pose estimation accuracy, and floorplan reconstruction fidelity and speed, achieving real-time performance at 25-45 FPS without GPU acceleration, which reduces the floorplan reconstruction time for a 1000 square meters scene from over 10 hours to just 9.44 minutes.
Authors: Zongru Wu, Pengzhou Cheng, Zheng Wu, Tianjie Ju, Zhuosheng Zhang, Gongshen Liu
Abstract: Perception-enhanced pre-training, particularly through grounding techniques, is widely adopted to enhance the performance of graphical user interface (GUI) agents. However, in resource-constrained scenarios, the format discrepancy between coordinate-oriented grounding and action-oriented reasoning limits the effectiveness of grounding for reasoning tasks. To address this challenge, we propose a query-oriented pivot approach called query inference, which serves as a bridge between GUI grounding and reasoning. By inferring potential user queries from a screenshot and its associated element coordinates, query inference improves the understanding of coordinates while aligning more closely with reasoning tasks. Experimental results show that query inference outperforms previous grounding techniques under the same training data scale. Notably, query inference achieves comparable or even better performance to large-scale grounding-enhanced OS-Atlas with less than 0.1% of training data. Furthermore, we explore the impact of reasoning formats and demonstrate that integrating additional semantic information into the input further boosts reasoning performance. The code is publicly available at https://github.com/ZrW00/GUIPivot.
Authors: Earnest Paul Ijjina, Aniruddha Srinivas Joshi, Goutham Kanahasabai, Keerthi Priyanka P
Abstract: The analysis of sales information, is a vital step in designing an effective marketing strategy. This work proposes a novel approach to analyse the shopping behaviour of customers to identify their purchase patterns. An extended version of the Multi-Cluster Overlapping k-Means Extension (MCOKE) algorithm with weighted k-Means algorithm is utilized to map customers to the garments of interest. The age & gender traits of the customer; the time spent and the expressions exhibited while selecting garments for purchase, are utilized to associate a customer or a group of customers to a garments they are interested in. Such study on the customer base of a retail business, may help in inferring the products of interest of their consumers, and enable them in developing effective business strategies, thus ensuring customer satisfaction, loyalty, increased sales and profits.
Authors: Giuseppe Stracquadanio, Federico Vasile, Elisa Maiettini, Nicol\`o Boccardo, Lorenzo Natale
Abstract: One of the most important research challenges in upper-limb prosthetics is enhancing the user-prosthesis communication to closely resemble the experience of a natural limb. As prosthetic devices become more complex, users often struggle to control the additional degrees of freedom. In this context, leveraging shared-autonomy principles can significantly improve the usability of these systems. In this paper, we present a novel eye-in-hand prosthetic grasping system that follows these principles. Our system initiates the approach-to-grasp action based on user's command and automatically configures the DoFs of a prosthetic hand. First, it reconstructs the 3D geometry of the target object without the need of a depth camera. Then, it tracks the hand motion during the approach-to-grasp action and finally selects a candidate grasp configuration according to user's intentions. We deploy our system on the Hannes prosthetic hand and test it on able-bodied subjects and amputees to validate its effectiveness. We compare it with a multi-DoF prosthetic control baseline and find that our method enables faster grasps, while simplifying the user experience. Code and demo videos are available online at https://hsp-iit.github.io/byogg/.
Authors: Junqi He, Yujie Zhang, Jialu Wang, Tao Wang, Pan Zhang, Chengjie Cai, Jinxing Yang, Xiao Lin, Xiaohui Yang
Abstract: Two-dimensional (2D) materials and heterostructures exhibit unique physical properties, necessitating efficient and accurate characterization methods. Leveraging advancements in artificial intelligence, we introduce a deep learning-based method for efficiently characterizing heterostructures and 2D materials, specifically MoS2-MoSe2 lateral heterostructures and MoS2 flakes with varying shapes and thicknesses. By utilizing YOLO models, we achieve an accuracy rate of over 94.67% in identifying these materials. Additionally, we explore the application of transfer learning across different materials, which further enhances model performance. This model exhibits robust generalization and anti-interference ability, ensuring reliable results in diverse scenarios. To facilitate practical use, we have developed an application that enables real-time analysis directly from optical microscope images, making the process significantly faster and more cost-effective than traditional methods. This deep learning-driven approach represents a promising tool for the rapid and accurate characterization of 2D materials, opening new avenues for research and development in material science.
Authors: Paolo Giannitrapani, Elio D. Di Claudio, Giovanni Jacovitti
Abstract: In the Full-Reference Image Quality Assessment context, Mean Opinion Score values represent subjective evaluations based on retinal perception, while objective metrics assess the reproduced image on the display. Bridging these subjective and objective domains requires parametric mapping functions, which are sensitive to the observer's viewing distance. This paper introduces a novel parametric model that separates perceptual effects due to strong edge degradations from those caused by texture distortions. These effects are quantified using two distinct quality indices. The first is the Blur Equivalent Linearized Estimator, designed to measure blur on strong and isolated edges while accounting for variations in viewing distance. The second is a Complex Peak Signal-to-Noise Ratio, which evaluates distortions affecting texture regions. The first-order effects of the estimator are directly tied to the first index, for which we introduce the concept of \emph{focalization}, interpreted as a linearization term. Starting from a Positional Fisher Information loss model applied to Gaussian blur distortion in natural images, we demonstrate how this model can generalize to linearize all types of distortions. Finally, we validate our theoretical findings by comparing them with several state-of-the-art classical and deep-learning-based full-reference image quality assessment methods on widely used benchmark datasets.
Authors: Yexiao He, Ziyao Wang, Yuning Zhang, Tingting Dan, Tianlong Chen, Guorong Wu, Ang Li
Abstract: Alzheimer's disease (AD) diagnosis is complex, requiring the integration of imaging and clinical data for accurate assessment. While deep learning has shown promise in brain MRI analysis, it often functions as a black box, limiting interpretability and lacking mechanisms to effectively integrate critical clinical data such as biomarkers, medical history, and demographic information. To bridge this gap, we propose NeuroSymAD, a neuro-symbolic framework that synergizes neural networks with symbolic reasoning. A neural network percepts brain MRI scans, while a large language model (LLM) distills medical rules to guide a symbolic system in reasoning over biomarkers and medical history. This structured integration enhances both diagnostic accuracy and explainability. Experiments on the ADNI dataset demonstrate that NeuroSymAD outperforms state-of-the-art methods by up to 2.91% in accuracy and 3.43% in F1-score while providing transparent and interpretable diagnosis.
Authors: Zirun Guo, Shulei Wang, Wang Lin, Weicai Yan, Yangyang Wu, Tao Jin
Abstract: Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstream datasets with missing modalities, performance can degrade significantly. Current methods often aggregate various missing cases to train recovery modules or align multimodal features, resulting in suboptimal performance, high computational costs, and the risk of catastrophic forgetting in continual environments where data arrives sequentially. In this paper, we formulate the dynamic missing modality problem as a continual learning task and introduce the continual multimodal missing modality task. To address this challenge efficiently, we introduce three types of prompts: modality-specific, task-aware, and task-specific prompts. These prompts enable the model to learn intra-modality, inter-modality, intra-task, and inter-task features. Furthermore, we propose a contrastive task interaction strategy to explicitly learn prompts correlating different modalities. We conduct extensive experiments on three public datasets, where our method consistently outperforms state-of-the-art approaches.
Authors: Shijia Zhang, Xiyu Ding, Brian Caffo, Junyu Chen, Cindy Zhang, Hadi Kharrazi, Zheyu Wang
Abstract: Early diagnosis of Alzheimer's disease (AD) is critical for intervention before irreversible neurodegeneration occurs. Structural MRI (sMRI) is widely used for AD diagnosis, but conventional deep learning approaches primarily rely on intensity-based features, which require large datasets to capture subtle structural changes. Jacobian determinant maps (JSM) provide complementary information by encoding localized brain deformations, yet existing multimodal fusion strategies fail to fully integrate these features with sMRI. We propose a cross-attention fusion framework to model the intrinsic relationship between sMRI intensity and JSM-derived deformations for AD classification. Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, we compare cross-attention, pairwise self-attention, and bottleneck attention with four pre-trained 3D image encoders. Cross-attention fusion achieves superior performance, with mean ROC-AUC scores of 0.903 (+/-0.033) for AD vs. cognitively normal (CN) and 0.692 (+/-0.061) for mild cognitive impairment (MCI) vs. CN. Despite its strong performance, our model remains highly efficient, with only 1.56 million parameters--over 40 times fewer than ResNet-34 (63M) and Swin UNETR (61.98M). These findings demonstrate the potential of cross-attention fusion for improving AD diagnosis while maintaining computational efficiency.
Authors: Yuezhi Yang, Qimin Chen, Vladimir G. Kim, Siddhartha Chaudhuri, Qixing Huang, Zhiqin Chen
Abstract: We introduce the first method for generating Vector Displacement Maps (VDMs): parameterized, detailed geometric stamps commonly used in 3D modeling. Given a single input image, our method first generates multi-view normal maps and then reconstructs a VDM from the normals via a novel reconstruction pipeline. We also propose an efficient algorithm for extracting VDMs from 3D objects, and present the first academic VDM dataset. Compared to existing 3D generative models focusing on complete shapes, we focus on generating parts that can be seamlessly attached to shape surfaces. The method gives artists rich control over adding geometric details to a 3D shape. Experiments demonstrate that our approach outperforms existing baselines. Generating VDMs offers additional benefits, such as using 2D image editing to customize and refine 3D details.
Authors: Wei Zhou, Hadi Amirpour, Christian Timmerer, Guangtao Zhai, Patrick Le Callet, Alan C. Bovik
Abstract: As multimedia services such as video streaming, video conferencing, virtual reality (VR), and online gaming continue to expand, ensuring high perceptual visual quality becomes a priority to maintain user satisfaction and competitiveness. However, multimedia content undergoes various distortions during acquisition, compression, transmission, and storage, resulting in the degradation of experienced quality. Thus, perceptual visual quality assessment (PVQA), which focuses on evaluating the quality of multimedia content based on human perception, is essential for optimizing user experiences in advanced communication systems. Several challenges are involved in the PVQA process, including diverse characteristics of multimedia content such as image, video, VR, point cloud, mesh, multimodality, etc., and complex distortion scenarios as well as viewing conditions. In this paper, we first present an overview of PVQA principles and methods. This includes both subjective methods, where users directly rate their experiences, and objective methods, where algorithms predict human perception based on measurable factors such as bitrate, frame rate, and compression levels. Based on the basics of PVQA, quality predictors for different multimedia data are then introduced. In addition to traditional images and videos, immersive multimedia and generative artificial intelligence (GenAI) content are also discussed. Finally, the paper concludes with a discussion on the future directions of PVQA research.
Authors: Ashish Verma, Aupendu Kar, Krishnendu Ghosh, Sobhan Kanti Dhara, Debashis Sen, Prabir Kumar Biswas
Abstract: Expert radiologists visually scan Chest X-Ray (CXR) images, sequentially fixating on anatomical structures to perform disease diagnosis. An automatic multi-label classifier of diseases in CXR images can benefit by incorporating aspects of the radiologists' approach. Recorded visual scanpaths of radiologists on CXR images can be used for the said purpose. But, such scanpaths are not available for most CXR images, which creates a gap even for modern deep learning based classifiers. This paper proposes to mitigate this gap by generating effective artificial visual scanpaths using a visual scanpath prediction model for CXR images. Further, a multi-class multi-label classifier framework is proposed that uses a generated scanpath and visual image features to classify diseases in CXR images. While the scanpath predictor is based on a recurrent neural network, the multi-label classifier involves a novel iterative sequential model with an attention module. We show that our scanpath predictor generates human-like visual scanpaths. We also demonstrate that the use of artificial visual scanpaths improves multi-class multi-label disease classification results on CXR images. The above observations are made from experiments involving around 0.2 million CXR images from 2 widely-used datasets considering the multi-label classification of 14 pathological findings. Code link: https://github.com/ashishverma03/SDC
Authors: Zhiqi Bu, Ruixuan Liu
Abstract: Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models. Critically, the performance of models is determined by the training hyperparameters, especially those of the learning rate schedule, thus requiring fine-grained hyperparameter tuning on the data. In practice, it is common to tune the learning rate hyperparameters through the grid search that (1) is computationally expensive as multiple runs are needed, and (2) increases the risk of data leakage as the selection of hyperparameters is data-dependent. In this work, we adapt the automatic learning rate schedule to DP optimization for any models and optimizers, so as to significantly mitigate or even eliminate the cost of hyperparameter tuning when applied together with automatic per-sample gradient clipping. Our hyperparameter-free DP optimization is almost as computationally efficient as the standard non-DP optimization, and achieves state-of-the-art DP performance on various language and vision tasks.
Authors: Changlin Song, Jiaqi Wang, Liyun Zhu, He Weng
Abstract: 3D scene reconstruction is essential for applications in virtual reality, robotics, and autonomous driving, enabling machines to understand and interact with complex environments. Traditional 3D Gaussian Splatting techniques rely on images captured from multiple viewpoints to achieve optimal performance, but this dependence limits their use in scenarios where only a single image is available. In this work, we introduce FlashDreamer, a novel approach for reconstructing a complete 3D scene from a single image, significantly reducing the need for multi-view inputs. Our approach leverages a pre-trained vision-language model to generate descriptive prompts for the scene, guiding a diffusion model to produce images from various perspectives, which are then fused to form a cohesive 3D reconstruction. Extensive experiments show that our method effectively and robustly expands single-image inputs into a comprehensive 3D scene, extending monocular 3D reconstruction capabilities without further training. Our code is available https://github.com/CharlieSong1999/FlashDreamer/tree/main.
URLs: https://github.com/CharlieSong1999/FlashDreamer/tree/main.
Authors: Henrui Tian, Wenhui Lei, Linrui Dai, Hanyu Chen, Xiaofan Zhang
Abstract: Fully-supervised lesion recognition methods in medical imaging face challenges due to the reliance on large annotated datasets, which are expensive and difficult to collect. To address this, synthetic lesion generation has become a promising approach. However, existing models struggle with scalability, fine-grained control over lesion attributes, and the generation of complex structures. We propose LesionDiffusion, a text-controllable lesion synthesis framework for 3D CT imaging that generates both lesions and corresponding masks. By utilizing a structured lesion report template, our model provides greater control over lesion attributes and supports a wider variety of lesion types. We introduce a dataset of 1,505 annotated CT scans with paired lesion masks and structured reports, covering 14 lesion types across 8 organs. LesionDiffusion consists of two components: a lesion mask synthesis network (LMNet) and a lesion inpainting network (LINet), both guided by lesion attributes and image features. Extensive experiments demonstrate that LesionDiffusion significantly improves segmentation performance, with strong generalization to unseen lesion types and organs, outperforming current state-of-the-art models. Code will be available at https://github.com/HengruiTianSJTU/LesionDiffusion.
Authors: Teng Zhang, Hongxu Jiang, Kuang Gong, Wei Shao
Abstract: Diffusion models transform an unknown data distribution into a Gaussian prior by progressively adding noise until the data become indistinguishable from pure noise. This stochastic process traces a path in probability space, evolving from the original data distribution (considered as a Gaussian with near-zero variance) to an isotropic Gaussian. The denoiser then learns to reverse this process, generating high-quality samples from random Gaussian noise. However, standard diffusion models, such as the Denoising Diffusion Probabilistic Model (DDPM), do not ensure a geodesic (i.e., shortest) path in probability space. This inefficiency necessitates the use of many intermediate time steps, leading to high computational costs in training and sampling. To address this limitation, we propose the Geodesic Diffusion Model (GDM), which defines a geodesic path under the Fisher-Rao metric with a variance-exploding noise scheduler. This formulation transforms the data distribution into a Gaussian prior with minimal energy, significantly improving the efficiency of diffusion models. We trained GDM by continuously sampling time steps from 0 to 1 and using as few as 15 evenly spaced time steps for model sampling. We evaluated GDM on two medical image-to-image generation tasks: CT image denoising and MRI image super-resolution. Experimental results show that GDM achieved state-of-the-art performance while reducing training time by a 50-fold compared to DDPM and 10-fold compared to Fast-DDPM, with 66 times faster sampling than DDPM and a similar sampling speed to Fast-DDPM. These efficiency gains enable rapid model exploration and real-time clinical applications. Our code is publicly available at: https://github.com/mirthAI/GDM-VE.
Authors: Lei Zhou, Nimu Yuan, Katjana Ehrlich, Jinyi Qi
Abstract: Deformable image registration is a fundamental task in medical image processing. Traditional optimization-based methods often struggle with accuracy in dealing with complex deformation. Recently, learning-based methods have achieved good performance on public datasets, but the scarcity of medical image data makes it challenging to build a generalizable model to handle diverse real-world scenarios. To address this, we propose a training-data-free learning-based method, Neural Correspondence Field (NCF), which can learn from just one data pair. Our approach employs a compact neural network to model the correspondence field and optimize model parameters for each individual image pair. Consequently, each pair has a unique set of network weights. Notably, our model is highly efficient, utilizing only 0.06 million parameters. Evaluation results showed that the proposed method achieved superior performance on a public Lung CT dataset and outperformed a traditional method on a head and neck dataset, demonstrating both its effectiveness and efficiency.
Authors: Gokul Puthumanaillam, Paulo Padrao, Jose Fuentes, Pranay Thangeda, William E. Schafer, Jae Hyuk Song, Karan Jagdale, Leonardo Bobadilla, Melkior Ornik
Abstract: Predicting the near-term behavior of a reactive agent is crucial in many robotic scenarios, yet remains challenging when observations of that agent are sparse or intermittent. Vision-Language Models (VLMs) offer a promising avenue by integrating textual domain knowledge with visual cues, but their one-shot predictions often miss important edge cases and unusual maneuvers. Our key insight is that iterative, counterfactual exploration--where a dedicated module probes each proposed behavior hypothesis, explicitly represented as a plausible trajectory, for overlooked possibilities--can significantly enhance VLM-based behavioral forecasting. We present TRACE (Tree-of-thought Reasoning And Counterfactual Exploration), an inference framework that couples tree-of-thought generation with domain-aware feedback to refine behavior hypotheses over multiple rounds. Concretely, a VLM first proposes candidate trajectories for the agent; a counterfactual critic then suggests edge-case variations consistent with partial observations, prompting the VLM to expand or adjust its hypotheses in the next iteration. This creates a self-improving cycle where the VLM progressively internalizes edge cases from previous rounds, systematically uncovering not only typical behaviors but also rare or borderline maneuvers, ultimately yielding more robust trajectory predictions from minimal sensor data. We validate TRACE on both ground-vehicle simulations and real-world marine autonomous surface vehicles. Experimental results show that our method consistently outperforms standard VLM-driven and purely model-based baselines, capturing a broader range of feasible agent behaviors despite sparse sensing. Evaluation videos and code are available at trace-robotics.github.io.
Authors: Elahe Delavari, Aws Khalil, Jaerock Kwon
Abstract: End-to-end vision-based imitation learning has demonstrated promising results in autonomous driving by learning control commands directly from expert demonstrations. However, traditional approaches rely on either regressionbased models, which provide precise control but lack confidence estimation, or classification-based models, which offer confidence scores but suffer from reduced precision due to discretization. This limitation makes it challenging to quantify the reliability of predicted actions and apply corrections when necessary. In this work, we introduce a dual-head neural network architecture that integrates both regression and classification heads to improve decision reliability in imitation learning. The regression head predicts continuous driving actions, while the classification head estimates confidence, enabling a correction mechanism that adjusts actions in low-confidence scenarios, enhancing driving stability. We evaluate our approach in a closed-loop setting within the CARLA simulator, demonstrating its ability to detect uncertain actions, estimate confidence, and apply real-time corrections. Experimental results show that our method reduces lane deviation and improves trajectory accuracy by up to 50%, outperforming conventional regression-only models. These findings highlight the potential of classification-guided confidence estimation in enhancing the robustness of vision-based imitation learning for autonomous driving. The source code is available at https://github.com/ElaheDlv/Confidence_Aware_IL.
Authors: Yuezhi Yang, Haitao Yang, Kiyohiro Nakayama, Xiangru Huang, Leonidas Guibas, Qixing Huang
Abstract: We present GenAnalysis, an implicit shape generation framework that allows joint analysis of man-made shapes, including shape matching and joint shape segmentation. The key idea is to enforce an as-affine-as-possible (AAAP) deformation between synthetic shapes of the implicit generator that are close to each other in the latent space, which we achieve by designing a regularization loss. It allows us to understand the shape variation of each shape in the context of neighboring shapes and also offers structure-preserving interpolations between the input shapes. We show how to extract these shape variations by recovering piecewise affine vector fields in the tangent space of each shape. These vector fields provide single-shape segmentation cues. We then derive shape correspondences by iteratively propagating AAAP deformations across a sequence of intermediate shapes. These correspondences are then used to aggregate single-shape segmentation cues into consistent segmentations. We conduct experiments on the ShapeNet dataset to show superior performance in shape matching and joint shape segmentation over previous methods.
Authors: Gal Yefet, Ayellet Tal
Abstract: This study addresses the challenge of self-supervised learning for 3D mesh analysis. It presents an new approach that uses random walks as a form of data augmentation to generate diverse representations of mesh surfaces. Furthermore, it employs a combination of contrastive and clustering losses. The contrastive learning framework maximizes similarity between augmented instances of the same mesh while minimizing similarity between different meshes. We integrate this with a clustering loss, enhancing class distinction across training epochs and mitigating training variance. Our model's effectiveness is evaluated using mean Average Precision (mAP) scores and a supervised SVM linear classifier on extracted features, demonstrating its potential for various downstream tasks such as object classification and shape retrieval.
Authors: Jeffrey Gu, Serena Yeung-Levy
Abstract: Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some or all of the parameters of another neural network, have become an increasingly important technique for conditioning and generalizing implicit neural representations (INRs), which represent signals or objects such as audio or 3D shapes using a neural network. However, despite the potential benefits of incorporating foundation models in hypernetwork methods, this research direction has not been investigated, likely due to the dissimilarity of the weight generation task with other visual tasks. To address this gap, we (1) show how foundation models can improve hypernetworks with Transformer-based architectures, (2) provide an empirical analysis of the benefits of foundation models for hypernetworks through the lens of the generalizable INR task, showing that leveraging foundation models improves performance, generalizability, and data efficiency across a variety of algorithms and modalities. We also provide further analysis in examining the design space of foundation model-based hypernetworks, including examining the choice of foundation models, algorithms, and the effect of scaling foundation models.
Authors: Shashank Gupta, Chaitanya Ahuja, Tsung-Yu Lin, Sreya Dutta Roy, Harrie Oosterhuis, Maarten de Rijke, Satya Narayan Shukla
Abstract: Reinforcement learning ( RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is the most popular choice of method for policy optimization. While effective in terms of performance, PPO is highly sensitive to hyper-parameters and involves substantial computational overhead. REINFORCE, on the other hand, mitigates some computational complexities such as high memory overhead and sensitive hyper-parameter tuning, but has suboptimal performance due to high-variance and sample inefficiency. While the variance of the REINFORCE can be reduced by sampling multiple actions per input prompt and using a baseline correction term, it still suffers from sample inefficiency. To address these challenges, we systematically analyze the efficiency-effectiveness trade-off between REINFORCE and PPO, and propose leave-one-out PPO ( LOOP), a novel RL for diffusion fine-tuning method. LOOP combines variance reduction techniques from REINFORCE, such as sampling multiple actions per input prompt and a baseline correction term, with the robustness and sample efficiency of PPO via clipping and importance sampling. Our results demonstrate that LOOP effectively improves diffusion models on various black-box objectives, and achieves a better balance between computational efficiency and performance.
Authors: Ziyuan Yang, Yingyu Chen, Zhiwen Wang, Hongming Shan, Yang Chen, Yi Zhang
Abstract: Reducing radiation doses benefits patients, however, the resultant low-dose computed tomography (LDCT) images often suffer from clinically unacceptable noise and artifacts. While deep learning (DL) shows promise in LDCT reconstruction, it requires large-scale data collection from multiple clients, raising privacy concerns. Federated learning (FL) has been introduced to address these privacy concerns; however, current methods are typically tailored to specific scanning protocols, which limits their generalizability and makes them less effective for unseen protocols. To address these issues, we propose SCAN-PhysFed, a novel SCanning- and ANatomy-level personalized Physics-Driven Federated learning paradigm for LDCT reconstruction. Since the noise distribution in LDCT data is closely tied to scanning protocols and anatomical structures being scanned, we design a dual-level physics-informed way to address these challenges. Specifically, we incorporate physical and anatomical prompts into our physics-informed hypernetworks to capture scanning- and anatomy-specific information, enabling dual-level physics-driven personalization of imaging features. These prompts are derived from the scanning protocol and the radiology report generated by a medical large language model (MLLM), respectively. Subsequently, client-specific decoders project these dual-level personalized imaging features back into the image domain. Besides, to tackle the challenge of unseen data, we introduce a novel protocol vector-quantization strategy (PVQS), which ensures consistent performance across new clients by quantifying the unseen scanning code as one of the codes in the scanning codebook. Extensive experimental results demonstrate the superior performance of SCAN-PhysFed on public datasets.
Authors: Pu Li, Wenhao Zhang, Jianwei Guo, Jinglu Chen, Dong-Ming Yan
Abstract: The integration of deep generative networks into generating Computer-Aided Design (CAD) models has garnered increasing attention over recent years. Traditional methods often rely on discrete sequences of parametric line/curve segments to represent sketches. Differently, we introduce RECAD, a novel framework that generates Raster sketches and 3D Extrusions for CAD models. Representing sketches as raster images offers several advantages over discrete sequences: 1) it breaks the limitations on the types and numbers of lines/curves, providing enhanced geometric representation capabilities; 2) it enables interpolation within a continuous latent space; and 3) it allows for more intuitive user control over the output. Technically, RECAD employs two diffusion networks: the first network generates extrusion boxes conditioned on the number and types of extrusions, while the second network produces sketch images conditioned on these extrusion boxes. By combining these two networks, RECAD effectively generates sketch-and-extrude CAD models, offering a more robust and intuitive approach to CAD model generation. Experimental results indicate that RECAD achieves strong performance in unconditional generation, while also demonstrating effectiveness in conditional generation and output editing.
Authors: Muhammad Rafiq, Hazrat Ali, Ghulam Mujtaba, Zubair Shah, Shoaib Azmat
Abstract: Deep learning-based computer-aided diagnosis (CAD) of medical images requires large datasets. However, the lack of large publicly available labeled datasets limits the development of deep learning-based CAD systems. Generative Adversarial Networks (GANs), in particular, CycleGAN, can be used to generate new cross-domain images without paired training data. However, most CycleGAN-based synthesis methods lack the potential to overcome alignment and asymmetry between the input and generated data. We propose a two-stage technique for the synthesis of abdominal MRI using cross-modality translation of abdominal CT. We show that the synthetic data can help improve the performance of the liver segmentation network. We increase the number of abdominal MRI images through cross-modality image transformation of unpaired CT images using a CycleGAN inspired deformation invariant network called EssNet. Subsequently, we combine the synthetic MRI images with the original MRI images and use them to improve the accuracy of the U-Net on a liver segmentation task. We train the U-Net on real MRI images and then on real and synthetic MRI images. Consequently, by comparing both scenarios, we achieve an improvement in the performance of U-Net. In summary, the improvement achieved in the Intersection over Union (IoU) is 1.17%. The results show potential to address the data scarcity challenge in medical imaging.
Authors: Xingzhuo Guo, Yu Zhang, Baixu Chen, Haoran Xu, Jianmin Wang, Mingsheng Long
Abstract: Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong performance across various tasks and modalities, their application to temporal predictive learning remains underexplored. Existing approaches treat predictive learning as a conditional generation problem, but often fail to fully exploit the temporal dynamics inherent in the data, leading to challenges in generating temporally coherent sequences. To address this, we introduce Dynamical Diffusion (DyDiff), a theoretically sound framework that incorporates temporally aware forward and reverse processes. Dynamical Diffusion explicitly models temporal transitions at each diffusion step, establishing dependencies on preceding states to better capture temporal dynamics. Through the reparameterization trick, Dynamical Diffusion achieves efficient training and inference similar to any standard diffusion model. Extensive experiments across scientific spatiotemporal forecasting, video prediction, and time series forecasting demonstrate that Dynamical Diffusion consistently improves performance in temporal predictive tasks, filling a crucial gap in existing methodologies. Code is available at this repository: https://github.com/thuml/dynamical-diffusion.
Authors: Purvi Goel, Haotian Zhang, C. Karen Liu, Kayvon Fatahalian
Abstract: Keyframes are a standard representation for kinematic motion specification. Recent learned motion-inbetweening methods use keyframes as a way to control generative motion models, and are trained to generate life-like motion that matches the exact poses and timings of input keyframes. However, the quality of generated motion may degrade if the timing of these constraints is not perfectly consistent with the desired motion. Unfortunately, correctly specifying keyframe timings is a tedious and challenging task in practice. Our goal is to create a system that synthesizes high-quality motion from keyframes, even if keyframes are imprecisely timed. We present a method that allows constraints to be retimed as part of the generation process. Specifically, we introduce a novel model architecture that explicitly outputs a time-warping function to correct mistimed keyframes, and spatial residuals that add pose details. We demonstrate how our method can automatically turn approximately timed keyframe constraints into diverse, realistic motions with plausible timing and detailed submovements.
Authors: Florian Dreyer, Ekaterina Kolos, Daria Matiash
Abstract: Large language models (LLMs) can answer questions and reason about complex tasks, also from the scientific domain. We assess several multimodal LLMs (MLLMs) on ScienceQA and find that Gemini models show the highest accuracy with little context, and the highest textual similarity to human explanations with richer context. Adapter-tuning of smaller MLLMs did not lead to any reliable performance. Training from Gemini outputs consistently underperformed training from the original data.
Authors: Jingyu Song, Haoyu Ma, Onur Bagoren, Advaith V. Sethuraman, Yiting Zhang, Katherine A. Skinner
Abstract: Underwater simulators offer support for building robust underwater perception solutions. Significant work has recently been done to develop new simulators and to advance the performance of existing underwater simulators. Still, there remains room for improvement on physics-based underwater sensor modeling and rendering efficiency. In this paper, we propose OceanSim, a high-fidelity GPU-accelerated underwater simulator to address this research gap. We propose advanced physics-based rendering techniques to reduce the sim-to-real gap for underwater image simulation. We develop OceanSim to fully leverage the computing advantages of GPUs and achieve real-time imaging sonar rendering and fast synthetic data generation. We evaluate the capabilities and realism of OceanSim using real-world data to provide qualitative and quantitative results. The project page for OceanSim is https://umfieldrobotics.github.io/OceanSim.
Authors: Seunghoi Kim, Henry F. J. Tregidgo, Matteo Figini, Chen Jin, Sarang Joshi, Daniel C. Alexander
Abstract: Hallucinations are spurious structures not present in the ground truth, posing a critical challenge in medical image reconstruction, especially for data-driven conditional models. We hypothesize that combining an unconditional diffusion model with data consistency, trained on a diverse dataset, can reduce these hallucinations. Based on this, we propose DynamicDPS, a diffusion-based framework that integrates conditional and unconditional diffusion models to enhance low-quality medical images while systematically reducing hallucinations. Our approach first generates an initial reconstruction using a conditional model, then refines it with an adaptive diffusion-based inverse problem solver. DynamicDPS skips early stage in the reverse process by selecting an optimal starting time point per sample and applies Wolfe's line search for adaptive step sizes, improving both efficiency and image fidelity. Using diffusion priors and data consistency, our method effectively reduces hallucinations from any conditional model output. We validate its effectiveness in Image Quality Transfer for low-field MRI enhancement. Extensive evaluations on synthetic and real MR scans, including a downstream task for tissue volume estimation, show that DynamicDPS reduces hallucinations, improving relative volume estimation by over 15% for critical tissues while using only 5% of the sampling steps required by baseline diffusion models. As a model-agnostic and fine-tuning-free approach, DynamicDPS offers a robust solution for hallucination reduction in medical imaging. The code will be made publicly available upon publication.
Authors: Wenda Chu, Yang Song, Yisong Yue
Abstract: We study the problem of posterior sampling in discrete-state spaces using discrete diffusion models. While posterior sampling methods for continuous diffusion models have achieved remarkable progress, analogous methods for discrete diffusion models remain challenging. In this work, we introduce a principled plug-and-play discrete diffusion posterior sampling algorithm based on split Gibbs sampling, which we call SG-DPS. Our algorithm enables reward-guided generation and solving inverse problems in discrete-state spaces. We demonstrate that SG-DPS converges to the true posterior distribution on synthetic benchmarks, and enjoys state-of-the-art posterior sampling performance on a range of benchmarks for discrete data, achieving up to 2x improved performance compared to existing baselines.
Authors: EungGu Yun, Heonjin Ha, Yeongwoo Nam, Bryan Dongik Lee
Abstract: This paper introduces LAFT, a novel feature transformation method designed to incorporate user knowledge and preferences into anomaly detection using natural language. Accurately modeling the boundary of normality is crucial for distinguishing abnormal data, but this is often challenging due to limited data or the presence of nuisance attributes. While unsupervised methods that rely solely on data without user guidance are common, they may fail to detect anomalies of specific interest. To address this limitation, we propose Language-Assisted Feature Transformation (LAFT), which leverages the shared image-text embedding space of vision-language models to transform visual features according to user-defined requirements. Combined with anomaly detection methods, LAFT effectively aligns visual features with user preferences, allowing anomalies of interest to be detected. Extensive experiments on both toy and real-world datasets validate the effectiveness of our method.
Authors: Wenhao Liang, Wei Emma Zhang, Lin Yue, Miao Xu, Olaf Maennel, Weitong Chen
Abstract: Kolmogorov Arnold Networks (KANs) are neural architectures inspired by the Kolmogorov Arnold representation theorem that leverage B Spline parameterizations for flexible, locally adaptive function approximation. Although KANs can capture complex nonlinearities beyond those modeled by standard MultiLayer Perceptrons (MLPs), they frequently exhibit miscalibrated confidence estimates manifesting as overconfidence in dense data regions and underconfidence in sparse areas. In this work, we systematically examine the impact of four critical hyperparameters including Layer Width, Grid Order, Shortcut Function, and Grid Range on the calibration of KANs. Furthermore, we introduce a novel TemperatureScaled Loss (TSL) that integrates a temperature parameter directly into the training objective, dynamically adjusting the predictive distribution during learning. Both theoretical analysis and extensive empirical evaluations on standard benchmarks demonstrate that TSL significantly reduces calibration errors, thereby improving the reliability of probabilistic predictions. Overall, our study provides actionable insights into the design of spline based neural networks and establishes TSL as a robust loss solution for enhancing calibration.
Authors: S. Chen, D. Ma, M. Raviselvan, S. Sundaramoorthy, K. Popuri, M. J. Ju, M. V. Sarunic, D. Ratra, M. F. Beg
Abstract: This study presents an AI-driven pipeline for automated retinal segmentation and thickness analysis in diabetic retinopathy (DR) using SD-OCT imaging. A deep neural network was trained to segment ten retinal layers, intra-retinal fluid, and hyperreflective foci (HRF), with performance evaluated across multiple architectures. SwinUNETR achieved the highest segmentation accuracy, while VM-Unet excelled in specific layers. Analysis revealed distinct thickness variations between NPDR and PDR, with correlations between layer thickness and visual acuity. The proposed method enhances DR assessment by reducing manual annotation effort and providing clinically relevant thickness maps for disease monitoring and treatment planning.
Authors: Linhao Li, Changhui Su, Yu Guo, Huimao Zhang, Dong Liang, Kun Shang
Abstract: Contrast-enhanced magnetic resonance imaging (CE-MRI) is crucial for tumor detection and diagnosis, but the use of gadolinium-based contrast agents (GBCAs) in clinical settings raises safety concerns due to potential health risks. To circumvent these issues while preserving diagnostic accuracy, we propose a novel Transformer with Localization Prompts (TLP) framework for synthesizing CE-MRI from non-contrast MR images. Our architecture introduces three key innovations: a hierarchical backbone that uses efficient Transformer to process multi-scale features; a multi-stage fusion system consisting of Local and Global Fusion modules that hierarchically integrate complementary information via spatial attention operations and cross-attention mechanisms, respectively; and a Fuzzy Prompt Generation (FPG) module that enhances the TLP model's generalization by emulating radiologists' manual annotation through stochastic feature perturbation. The framework uniquely enables interactive clinical integration by allowing radiologists to input diagnostic prompts during inference, synergizing artificial intelligence with medical expertise. This research establishes a new paradigm for contrast-free MRI synthesis while addressing critical clinical needs for safer diagnostic procedures. Codes are available at https://github.com/ChanghuiSu/TLP.
Authors: Pooya Mohammadi Kazaj, Giovanni Baj, Yazdan Salimi, Anselm W. Stark, Waldo Valenzuela, George CM. Siontis, Habib Zaidi, Mauricio Reyes, Christoph Graeni, Isaac Shiri
Abstract: While numerous architectures for medical image segmentation have been proposed, achieving competitive performance with state-of-the-art models networks such as nnUNet, still leave room for further innovation. In this work, we introduce nnUZoo, an open source benchmarking framework built upon nnUNet, which incorporates various deep learning architectures, including CNNs, Transformers, and Mamba-based models. Using this framework, we provide a fair comparison to demystify performance claims across different medical image segmentation tasks. Additionally, in an effort to enrich the benchmarking, we explored five new architectures based on Mamba and Transformers, collectively named X2Net, and integrated them into nnUZoo for further evaluation. The proposed models combine the features of conventional U2Net, nnUNet, CNN, Transformer, and Mamba layers and architectures, called X2Net (UNETR2Net (UNETR), SwT2Net (SwinTransformer), SS2D2Net (SwinUMamba), Alt1DM2Net (LightUMamba), and MambaND2Net (MambaND)). We extensively evaluate the performance of different models on six diverse medical image segmentation datasets, including microscopy, ultrasound, CT, MRI, and PET, covering various body parts, organs, and labels. We compare their performance, in terms of dice score and computational efficiency, against their baseline models, U2Net, and nnUNet. CNN models like nnUNet and U2Net demonstrated both speed and accuracy, making them effective choices for medical image segmentation tasks. Transformer-based models, while promising for certain imaging modalities, exhibited high computational costs. Proposed Mamba-based X2Net architecture (SS2D2Net) achieved competitive accuracy with no significantly difference from nnUNet and U2Net, while using fewer parameters. However, they required significantly longer training time, highlighting a trade-off between model efficiency and computational cost.
Authors: Kun Zhang, Jingyu Li, Zhe Li, Jingjing Zhang
Abstract: With the rapid growth of multi-modal data from social media, short video platforms, and e-commerce, content-based retrieval has become essential for efficiently searching and utilizing heterogeneous information. Over time, retrieval techniques have evolved from Unimodal Retrieval (UR) to Cross-modal Retrieval (CR) and, more recently, to Composed Multi-modal Retrieval (CMR). CMR enables users to retrieve images or videos by integrating a reference visual input with textual modifications, enhancing search flexibility and precision. This paper provides a comprehensive review of CMR, covering its fundamental challenges, technical advancements, and categorization into supervised, zero-shot, and semi-supervised learning paradigms. We discuss key research directions, including data augmentation, model architecture, and loss optimization in supervised CMR, as well as transformation frameworks and external knowledge integration in zero-shot CMR. Additionally, we highlight the application potential of CMR in composed image retrieval, video retrieval, and person retrieval, which have significant implications for e-commerce, online search, and public security. Given its ability to refine and personalize search experiences, CMR is poised to become a pivotal technology in next-generation retrieval systems. A curated list of related works and resources is available at: https://github.com/kkzhang95/Awesome-Composed-Multi-modal-Retrieval
URLs: https://github.com/kkzhang95/Awesome-Composed-Multi-modal-Retrieval
Authors: Xiaoyu Zheng, Jing Wen, Jiaxin Zhuang, Yao Du, Jing Cong, Limei Guo, Chao He, Lin Luo, Hao Chen
Abstract: Polarization, as a new optical imaging tool, has been explored to assist in the diagnosis of pathology. Moreover, converting the polarimetric Mueller Matrix (MM) to standardized stained images becomes a promising approach to help pathologists interpret the results. However, existing methods for polarization-based virtual staining are still in the early stage, and the diffusion-based model, which has shown great potential in enhancing the fidelity of the generated images, has not been studied yet. In this paper, a Regulated Bridge Diffusion Model (RBDM) for polarization-based virtual staining is proposed. RBDM utilizes the bidirectional bridge diffusion process to learn the mapping from polarization images to other modalities such as H\&E and fluorescence. And to demonstrate the effectiveness of our model, we conduct the experiment on our manually collected dataset, which consists of 18,000 paired polarization, fluorescence and H\&E images, due to the unavailability of the public dataset. The experiment results show that our model greatly outperforms other benchmark methods. Our dataset and code will be released upon acceptance.
Authors: Jiantao Lin, Xin Yang, Meixi Chen, Yingjie Xu, Dongyu Yan, Leyi Wu, Xinli Xu, Lie XU, Shunsi Zhang, Ying-Cong Chen
Abstract: Diffusion models have achieved great success in generating 2D images. However, the quality and generalizability of 3D content generation remain limited. State-of-the-art methods often require large-scale 3D assets for training, which are challenging to collect. In this work, we introduce Kiss3DGen (Keep It Simple and Straightforward in 3D Generation), an efficient framework for generating, editing, and enhancing 3D objects by repurposing a well-trained 2D image diffusion model for 3D generation. Specifically, we fine-tune a diffusion model to generate ''3D Bundle Image'', a tiled representation composed of multi-view images and their corresponding normal maps. The normal maps are then used to reconstruct a 3D mesh, and the multi-view images provide texture mapping, resulting in a complete 3D model. This simple method effectively transforms the 3D generation problem into a 2D image generation task, maximizing the utilization of knowledge in pretrained diffusion models. Furthermore, we demonstrate that our Kiss3DGen model is compatible with various diffusion model techniques, enabling advanced features such as 3D editing, mesh and texture enhancement, etc. Through extensive experiments, we demonstrate the effectiveness of our approach, showcasing its ability to produce high-quality 3D models efficiently.
Authors: Dawid Mazur, Tomasz Rybotycki, Piotr Gawron
Abstract: Training of machine learning models consumes large amounts of energy. Since the energy consumption becomes a major problem in the development and implementation of artificial intelligence systems there exists a need to investigate the ways to reduce use of the resources by these systems. In this work we study how application of quantum annealers could lead to reduction of energy cost in training models aiming at pixel-level segmentation of hyperspectral images. Following the results of QBM4EO team, we propose a classical machine learning model, partially trained using quantum annealer, for hyperspectral image segmentation. We show that the model trained using quantum annealer is better or at least comparable with models trained using alternative algorithms, according to the preselected, common metrics. While direct energy use comparison does not make sense at the current stage of quantum computing technology development, we believe that our work proves that quantum annealing should be considered as a tool for training at least some machine learning models.
Authors: Haoxuan Li, Ziya Erkoc, Lei Li, Daniele Sirigatti, Vladyslav Rozov, Angela Dai, Matthias Nie{\ss}ner
Abstract: We introduce MeshPad, a generative approach that creates 3D meshes from sketch inputs. Building on recent advances in artistic-designed triangle mesh generation, our approach addresses the need for interactive artistic mesh creation. To this end, we focus on enabling consistent edits by decomposing editing into 'deletion' of regions of a mesh, followed by 'addition' of new mesh geometry. Both operations are invoked by simple user edits of a sketch image, facilitating an iterative content creation process and enabling the construction of complex 3D meshes. Our approach is based on a triangle sequence-based mesh representation, exploiting a large Transformer model for mesh triangle addition and deletion. In order to perform edits interactively, we introduce a vertex-aligned speculative prediction strategy on top of our additive mesh generator. This speculator predicts multiple output tokens corresponding to a vertex, thus significantly reducing the computational cost of inference and accelerating the editing process, making it possible to execute each editing step in only a few seconds. Comprehensive experiments demonstrate that MeshPad outperforms state-of-the-art sketch-conditioned mesh generation methods, achieving more than 22% mesh quality improvement in Chamfer distance, and being preferred by 90% of participants in perceptual evaluations.
Authors: A. Tajja, A. Aghabiglou, E. Tolley, J-P. Kneib, J-P. Thiran, Y. Wiaux
Abstract: Recently, the R2D2 paradigm, standing for ''Residual-to-Residual DNN series for high-Dynamic-range imaging'', was introduced for image formation in Radio Interferometry (RI) as a learned version of the traditional algorithm CLEAN. The first incarnations of R2D2 are limited to planar imaging on small fields of view, failing to meet the spherical-imaging requirement of modern telescopes observing wide fields. To address this limitation, we propose the spherical-imaging extension S-R2D2. Firstly, as R2D2, S-R2D2 encapsulates its minor cycles in existing 2D-Euclidean deep neural network (DNN) architectures, but adapts its iterative scheme to incorporate the wide-field measurement model mapping a spherical image to visibility data. We implemented this model as the composition of an efficient Fourier-based interpolator mapping the spherical image onto the equatorial plane, with the standard RI operator mapping the equatorial-plane image to visibility data. Importantly, the interpolation step must inevitably be performed at a lower-than-optimal resolution on the plane, to meet the high-resolution requirement on the sphere of wide-field imaging while preserving scalability. Therefore, secondly, we design S-R2D2's DNN training loss to jointly learn to correct the interpolation approximations and identify residual image structures on the sphere, ensuring consistency with the spherical ground truth using the adjoint plane-to-sphere interpolator. Finally, we demonstrate through simulations S-R2D2's capability to perform fast and accurate reconstructions of spherical monochromatic intensity images, across high-resolution, high-dynamic-range settings.
Authors: Carlos Gomes, Isabelle Wittmann, Damien Robert, Johannes Jakubik, Tim Reichelt, Michele Martone, Stefano Maurogiovanni, Rikard Vinge, Jonas Hurst, Erik Scheurer, Rocco Sedona, Thomas Brunschwiler, Stefan Kesselheim, Matej Batic, Philip Stier, Jan Dirk Wegner, Gabriele Cavallaro, Edzer Pebesma, Michael Marszalek, Miguel A Belenguer-Plomer, Kennedy Adriko, Paolo Fraccaro, Romeo Kienzler, Rania Briq, Sabrina Benassou, Michele Lazzarini, Conrad M Albrecht
Abstract: Over the past decades, there has been an explosion in the amount of available Earth Observation (EO) data. The unprecedented coverage of the Earth's surface and atmosphere by satellite imagery has resulted in large volumes of data that must be transmitted to ground stations, stored in data centers, and distributed to end users. Modern Earth System Models (ESMs) face similar challenges, operating at high spatial and temporal resolutions, producing petabytes of data per simulated day. Data compression has gained relevance over the past decade, with neural compression (NC) emerging from deep learning and information theory, making EO data and ESM outputs ideal candidates due to their abundance of unlabeled data. In this review, we outline recent developments in NC applied to geospatial data. We introduce the fundamental concepts of NC including seminal works in its traditional applications to image and video compression domains with focus on lossy compression. We discuss the unique characteristics of EO and ESM data, contrasting them with "natural images", and explain the additional challenges and opportunities they present. Moreover, we review current applications of NC across various EO modalities and explore the limited efforts in ESM compression to date. The advent of self-supervised learning (SSL) and foundation models (FM) has advanced methods to efficiently distill representations from vast unlabeled data. We connect these developments to NC for EO, highlighting the similarities between the two fields and elaborate on the potential of transferring compressed feature representations for machine--to--machine communication. Based on insights drawn from this review, we devise future directions relevant to applications in EO and ESM.
Authors: Saeed Shakuri, Alireza Rezvanian
Abstract: Lung cancer has the highest rate of cancer-caused deaths, and early-stage diagnosis could increase the survival rate. Lung nodules are common indicators of lung cancer, making their detection crucial. Various lung nodule detection models exist, but many lack efficiency. Hence, we propose a more efficient approach by leveraging 2D CT slices, reducing computational load and complexity in training and inference. We employ the tiny version of Swin Transformer to benefit from Vision Transformers (ViT) while maintaining low computational cost. A Feature Pyramid Network is added to enhance detection, particularly for small nodules. Additionally, Transfer Learning is used to accelerate training. Our experimental results show that the proposed model outperforms state-of-the-art methods, achieving higher mAP and mAR for small nodules by 1.3% and 1.6%, respectively. Overall, our model achieves the highest mAP of 94.7% and mAR of 94.9%.
Authors: Masih Eskandar, Tooba Imtiaz, Davin Hill, Zifeng Wang, Jennifer Dy
Abstract: Humans can naturally learn new and varying tasks in a sequential manner. Continual learning is a class of learning algorithms that updates its learned model as it sees new data (on potentially new tasks) in a sequence. A key challenge in continual learning is that as the model is updated to learn new tasks, it becomes susceptible to catastrophic forgetting, where knowledge of previously learned tasks is lost. A popular approach to mitigate forgetting during continual learning is to maintain a small buffer of previously-seen samples and to replay them during training. However, this approach is limited by the small buffer size, and while forgetting is reduced, it is still present. In this paper, we propose a novel loss function, STAR, that exploits the worst-case parameter perturbation that reduces the KL-divergence of model predictions with that of its local parameter neighborhood to promote stability and alleviate forgetting. STAR can be combined with almost any existing rehearsal-based method as a plug-and-play component. We empirically show that STAR consistently improves the performance of existing methods by up to 15% across varying baselines and achieves superior or competitive accuracy to that of state-of-the-art methods aimed at improving rehearsal-based continual learning.
Authors: Arnesh Batra, Arush Gumber, Anushk Kumar
Abstract: The increasing prevalence of lumbar spinal canal stenosis has resulted in a surge of MRI (Magnetic Resonance Imaging), leading to labor-intensive interpretation and significant inter-reader variability, even among expert radiologists. This paper introduces a novel and efficient deep-learning framework that fully automates the grading of lumbar spinal canal stenosis. We demonstrate state-of-the-art performance in grading spinal canal stenosis on a dataset of 1,975 unique studies, each containing three distinct types of 3D cross-sectional spine images: Axial T2, Sagittal T1, and Sagittal T2/STIR. Employing a distinctive training strategy, our proposed multistage approach effectively integrates sagittal and axial images. This strategy employs a multi-view model with a sequence-based architecture, optimizing feature extraction and cross-view alignment to achieve an AUROC (Area Under the Receiver Operating Characteristic Curve) of 0.971 in spinal canal stenosis grading surpassing other state-of-the-art methods.
Authors: Yingxue Xu, Fengtao Zhou, Chenyu Zhao, Yihui Wang, Can Yang, Hao Chen
Abstract: The integration of multimodal data including pathology images and gene profiles is widely applied in precise survival prediction. Despite recent advances in multimodal survival models, collecting complete modalities for multimodal fusion still poses a significant challenge, hindering their application in clinical settings. Current approaches tackling incomplete modalities often fall short, as they typically compensate for only a limited part of the knowledge of missing modalities. To address this issue, we propose a Distilled Prompt Learning framework (DisPro) to utilize the strong robustness of Large Language Models (LLMs) to missing modalities, which employs two-stage prompting for compensation of comprehensive information for missing modalities. In the first stage, Unimodal Prompting (UniPro) distills the knowledge distribution of each modality, preparing for supplementing modality-specific knowledge of the missing modality in the subsequent stage. In the second stage, Multimodal Prompting (MultiPro) leverages available modalities as prompts for LLMs to infer the missing modality, which provides modality-common information. Simultaneously, the unimodal knowledge acquired in the first stage is injected into multimodal inference to compensate for the modality-specific knowledge of the missing modality. Extensive experiments covering various missing scenarios demonstrated the superiority of the proposed method. The code is available at https://github.com/Innse/DisPro.
Authors: Alexander Karpekov, Sonia Chernova, Thomas Pl\"otz
Abstract: Human Activity Recognition (HAR) using ambient sensors has great potential for practical applications, particularly in elder care and independent living. However, deploying HAR systems in real-world settings remains challenging due to the high cost of labeled data, the need for pre-segmented sensor streams, and the lack of flexibility in activity granularity. To address these limitations, we introduce DISCOVER, a method designed to discover fine-grained human sub-activities from unlabeled sensor data without relying on pre-segmentation. DISCOVER combines unsupervised feature extraction and clustering with a user-friendly visualization tool to streamline the labeling process. DISCOVER enables domain experts to efficiently annotate only a minimal set of representative cluster centroids, reducing the annotation workload to a small number of samples (0.05% of our dataset). We demonstrate DISCOVER's effectiveness through a re-annotation exercise on widely used HAR datasets, showing that it uncovers finer-grained activities and produces more nuanced annotations than traditional coarse labels. DISCOVER represents a step toward practical, deployable HAR systems that adapt to diverse real environments.
Authors: Heming Fu, Hongkai Chen, Shan Lin, Guoliang Xing
Abstract: Alzheimer's Disease (AD) has become an increasingly critical global health concern, which necessitates effective monitoring solutions in smart health applications. However, the development of such solutions is significantly hindered by the scarcity of AD-specific activity datasets. To address this challenge, we propose SHADE-AD, a Large Language Model (LLM) framework for Synthesizing Human Activity Datasets Embedded with AD features. Leveraging both public datasets and our own collected data from 99 AD patients, SHADE-AD synthesizes human activity videos that specifically represent AD-related behaviors. By employing a three-stage training mechanism, it broadens the range of activities beyond those collected from limited deployment settings. We conducted comprehensive evaluations of the generated dataset, demonstrating significant improvements in downstream tasks such as Human Activity Recognition (HAR) detection, with enhancements of up to 79.69%. Detailed motion metrics between real and synthetic data show strong alignment, validating the realism and utility of the synthesized dataset. These results underscore SHADE-AD's potential to advance smart health applications by providing a cost-effective, privacy-preserving solution for AD monitoring.
Authors: Tiansheng Wen, Yifei Wang, Zequn Zeng, Zhong Peng, Yudi Su, Xinyang Liu, Bo Chen, Hongwei Liu, Stefanie Jegelka, Chenyu You
Abstract: Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling. Matryoshka Representation Learning (MRL) recently emerged as a solution for adaptive embedding lengths, but it requires full model retraining and suffers from noticeable performance degradations at short lengths. In this paper, we show that sparse coding offers a compelling alternative for achieving adaptive representation with minimal overhead and higher fidelity. We propose Contrastive Sparse Representation (CSR), a method that sparsifies pre-trained embeddings into a high-dimensional but selectively activated feature space. By leveraging lightweight autoencoding and task-aware contrastive objectives, CSR preserves semantic quality while allowing flexible, cost-effective inference at different sparsity levels. Extensive experiments on image, text, and multimodal benchmarks demonstrate that CSR consistently outperforms MRL in terms of both accuracy and retrieval speed-often by large margins-while also cutting training time to a fraction of that required by MRL. Our results establish sparse coding as a powerful paradigm for adaptive representation learning in real-world applications where efficiency and fidelity are both paramount. Code is available at https://github.com/neilwen987/CSR_Adaptive_Rep
Authors: Ali Tourani, Saad Ejaz, Hriday Bavle, David Morilla-Cabello, Jose Luis Sanchez-Lopez, Holger Voos
Abstract: Current Visual Simultaneous Localization and Mapping (VSLAM) systems often struggle to create maps that are both semantically rich and easily interpretable. While incorporating semantic scene knowledge aids in building richer maps with contextual associations among mapped objects, representing them in structured formats like scene graphs has not been widely addressed, encountering complex map comprehension and limited scalability. This paper introduces visual S-Graphs (vS-Graphs), a novel real-time VSLAM framework that integrates vision-based scene understanding with map reconstruction and comprehensible graph-based representation. The framework infers structural elements (i.e., rooms and corridors) from detected building components (i.e., walls and ground surfaces) and incorporates them into optimizable 3D scene graphs. This solution enhances the reconstructed map's semantic richness, comprehensibility, and localization accuracy. Extensive experiments on standard benchmarks and real-world datasets demonstrate that vS-Graphs outperforms state-of-the-art VSLAM methods, reducing trajectory error by an average of 3.38% and up to 9.58% on real-world data. Furthermore, the proposed framework achieves environment-driven semantic entity detection accuracy comparable to precise LiDAR-based frameworks using only visual features. A web page containing more media and evaluation outcomes is available on https://snt-arg.github.io/vsgraphs-results/.
Authors: Adri\`a L\'opez Escoriza, Nicklas Hansen, Stone Tao, Tongzhou Mu, Hao Su
Abstract: Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively exploring the expansive state-action space. However, despite a lack of dense rewards, these tasks often have a multi-stage structure, which can be leveraged to decompose the overall objective into manageable subgoals. In this work, we propose DEMO3, a framework that exploits this structure for efficient learning from visual inputs. Specifically, our approach incorporates multi-stage dense reward learning, a bi-phasic training scheme, and world model learning into a carefully designed demonstration-augmented RL framework that strongly mitigates the challenge of exploration in long-horizon tasks. Our evaluations demonstrate that our method improves data-efficiency by an average of 40% and by 70% on particularly difficult tasks compared to state-of-the-art approaches. We validate this across 16 sparse-reward tasks spanning four domains, including challenging humanoid visual control tasks using as few as five demonstrations.
Authors: Zhengyuan Jiang, Yuepeng Hu, Yuchen Yang, Yinzhi Cao, Neil Zhenqiang Gong
Abstract: Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the models themselves are aligned to reduce harmful outputs. However, these defenses remain vulnerable when an attacker strategically designs adversarial prompts to bypass these safety guardrails. In this work, we propose PromptTune, a method to jailbreak text-to-image models with safety guardrails using a fine-tuned large language model. Unlike other query-based jailbreak attacks that require repeated queries to the target model, our attack generates adversarial prompts efficiently after fine-tuning our AttackLLM. We evaluate our method on three datasets of unsafe prompts and against five safety guardrails. Our results demonstrate that our approach effectively bypasses safety guardrails, outperforms existing no-box attacks, and also facilitates other query-based attacks.
Authors: Haoran You, Baopu Li, Zhanyi Sun, Xu Ouyang, Yingyan Celine Lin
Abstract: Neural architecture search (NAS) has demonstrated amazing success in searching for efficient deep neural networks (DNNs) from a given supernet. In parallel, the lottery ticket hypothesis has shown that DNNs contain small subnetworks that can be trained from scratch to achieve a comparable or higher accuracy than original DNNs. As such, it is currently a common practice to develop efficient DNNs via a pipeline of first search and then prune. Nevertheless, doing so often requires a search-train-prune-retrain process and thus prohibitive computational cost. In this paper, we discover for the first time that both efficient DNNs and their lottery subnetworks (i.e., lottery tickets) can be directly identified from a supernet, which we term as SuperTickets, via a two-in-one training scheme with jointly architecture searching and parameter pruning. Moreover, we develop a progressive and unified SuperTickets identification strategy that allows the connectivity of subnetworks to change during supernet training, achieving better accuracy and efficiency trade-offs than conventional sparse training. Finally, we evaluate whether such identified SuperTickets drawn from one task can transfer well to other tasks, validating their potential of handling multiple tasks simultaneously. Extensive experiments and ablation studies on three tasks and four benchmark datasets validate that our proposed SuperTickets achieve boosted accuracy and efficiency trade-offs than both typical NAS and pruning pipelines, regardless of having retraining or not. Codes and pretrained models are available at https://github.com/RICE-EIC/SuperTickets.
Authors: Nathanael L. Baisa
Abstract: Learning representative, robust and discriminative information from images is essential for effective person re-identification (Re-Id). In this paper, we propose a compound approach for end-to-end discriminative deep feature learning for person Re-Id based on both body and hand images. We carefully design the Local-Aware Global Attention Network (LAGA-Net), a multi-branch deep network architecture consisting of one branch for spatial attention, one branch for channel attention, one branch for global feature representations and another branch for local feature representations. The attention branches focus on the relevant features of the image while suppressing the irrelevant backgrounds. In order to overcome the weakness of the attention mechanisms, equivariant to pixel shuffling, we integrate relative positional encodings into the spatial attention module to capture the spatial positions of pixels. The global branch intends to preserve the global context or structural information. For the the local branch, which intends to capture the fine-grained information, we perform uniform partitioning to generate stripes on the conv-layer horizontally. We retrieve the parts by conducting a soft partition without explicitly partitioning the images or requiring external cues such as pose estimation. A set of ablation study shows that each component contributes to the increased performance of the LAGA-Net. Extensive evaluations on four popular body-based person Re-Id benchmarks and two publicly available hand datasets demonstrate that our proposed method consistently outperforms existing state-of-the-art methods.
Authors: Nathanael L. Baisa
Abstract: In this paper, we propose a multi-task representation learning framework to jointly estimate the identity, gender and age of individuals from their hand images for the purpose of criminal investigations since the hand images are often the only available information in cases of serious crime such as sexual abuse. We investigate different up-to-date deep learning architectures and compare their performance for joint estimation of identity, gender and age from hand images of perpetrators of serious crime. To simplify the age prediction, we create age groups for the age estimation. We make extensive evaluations and comparisons of both convolution-based and transformer-based deep learning architectures on a publicly available 11k hands dataset. Our experimental analysis shows that it is possible to efficiently estimate not only identity but also other attributes such as gender and age of suspects jointly from hand images for criminal investigations, which is crucial in assisting international police forces in the court to identify and convict abusers.
Authors: Tao Feng, Jie Zhang, Huashan Liu, Zhijie Wang, Shengyuan Pang
Abstract: Deep hashing retrieval has gained widespread use in big data retrieval due to its robust feature extraction and efficient hashing process. However, training advanced deep hashing models has become more expensive due to complex optimizations and large datasets. Coreset selection and Dataset Condensation lower overall training costs by reducing the volume of training data without significantly compromising model accuracy for classification task. In this paper, we explore the effect of mainstream dataset condensation methods for deep hashing retrieval and propose IEM (Information-intensive feature Embedding Matching), which is centered on distribution matching and incorporates model and data augmentation techniques to further enhance the feature of hashing space. Extensive experiments demonstrate the superior performance and efficiency of our approach.
Authors: Liang Pan, Jingbo Wang, Buzhen Huang, Junyu Zhang, Haofan Wang, Xu Tang, Yangang Wang
Abstract: We present a physics-based character control framework for synthesizing human-scene interactions. Recent advances adopt physics simulation to mitigate artifacts produced by data-driven kinematic approaches. However, existing physics-based methods mainly focus on single-object environments, resulting in limited applicability in realistic 3D scenes with multi-objects. To address such challenges, we propose a framework that enables physically simulated characters to perform long-term interaction tasks in diverse, cluttered, and unseen 3D scenes. The key idea is to decouple human-scene interactions into two fundamental processes, Interacting and Navigating, which motivates us to construct two reusable Controllers, namely InterCon and NavCon. Specifically, InterCon uses two complementary policies to enable characters to enter or leave the interacting state with a particular object (e.g., sitting on a chair or getting up). To realize navigation in cluttered environments, we introduce NavCon, where a trajectory following policy enables characters to track pre-planned collision-free paths. Benefiting from the divide and conquer strategy, we can train all policies in simple environments and directly apply them in complex multi-object scenes through coordination from a rule-based scheduler. Video and code are available at https://github.com/liangpan99/InterScene.
Authors: Marcel Kollovieh, Lukas Gosch, Marten Lienen, Yan Scholten, Leo Schwinn, Stephan G\"unnemann
Abstract: Most adversarial attacks and defenses focus on perturbations within small $\ell_p$-norm constraints. However, $\ell_p$ threat models cannot capture all relevant semantics-preserving perturbations, and hence, the scope of robustness evaluations is limited. In this work, we introduce Score-Based Adversarial Generation (ScoreAG), a novel framework that leverages the advancements in score-based generative models to generate unrestricted adversarial examples that overcome the limitations of $\ell_p$-norm constraints. Unlike traditional methods, ScoreAG maintains the core semantics of images while generating adversarial examples, either by transforming existing images or synthesizing new ones entirely from scratch. We further exploit the generative capability of ScoreAG to purify images, empirically enhancing the robustness of classifiers. Our extensive empirical evaluation demonstrates that ScoreAG improves upon the majority of state-of-the-art attacks and defenses across multiple benchmarks. This work highlights the importance of investigating adversarial examples bounded by semantics rather than $\ell_p$-norm constraints. ScoreAG represents an important step towards more encompassing robustness assessments.
Authors: Yifei Zhang, James Song, Siyi Gu, Tianxu Jiang, Bo Pan, Guangji Bai, Liang Zhao
Abstract: Explainable AI (XAI) has gained significant attention for providing insights into the decision-making processes of deep learning models, particularly for image classification tasks through visual explanations visualized by saliency maps. Despite their success, challenges remain due to the lack of annotated datasets and standardized evaluation pipelines. In this paper, we introduce Saliency-Bench, a novel benchmark suite designed to evaluate visual explanations generated by saliency methods across multiple datasets. We curated, constructed, and annotated eight datasets, each covering diverse tasks such as scene classification, cancer diagnosis, object classification, and action classification, with corresponding ground-truth explanations. The benchmark includes a standardized and unified evaluation pipeline for assessing faithfulness and alignment of the visual explanation, providing a holistic visual explanation performance assessment. We benchmark these eight datasets with widely used saliency methods on different image classifier architectures to evaluate explanation quality. Additionally, we developed an easy-to-use API for automating the evaluation pipeline, from data accessing, and data loading, to result evaluation. The benchmark is available via our website: https://xaidataset.github.io.
Authors: Yung Jer Wong, Teck Khim Ng
Abstract: Diffusion models (DMs) are generative models that learn to synthesize images from Gaussian noise. DMs can be trained to do a variety of tasks such as image generation and image super-resolution. Researchers have made significant improvements in the capability of synthesizing photorealistic images in the past few years. These successes also hasten the need to address the potential misuse of synthesized images. In this paper, we highlighted the effectiveness of Bayer pattern and local statistics in distinguishing digital camera images from DM-generated images. We further hypothesized that local statistics should be used to address the spatial non-stationarity problems in images. We showed that our approach produced promising results for distinguishing real images from synthesized images. This approach is also robust to various perturbations such as image resizing and JPEG compression.
Authors: Ruohao Guo, Xianghua Ying, Yaru Chen, Dantong Niu, Guangyao Li, Liao Qu, Yanyu Qi, Jinxing Zhou, Bowei Xing, Wenzhen Yue, Ji Shi, Qixun Wang, Peiliang Zhang, Buwen Liang
Abstract: In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos. To facilitate this research, we introduce a high-quality benchmark named AVISeg, containing over 90K instance masks from 26 semantic categories in 926 long videos. Additionally, we propose a strong baseline model for this task. Our model first localizes sound source within each frame, and condenses object-specific contexts into concise tokens. Then it builds long-range audio-visual dependencies between these tokens using window-based attention, and tracks sounding objects among the entire video sequences. Extensive experiments reveal that our method performs best on AVISeg, surpassing the existing methods from related tasks. We further conduct the evaluation on several multi-modal large models. Unfortunately, they exhibits subpar performance on instance-level sound source localization and temporal perception. We expect that AVIS will inspire the community towards a more comprehensive multi-modal understanding. Dataset and code is available at https://github.com/ruohaoguo/avis.
Authors: Ge Sun, Sheng Wang, Lei Zhu, Ming Liu, Jun Ma
Abstract: Accurate prediction of pedestrian trajectories is crucial for improving the safety of autonomous driving. However, this task is generally nontrivial due to the inherent stochasticity of human motion, which naturally requires the predictor to generate multi-modal prediction. Previous works leverage various generative methods, such as GAN and VAE, for pedestrian trajectory prediction. Nevertheless, these methods may suffer from mode collapse and relatively low-quality results. The denoising diffusion probabilistic model (DDPM) has recently been applied to trajectory prediction due to its simple training process and powerful reconstruction ability. However, current diffusion-based methods do not fully utilize input information and usually require many denoising iterations that lead to a long inference time or an additional network for initialization. To address these challenges and facilitate the use of diffusion models in multi-modal trajectory prediction, we propose GDTS, a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction. Considering the "goal-driven" characteristics of human motion, GDTS leverages goal estimation to guide the generation of the diffusion network. A two-stage tree sampling algorithm is presented, which leverages common features to reduce the inference time and improve accuracy for multi-modal prediction. Experimental results demonstrate that our proposed framework achieves comparable state-of-the-art performance with real-time inference speed in public datasets.
Authors: Stathis Galanakis, Alexandros Lattas, Stylianos Moschoglou, Stefanos Zafeiriou
Abstract: The remarkable progress in 3D face reconstruction has resulted in high-detail and photorealistic facial representations. Recently, Diffusion Models have revolutionized the capabilities of generative methods by surpassing the performance of GANs. In this work, we present FitDiff, a diffusion-based 3D facial avatar generative model. Leveraging diffusion principles, our model accurately generates relightable facial avatars, utilizing an identity embedding extracted from an "in-the-wild" 2D facial image. The introduced multi-modal diffusion model is the first to concurrently output facial reflectance maps (diffuse and specular albedo and normals) and shapes, showcasing great generalization capabilities. It is solely trained on an annotated subset of a public facial dataset, paired with 3D reconstructions. We revisit the typical 3D facial fitting approach by guiding a reverse diffusion process using perceptual and face recognition losses. Being the first 3D LDM conditioned on face recognition embeddings, FitDiff reconstructs relightable human avatars, that can be used as-is in common rendering engines, starting only from an unconstrained facial image, and achieving state-of-the-art performance.
Authors: Fan Ma, Xiaojie Jin, Heng Wang, Yuchen Xian, Jiashi Feng, Yi Yang
Abstract: Recent advances in large video-language models have displayed promising outcomes in video comprehension. Current approaches straightforwardly convert video into language tokens and employ large language models for multi-modal tasks. However, this method often leads to the generation of irrelevant content, commonly known as "hallucination", as the length of the text increases and the impact of the video diminishes. To address this problem, we propose Vista-LLaMA, a novel framework that maintains the consistent distance between all visual tokens and any language tokens, irrespective of the generated text length. Vista-LLaMA omits relative position encoding when determining attention weights between visual and text tokens, retaining the position encoding for text and text tokens. This amplifies the effect of visual tokens on text generation, especially when the relative distance is longer between visual and text tokens. The proposed attention mechanism significantly reduces the chance of producing irrelevant text related to the video content. Furthermore, we present a sequential visual projector that projects the current video frame into tokens of language space with the assistance of the previous frame. This approach not only captures the temporal relationship within the video, but also allows less visual tokens to encompass the entire video. Our approach significantly outperforms various previous methods (e.g., Video-ChatGPT, MovieChat) on four challenging open-ended video question answering benchmarks. We reach an accuracy of 60.7 on the zero-shot NExT-QA and 60.5 on the zero-shot MSRVTT-QA, setting a new state-of-the-art performance. This project is available at https://jinxxian.github.io/Vista-LLaMA.
Authors: Lokesh Veeramacheneni (University of Bonn), Moritz Wolter (University of Bonn), Hildegard Kuehne (University of Tuebingen, MIT-IBM Watson AI Lab), Juergen Gall (University of Bonn, Lamarr Institute for Machine Learning,Artificial Intelligence)
Abstract: Modern metrics for generative learning like Fr\'echet Inception Distance (FID) and DINOv2-Fr\'echet Distance (FD-DINOv2) demonstrate impressive performance. However, they suffer from various shortcomings, like a bias towards specific generators and datasets. To address this problem, we propose the Fr\'echet Wavelet Distance (FWD) as a domain-agnostic metric based on the Wavelet Packet Transform ($W_p$). FWD provides a sight across a broad spectrum of frequencies in images with a high resolution, preserving both spatial and textural aspects. Specifically, we use $W_p$ to project generated and real images to the packet coefficient space. We then compute the Fr\'echet distance with the resultant coefficients to evaluate the quality of a generator. This metric is general-purpose and dataset-domain agnostic, as it does not rely on any pre-trained network, while being more interpretable due to its ability to compute Fr\'echet distance per packet, enhancing transparency. We conclude with an extensive evaluation of a wide variety of generators across various datasets that the proposed FWD can generalize and improve robustness to domain shifts and various corruptions compared to other metrics.
Authors: Binh M. Le, Jiwon Kim, Simon S. Woo, Kristen Moore, Alsharif Abuadbba, Shahroz Tariq
Abstract: Deepfakes have rapidly emerged as a serious threat to society due to their ease of creation and dissemination, triggering the accelerated development of detection technologies. However, many existing detectors rely on labgenerated datasets for validation, which may not prepare them for novel, real-world deepfakes. This paper extensively reviews and analyzes state-of-the-art deepfake detectors, evaluating them against several critical criteria. These criteria categorize detectors into 4 high-level groups and 13 finegrained sub-groups, aligned with a unified conceptual framework we propose. This classification offers practical insights into the factors affecting detector efficacy. We evaluate the generalizability of 16 leading detectors across comprehensive attack scenarios, including black-box, white-box, and graybox settings. Our systematized analysis and experiments provide a deeper understanding of deepfake detectors and their generalizability, paving the way for future research and the development of more proactive defenses against deepfakes.
Authors: Yurui Chen, Junge Zhang, Ziyang Xie, Wenye Li, Feihu Zhang, Jiachen Lu, Li Zhang
Abstract: Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety. However, traditional simulation systems, which often heavily rely on manual modeling and 2D image editing, struggled with scaling to extensive scenes and generating realistic simulation data. In this study, we present S-NeRF++, an innovative autonomous driving simulation system based on neural reconstruction. Trained on widely-used self-driving datasets such as nuScenes and Waymo, S-NeRF++ can generate a large number of realistic street scenes and foreground objects with high rendering quality as well as offering considerable flexibility in manipulation and simulation. Specifically, S-NeRF++ is an enhanced neural radiance field for synthesizing large-scale scenes and moving vehicles, with improved scene parameterization and camera pose learning. The system effectively utilizes noisy and sparse LiDAR data to refine training and address depth outliers, ensuring high-quality reconstruction and novel-view rendering. It also provides a diverse foreground asset bank by reconstructing and generating different foreground vehicles to support comprehensive scenario creation.Moreover, we have developed an advanced foreground-background fusion pipeline that skillfully integrates illumination and shadow effects, further enhancing the realism of our simulations. With the high-quality simulated data provided by our S-NeRF++, we found the perception methods enjoy performance boosts on several autonomous driving downstream tasks, further demonstrating our proposed simulator's effectiveness.
Authors: Ji Qi, Ming Ding, Weihan Wang, Yushi Bai, Qingsong Lv, Wenyi Hong, Bin Xu, Lei Hou, Juanzi Li, Yuxiao Dong, Jie Tang
Abstract: Vision-Language Models (VLMs) have demonstrated their broad effectiveness thanks to extensive training in aligning visual instructions to responses. However, such training of conclusive alignment leads models to ignore essential visual reasoning, further resulting in failures in meticulous visual problems and unfaithful responses. Drawing inspiration from human cognition in solving visual problems (e.g., marking, zoom in), this paper introduces Chain of Manipulations, a mechanism that enables VLMs to solve problems step-by-step with evidence. After training, models can solve various visual problems by eliciting intrinsic manipulations (e.g., grounding, zoom in) with results (e.g., boxes, image) actively without involving external tools, while also allowing users to trace error causes. We study the roadmap to implement this mechanism, including (1) a flexible design of manipulations upon extensive analysis, (2) an efficient automated data generation pipeline, (3) a compatible VLM architecture capable of multi-turn multi-image, and (4) a model training process for versatile capabilities. With the design, we also manually annotate 6K high-quality samples for the challenging graphical mathematical problems. Our trained model, \textbf{CogCoM}, equipped with this mechanism with 17B parameters achieves state-of-the-art performance across 9 benchmarks from 4 categories, demonstrating the effectiveness while preserving the interpretability. Our code, model weights, and collected data are publicly available at https://github.com/THUDM/CogCoM.
Authors: Zhuang Liu, Kaiming He
Abstract: We revisit the "dataset classification" experiment suggested by Torralba & Efros (2011) a decade ago, in the new era with large-scale, diverse, and hopefully less biased datasets as well as more capable neural network architectures. Surprisingly, we observe that modern neural networks can achieve excellent accuracy in classifying which dataset an image is from: e.g., we report 84.7% accuracy on held-out validation data for the three-way classification problem consisting of the YFCC, CC, and DataComp datasets. Our further experiments show that such a dataset classifier could learn semantic features that are generalizable and transferable, which cannot be explained by memorization. We hope our discovery will inspire the community to rethink issues involving dataset bias.
Authors: Hala Djeghim, Nathan Piasco, Moussab Bennehar, Luis Rold\~ao, Dzmitry Tsishkou, D\'esir\'e Sidib\'e
Abstract: Neural implicit surface representation methods have recently shown impressive 3D reconstruction results. However, existing solutions struggle to reconstruct driving scenes due to their large size, highly complex nature and their limited visual observation overlap. Hence, to achieve accurate reconstructions, additional supervision data such as LiDAR, strong geometric priors, and long training times are required. To tackle such limitations, we present ViiNeuS, a new hybrid implicit surface learning method that efficiently initializes the signed distance field to reconstruct large driving scenes from 2D street view images. ViiNeuS's hybrid architecture models two separate implicit fields: one representing the volumetric density of the scene, and another one representing the signed distance to the surface. To accurately reconstruct urban outdoor driving scenarios, we introduce a novel volume-rendering strategy that relies on self-supervised probabilistic density estimation to sample points near the surface and transition progressively from volumetric to surface representation. Our solution permits a proper and fast initialization of the signed distance field without relying on any geometric prior on the scene, compared to concurrent methods. By conducting extensive experiments on four outdoor driving datasets, we show that ViiNeuS can learn an accurate and detailed 3D surface representation of various urban scene while being two times faster to train compared to previous state-of-the-art solutions.
Authors: Ziyou Liang, Weifeng Liu, Run Wang, Mengjie Wu, Boheng Li, Yuyang Zhang, Lina Wang, Xinyi Yang
Abstract: In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In our preliminary experiments, we find that the artifacts in fake images always change with the development of the generative model, while natural images exhibit stable statistical properties. In this paper, we employ natural traces shared only by real images as an additional target for a classifier. Specifically, we introduce a self-supervised feature mapping process for natural trace extraction and develop a transfer learning based on soft contrastive loss to bring them closer to real images and further away from fake ones. This motivates the detector to make decisions based on the proximity of images to the natural traces. To conduct a comprehensive experiment, we built a high-quality and diverse dataset that includes generative models comprising GANs and diffusion models, to evaluate the effectiveness in generalizing unknown forgery techniques and robustness in surviving different transformations. Experimental results show that our proposed method gives 96.2% mAP significantly outperforms the baselines. Extensive experiments conducted on popular commercial platforms reveal that our proposed method achieves an accuracy exceeding 78.4%, underscoring its practicality for real-world application deployment.
Authors: Lingdong Kong, Xiang Xu, Jun Cen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Abstract: Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models. This study introduces Calib3D, a pioneering effort to benchmark and scrutinize the reliability of 3D scene understanding models from an uncertainty estimation viewpoint. We comprehensively evaluate 28 state-of-the-art models across 10 diverse 3D datasets, uncovering insightful phenomena that cope with both the aleatoric and epistemic uncertainties in 3D scene understanding. We discover that despite achieving impressive levels of accuracy, existing models frequently fail to provide reliable uncertainty estimates -- a pitfall that critically undermines their applicability in safety-sensitive contexts. Through extensive analysis of key factors such as network capacity, LiDAR representations, rasterization resolutions, and 3D data augmentation techniques, we correlate these aspects directly with the model calibration efficacy. Furthermore, we introduce DeptS, a novel depth-aware scaling approach aimed at enhancing 3D model calibration. Extensive experiments across a wide range of configurations validate the superiority of our method. We hope this work could serve as a cornerstone for fostering reliable 3D scene understanding. Code and benchmark toolkit are publicly available.
Authors: Isabella Liu, Hao Su, Xiaolong Wang
Abstract: Modern 3D engines and graphics pipelines require mesh as a memory-efficient representation, which allows efficient rendering, geometry processing, texture editing, and many other downstream operations. However, it is still highly difficult to obtain high-quality mesh in terms of detailed structure and time consistency from dynamic observations. To this end, we introduce Dynamic Gaussians Mesh (DG-Mesh), a framework to reconstruct a high-fidelity and time-consistent mesh from dynamic input. Our work leverages the recent advancement in 3D Gaussian Splatting to construct the mesh sequence with temporal consistency from dynamic observations. Building on top of this representation, DG-Mesh recovers high-quality meshes from the Gaussian points and can track the mesh vertices over time, which enables applications such as texture editing on dynamic objects. We introduce the Gaussian-Mesh Anchoring, which encourages evenly distributed Gaussians, resulting better mesh reconstruction through mesh-guided densification and pruning on the deformed Gaussians. By applying cycle-consistent deformation between the canonical and the deformed space, we can project the anchored Gaussian back to the canonical space and optimize Gaussians across all time frames. During the evaluation on different datasets, DG-Mesh provides significantly better mesh reconstruction and rendering than baselines. Project page: https://www.liuisabella.com/DG-Mesh
Authors: Yuying Ge, Sijie Zhao, Jinguo Zhu, Yixiao Ge, Kun Yi, Lin Song, Chen Li, Xiaohan Ding, Ying Shan
Abstract: The rapid evolution of multimodal foundation model has demonstrated significant progresses in vision-language understanding and generation, e.g., our previous work SEED-LLaMA. However, there remains a gap between its capability and the real-world applicability, primarily due to the model's limited capacity to effectively respond to various user instructions and interact with diverse visual data. In this work, we focus on bridging this gap through integrating two enhanced features: (1) comprehending images of arbitrary sizes and ratios, and (2) enabling multi-granularity image generation. We present a unified and versatile foundation model, namely, SEED-X, which is able to model multi-granularity visual semantics for comprehension and generation tasks. Besides the competitive results on public benchmarks, SEED-X demonstrates its effectiveness in handling real-world applications across various domains after instruction tuning. We hope that our work will inspire future research into what can be achieved by versatile multimodal foundation models in real-world applications. The models, codes, and datasets are released in https://github.com/AILab-CVC/SEED-X.
Authors: Merey Ramazanova, Alejandro Pardo, Bernard Ghanem, Motasem Alfarra
Abstract: Understanding videos that contain multiple modalities is crucial, especially in egocentric videos, where combining various sensory inputs significantly improves tasks like action recognition and moment localization. However, real-world applications often face challenges with incomplete modalities due to privacy concerns, efficiency needs, or hardware issues. Current methods, while effective, often necessitate retraining the model entirely to handle missing modalities, making them computationally intensive, particularly with large training datasets. In this study, we propose a novel approach to address this issue at test time without requiring retraining. We frame the problem as a test-time adaptation task, where the model adjusts to the available unlabeled data at test time. Our method, MiDl~(Mutual information with self-Distillation), encourages the model to be insensitive to the specific modality source present during testing by minimizing the mutual information between the prediction and the available modality. Additionally, we incorporate self-distillation to maintain the model's original performance when both modalities are available. MiDl represents the first self-supervised, online solution for handling missing modalities exclusively at test time. Through experiments with various pretrained models and datasets, MiDl demonstrates substantial performance improvement without the need for retraining.
Authors: Zerui Chen, Shizhe Chen, Etienne Arlaud, Ivan Laptev, Cordelia Schmid
Abstract: In this work, we aim to learn a unified vision-based policy for multi-fingered robot hands to manipulate a variety of objects in diverse poses. Though prior work has shown benefits of using human videos for policy learning, performance gains have been limited by the noise in estimated trajectories. Moreover, reliance on privileged object information such as ground-truth object states further limits the applicability in realistic scenarios. To address these limitations, we propose a new framework ViViDex to improve vision-based policy learning from human videos. It first uses reinforcement learning with trajectory guided rewards to train state-based policies for each video, obtaining both visually natural and physically plausible trajectories from the video. We then rollout successful episodes from state-based policies and train a unified visual policy without using any privileged information. We propose coordinate transformation to further enhance the visual point cloud representation, and compare behavior cloning and diffusion policy for the visual policy training. Experiments both in simulation and on the real robot demonstrate that ViViDex outperforms state-of-the-art approaches on three dexterous manipulation tasks.
Authors: Olivia Wiles, Chuhan Zhang, Isabela Albuquerque, Ivana Kaji\'c, Su Wang, Emanuele Bugliarello, Yasumasa Onoe, Chris Knutsen, Cyrus Rashtchian, Jordi Pont-Tuset, Aida Nematzadeh
Abstract: While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for collecting human judgements, the quality of these components is not systematically measured. Human-rated prompt sets are generally small and the reliability of the ratings -- and thereby the prompt set used to compare models -- is not evaluated. We address this gap by performing an extensive study evaluating auto-eval metrics and human templates. We provide three main contributions: (1) We introduce a comprehensive skills-based benchmark that can discriminate models across different human templates. This skills-based benchmark categorises prompts into sub-skills, allowing a practitioner to pinpoint not only which skills are challenging, but at what level of complexity a skill becomes challenging. (2) We gather human ratings across four templates and four T2I models for a total of >100K annotations. This allows us to understand where differences arise due to inherent ambiguity in the prompt and where they arise due to differences in metric and model quality. (3) Finally, we introduce a new QA-based auto-eval metric that is better correlated with human ratings than existing metrics for our new dataset, across different human templates, and on TIFA160.
Authors: Yufeng Yang, Adrian Kneip, Charlotte Frenkel
Abstract: Edge vision systems combining sensing and embedded processing promise low-latency, decentralized, and energy-efficient solutions that forgo reliance on the cloud. As opposed to conventional frame-based vision sensors, event-based cameras deliver a microsecond-scale temporal resolution with sparse information encoding, thereby outlining new opportunities for edge vision systems. However, mainstream algorithms for frame-based vision, which mostly rely on convolutional neural networks (CNNs), can hardly exploit the advantages of event-based vision as they are typically optimized for dense matrix-vector multiplications. While event-driven graph neural networks (GNNs) have recently emerged as a promising solution for sparse event-based vision, their irregular structure is a challenge that currently hinders the design of efficient hardware accelerators. In this paper, we propose EvGNN, the first event-driven GNN accelerator for low-footprint, ultra-low-latency, and high-accuracy edge vision with event-based cameras. It relies on three central ideas: (i) directed dynamic graphs exploiting single-hop nodes with edge-free storage, (ii) event queues for the efficient identification of local neighbors within a spatiotemporally decoupled search range, and (iii) a novel layer-parallel processing scheme allowing for a low-latency execution of multi-layer GNNs. We deployed EvGNN on a Xilinx KV260 Ultrascale+ MPSoC platform and benchmarked it on the N-CARS dataset for car recognition, demonstrating a classification accuracy of 87.8% and an average latency per event of 16$\mu$s, thereby enabling real-time, microsecond-resolution event-based vision at the edge.
Authors: Chenying Liu, Conrad Albrecht, Yi Wang, Xiao Xiang Zhu
Abstract: We explore the potential of large-scale noisily labeled data to enhance feature learning by pretraining semantic segmentation models within a multi-modal framework for geospatial applications. We propose a novel Cross-modal Sample Selection (CromSS) method, a weakly supervised pretraining strategy designed to improve feature representations through cross-modal consistency and noise mitigation techniques. Unlike conventional pretraining approaches, CromSS exploits massive amounts of noisy and easy-to-come-by labels for improved feature learning beneficial to semantic segmentation tasks. We investigate middle and late fusion strategies to optimize the multi-modal pretraining architecture design. We also introduce a cross-modal sample selection module to mitigate the adverse effects of label noise, which employs a cross-modal entangling strategy to refine the estimated confidence masks within each modality to guide the sampling process. Additionally, we introduce a spatial-temporal label smoothing technique to counteract overconfidence for enhanced robustness against noisy labels. To validate our approach, we assembled the multi-modal dataset, NoLDO-S12, which consists of a large-scale noisy label subset from Google's Dynamic World (DW) dataset for pretraining and two downstream subsets with high-quality labels from Google DW and OpenStreetMap (OSM) for transfer learning. Experimental results on two downstream tasks and the publicly available DFC2020 dataset demonstrate that when effectively utilized, the low-cost noisy labels can significantly enhance feature learning for segmentation tasks. All data, code, and pretrained weights will be made publicly available.
Authors: Yuanye Liu, Zheyao Gao, Nannan Shi, Fuping Wu, Yuxin Shi, Qingchao Chen, Xiahai Zhuang
Abstract: Accurate staging of liver fibrosis from magnetic resonance imaging (MRI) is crucial in clinical practice. While conventional methods often focus on a specific sub-region, multi-view learning captures more information by analyzing multiple patches simultaneously. However, previous multi-view approaches could not typically calculate uncertainty by nature, and they generally integrate features from different views in a black-box fashion, hence compromising reliability as well as interpretability of the resulting models. In this work, we propose a new multi-view method based on evidential learning, referred to as MERIT, which tackles the two challenges in a unified framework. MERIT enables uncertainty quantification of the predictions to enhance reliability, and employs a logic-based combination rule to improve interpretability. Specifically, MERIT models the prediction from each sub-view as an opinion with quantified uncertainty under the guidance of the subjective logic theory. Furthermore, a distribution-aware base rate is introduced to enhance performance, particularly in scenarios involving class distribution shifts. Finally, MERIT adopts a feature-specific combination rule to explicitly fuse multi-view predictions, thereby enhancing interpretability. Results have showcased the effectiveness of the proposed MERIT, highlighting the reliability and offering both ad-hoc and post-hoc interpretability. They also illustrate that MERIT can elucidate the significance of each view in the decision-making process for liver fibrosis staging. Our code has be released via https://github.com/HenryLau7/MERIT.
Authors: Yuzhong Zhao, Feng Liu, Yue Liu, Mingxiang Liao, Chen Gong, Qixiang Ye, Fang Wan
Abstract: One fundamental task of multimodal models is to translate referred image regions to human preferred language descriptions. Existing methods, however, ignore the resolution adaptability needs of different tasks, which hinders them to find out precise language descriptions. In this study, we propose a DynRefer approach, to pursue high-accuracy region-level referring through mimicking the resolution adaptability of human visual cognition. During training, DynRefer stochastically aligns language descriptions of multimodal tasks with images of multiple resolutions, which are constructed by nesting a set of random views around the referred region. During inference, DynRefer performs selectively multimodal referring by sampling proper region representations for tasks from the nested views based on image and task priors. This allows the visual information for referring to better match human preferences, thereby improving the representational adaptability of region-level multimodal models. Experiments show that DynRefer brings mutual improvement upon broad tasks including region-level captioning, open-vocabulary region recognition and attribute detection. Furthermore, DynRefer achieves state-of-the-art results on multiple region-level multimodal tasks using a single model. Code is available at https://github.com/callsys/DynRefer.
Authors: Jingwei Xu, Yikai Wang, Yiqun Zhao, Yanwei Fu, Shenghua Gao
Abstract: Unveiling an empty street from crowded observations captured by in-car cameras is crucial for autonomous driving. However, removing all temporarily static objects, such as stopped vehicles and standing pedestrians, presents a significant challenge. Unlike object-centric 3D inpainting, which relies on thorough observation in a small scene, street scene cases involve long trajectories that differ from previous 3D inpainting tasks. The camera-centric moving environment of captured videos further complicates the task due to the limited degree and time duration of object observation. To address these obstacles, we introduce StreetUnveiler to reconstruct an empty street. StreetUnveiler learns a 3D representation of the empty street from crowded observations. Our representation is based on the hard-label semantic 2D Gaussian Splatting (2DGS) for its scalability and ability to identify Gaussians to be removed. We inpaint rendered image after removing unwanted Gaussians to provide pseudo-labels and subsequently re-optimize the 2DGS. Given its temporal continuous movement, we divide the empty street scene into observed, partial-observed, and unobserved regions, which we propose to locate through a rendered alpha map. This decomposition helps us to minimize the regions that need to be inpainted. To enhance the temporal consistency of the inpainting, we introduce a novel time-reversal framework to inpaint frames in reverse order and use later frames as references for earlier frames to fully utilize the long-trajectory observations. Our experiments conducted on the street scene dataset successfully reconstructed a 3D representation of the empty street. The mesh representation of the empty street can be extracted for further applications. The project page and more visualizations can be found at: https://streetunveiler.github.io
Authors: Jingyun Xue, Hongfa Wang, Qi Tian, Yue Ma, Andong Wang, Zhiyuan Zhao, Shaobo Min, Wenzhe Zhao, Kaihao Zhang, Heung-Yeung Shum, Wei Liu, Mengyang Liu, Wenhan Luo
Abstract: Controllable character image animation has a wide range of applications. Although existing studies have consistently improved performance, challenges persist in the field of character image animation, particularly concerning stability in complex backgrounds and tasks involving multiple characters. To address these challenges, we propose a novel multi-condition guided framework for character image animation, employing several well-designed input modules to enhance the implicit decoupling capability of the model. First, the optical flow guider calculates the background optical flow map as guidance information, which enables the model to implicitly learn to decouple the background motion into background constants and background momentum during training, and generate a stable background by setting zero background momentum during inference. Second, the depth order guider calculates the order map of the characters, which transforms the depth information into the positional information of multiple characters. This facilitates the implicit learning of decoupling different characters, especially in accurately separating the occluded body parts of multiple characters. Third, the reference pose map is input to enhance the ability to decouple character texture and pose information in the reference image. Furthermore, to fill the gap of fair evaluation of multi-character image animation, we propose a new benchmark comprising about 4,000 frames. Extensive qualitative and quantitative evaluations demonstrate that our method excels in generating high-quality character animations, especially in scenarios of complex backgrounds and multiple characters.
Authors: Yulong Yang, Felix O'Mahony, Christine Allen-Blanchette
Abstract: In this paper, we introduce group convolutional neural networks (GCNNs) equivariant to color variation. GCNNs have been designed for a variety of geometric transformations from 2D and 3D rotation groups, to semi-groups such as scale. Despite the improved interpretability, accuracy and generalizability of these architectures, GCNNs have seen limited application in the context of perceptual quantities. Notably, the recent CEConv network uses a GCNN to achieve equivariance to hue transformations by convolving input images with a hue rotated RGB filter. However, this approach leads to invalid RGB values which break equivariance and degrade performance. We resolve these issues with a lifting layer that transforms the input image directly, thereby circumventing the issue of invalid RGB values and improving equivariance error by over three orders of magnitude. Moreover, we extend the notion of color equivariance to include equivariance to saturation and luminance shift. Our hue-, saturation-, luminance- and color-equivariant networks achieve strong generalization to out-of-distribution perceptual variations and improved sample efficiency over conventional architectures. We demonstrate the utility of our approach on synthetic and real world datasets where we consistently outperform competitive baselines.
Authors: Xubing Ye, Yukang Gan, Xiaoke Huang, Yixiao Ge, Yansong Tang
Abstract: Vision-Language Models (VLMs) have achieved remarkable success in various multi-modal tasks, but they are often bottlenecked by the limited context window and high computational cost of processing high-resolution image inputs and videos. Vision compression can alleviate this problem by reducing the vision token count. Previous approaches compress vision tokens with external modules and force LLMs to understand the compressed ones, leading to visual information loss. However, the LLMs' understanding paradigm of vision tokens is not fully utilised in the compression learning process. We propose VoCo-LLaMA, the first approach to compress vision tokens using LLMs. By introducing Vision Compression tokens during the vision instruction tuning phase and leveraging attention distillation, our method distill how LLMs comprehend vision tokens into their processing of VoCo tokens. VoCo-LLaMA facilitates effective vision compression and improves the computational efficiency during the inference stage. Specifically, our method achieves minimal performance loss with a compression ratio of 576$\times$, resulting in up to 94.8$\%$ fewer FLOPs and 69.6$\%$ acceleration in inference time. Furthermore, through continuous training using time-series compressed token sequences of video frames, VoCo-LLaMA demonstrates the ability to understand temporal correlations, outperforming previous methods on popular video question-answering benchmarks. Our approach presents a promising way to unlock the full potential of VLMs' contextual window, enabling more scalable multi-modal applications. The project page, along with the associated code, can be accessed via https://yxxxb.github.io/VoCo-LLaMA-page/.
Authors: Haodong Duan, Xinyu Fang, Junming Yang, Xiangyu Zhao, Yuxuan Qiao, Mo Li, Amit Agarwal, Zhe Chen, Lin Chen, Yuan Liu, Yubo Ma, Hailong Sun, Yifan Zhang, Shiyin Lu, Tack Hwa Wong, Weiyun Wang, Peiheng Zhou, Xiaozhe Li, Chaoyou Fu, Junbo Cui, Xiaoyi Dong, Yuhang Zang, Pan Zhang, Jiaqi Wang, Dahua Lin, Kai Chen
Abstract: We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friendly and comprehensive framework for researchers and developers to evaluate existing multi-modality models and publish reproducible evaluation results. In VLMEvalKit, we implement over 70 different large multi-modality models, including both proprietary APIs and open-source models, as well as more than 20 different multi-modal benchmarks. By implementing a single interface, new models can be easily added to the toolkit, while the toolkit automatically handles the remaining workloads, including data preparation, distributed inference, prediction post-processing, and metric calculation. Although the toolkit is currently mainly used for evaluating large vision-language models, its design is compatible with future updates that incorporate additional modalities, such as audio and video. Based on the evaluation results obtained with the toolkit, we host OpenVLM Leaderboard, a comprehensive leaderboard to track the progress of multi-modality learning research. The toolkit is released at https://github.com/open-compass/VLMEvalKit and is actively maintained.
Authors: Amir Mohammad Karimi Mamaghan, Samuele Papa, Karl Henrik Johansson, Stefan Bauer, Andrea Dittadi
Abstract: Object-centric (OC) representations, which model visual scenes as compositions of discrete objects, have the potential to be used in various downstream tasks to achieve systematic compositional generalization and facilitate reasoning. However, these claims have yet to be thoroughly validated empirically. Recently, foundation models have demonstrated unparalleled capabilities across diverse domains, from language to computer vision, positioning them as a potential cornerstone of future research for a wide range of computational tasks. In this paper, we conduct an extensive empirical study on representation learning for downstream Visual Question Answering (VQA), which requires an accurate compositional understanding of the scene. We thoroughly investigate the benefits and trade-offs of OC models and alternative approaches including large pre-trained foundation models on both synthetic and real-world data, ultimately identifying a promising path to leverage the strengths of both paradigms. The extensiveness of our study, encompassing over 600 downstream VQA models and 15 different types of upstream representations, also provides several additional insights that we believe will be of interest to the community at large.
Authors: Yike Zhang, Eduardo Davalos, Dingjie Su, Ange Lou, Jack H. Noble
Abstract: Cochlear Implant (CI) procedures require the insertion of an electrode array into the cochlea within the inner ear. To achieve this, mastoidectomy, a surgical procedure involving the removal of part of the mastoid region of the temporal bone using a high-speed drill provides safe access to the cochlea through the middle and inner ear. In this paper, we propose a novel Mamba-based method to synthesize the mastoidectomy volume using only preoperative Computed Tomography (CT) scans, where the mastoid remains intact. Our approach introduces a self-supervised learning framework designed to predict the mastoidectomy shape and reconstruct a 3D post-mastoidectomy surface directly from preoperative CT scans. This reconstruction aligns with intraoperative microscope views, enabling various downstream surgical applications. For training, we leverage postoperative CT scans to bypass manual data cleaning and labeling, even when the region removed during mastoidectomy is affected by challenges such as metal artifacts, low signal-to-noise ratio, or electrode wiring. Our method achieves a mean Dice score of 0.70 in estimating mastoidectomy regions, demonstrating its effectiveness for accurate and efficient surgical preoperative planning.
Authors: Danfeng Guo, Demetri Terzopoulos
Abstract: Large Vision-Language Models (LVLMs) have achieved significant success in recent years, and they have been extended to the medical domain. Although demonstrating satisfactory performance on medical Visual Question Answering (VQA) tasks, Medical LVLMs (MLVLMs) suffer from the hallucination problem, which makes them fail to diagnose complex pathologies. Moreover, they readily fail to learn minority pathologies due to imbalanced training data. We propose two prompting strategies for MLVLMs that reduce hallucination and improve VQA performance. In the first strategy, we provide a detailed explanation of the queried pathology. In the second strategy, we fine-tune a cheap, weak learner to achieve high performance on a specific metric, and textually provide its judgment to the MLVLM. Tested on the MIMIC-CXR-JPG and Chexpert datasets, our methods significantly improve the diagnostic F1 score, with the highest increase being 0.27. We also demonstrate that our prompting strategies can be extended to general LVLM domains. Based on POPE metrics, it effectively suppresses the false negative predictions of existing LVLMs and improves Recall by approximately 0.07.
Authors: Hongjun Wang, Sagar Vaze, Kai Han
Abstract: Generalized Category Discovery (GCD) is a challenging task in which, given a partially labelled dataset, models must categorize all unlabelled instances, regardless of whether they come from labelled categories or from new ones. In this paper, we challenge a remaining assumption in this task: that all images share the same domain. Specifically, we introduce a new task and method to handle GCD when the unlabelled data also contains images from different domains to the labelled set. Our proposed `HiLo' networks extract High-level semantic and Low-level domain features, before minimizing the mutual information between the representations. Our intuition is that the clusterings based on domain information and semantic information should be independent. We further extend our method with a specialized domain augmentation tailored for the GCD task, as well as a curriculum learning approach. Finally, we construct a benchmark from corrupted fine-grained datasets as well as a large-scale evaluation on DomainNet with real-world domain shifts, reimplementing a number of GCD baselines in this setting. We demonstrate that HiLo outperforms SoTA category discovery models by a large margin on all evaluations.
Authors: Hossein Jafarinia, Alireza Alipanah, Danial Hamdi, Saeed Razavi, Nahal Mirzaie, Mohammad Hossein Rohban
Abstract: Whole Slide Image (WSI) classification with multiple instance learning (MIL) in digital pathology faces significant computational challenges. Current methods mostly rely on extensive self-supervised learning (SSL) for satisfactory performance, requiring long training periods and considerable computational resources. At the same time, no pre-training affects performance due to domain shifts from natural images to WSIs. We introduce Snuffy architecture, a novel MIL-pooling method based on sparse transformers that mitigates performance loss with limited pre-training and enables continual few-shot pre-training as a competitive option. Our sparsity pattern is tailored for pathology and is theoretically proven to be a universal approximator with the tightest probabilistic sharp bound on the number of layers for sparse transformers, to date. We demonstrate Snuffy's effectiveness on CAMELYON16 and TCGA Lung cancer datasets, achieving superior WSI and patch-level accuracies. The code is available on https://github.com/jafarinia/snuffy.
Authors: Zhangquan Chen, Puhua Jiang, Ruqi Huang
Abstract: In this paper, we present DV-Matcher, a novel learning-based framework for estimating dense correspondences between non-rigidly deformable point clouds. Learning directly from unstructured point clouds without meshing or manual labelling, our framework delivers high-quality dense correspondences, which is of significant practical utility in point cloud processing. Our key contributions are two-fold: First, we propose a scheme to inject prior knowledge from pre-trained vision models into geometric feature learning, which effectively complements the local nature of geometric features with global and semantic information; Second, we propose a novel deformation-based module to promote the extrinsic alignment induced by the learned correspondences, which effectively enhances the feature learning. Experimental results show that our method achieves state-of-the-art results in matching non-rigid point clouds in both near-isometric and heterogeneous shape collection as well as more realistic partial and noisy data.
Authors: Sihan Yang, Xuande Mi, Jiadong Feng, Haixia Bi, Hai Zhang, Jian Sun
Abstract: Large foundation models, known for their strong zero-shot generalization capabilities, can be applied to a wide range of downstream tasks. However, developing foundation models for medical image segmentation poses a significant challenge due to the domain gap between natural and medical images. While fine-tuning techniques based on the Segment Anything Model (SAM) have been explored, they primarily focus on scaling up data or refining inference strategies without incorporating domain-specific architectural designs, limiting their zero-shot performance. To optimize segmentation performance under standard inference settings and provide a strong baseline for future research, we introduce SyncSAM, which employs a synchronized dual-branch encoder that integrates convolution and Transformer features in a synchronized manner to enhance medical image encoding, and a multi-scale dual-branch decoder to preserve image details. SyncSAM is trained on two of the largest medical image segmentation datasets, SA-Med2D-20M and IMed-361M, resulting in a series of pre-trained models for universal medical image segmentation. Experimental results demonstrate that SyncSAM not only achieves state-of-the-art performance on test sets but also exhibits strong zero-shot capabilities on unseen datasets. The code and model weights are available at https://github.com/Hhankyangg/SyncSAM.
Authors: Changkun Liu, Shuai Chen, Yash Bhalgat, Siyan Hu, Ming Cheng, Zirui Wang, Victor Adrian Prisacariu, Tristan Braud
Abstract: We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localization accuracy of state-of-the-art absolute pose regression and scene coordinate regression methods. The 3DGS model renders high-quality synthetic images and depth maps to facilitate the establishment of 2D-3D correspondences. GS-CPR obviates the need for training feature extractors or descriptors by operating directly on RGB images, utilizing the 3D foundation model, MASt3R, for precise 2D matching. To improve the robustness of our model in challenging outdoor environments, we incorporate an exposure-adaptive module within the 3DGS framework. Consequently, GS-CPR enables efficient one-shot pose refinement given a single RGB query and a coarse initial pose estimation. Our proposed approach surpasses leading NeRF-based optimization methods in both accuracy and runtime across indoor and outdoor visual localization benchmarks, achieving new state-of-the-art accuracy on two indoor datasets. The project page is available at https://xrim-lab.github.io/GS-CPR/.
Authors: Muhammad Aqeel, Shakiba Sharifi, Marco Cristani, Francesco Setti
Abstract: This study introduces the Iterative Refinement Process (IRP), a robust anomaly detection methodology designed for high-stakes industrial quality control. The IRP enhances defect detection accuracy through a cyclic data refinement strategy, iteratively removing misleading data points to improve model performance and robustness. We validate the IRP's effectiveness using two benchmark datasets, Kolektor SDD2 (KSDD2) and MVTec AD, covering a wide range of industrial products and defect types. Our experimental results demonstrate that the IRP consistently outperforms traditional anomaly detection models, particularly in environments with high noise levels. This study highlights the IRP's potential to significantly enhance anomaly detection processes in industrial settings, effectively managing the challenges of sparse and noisy data.
Authors: Min Shi, Fuxiao Liu, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, Yilin Zhao, De-An Huang, Hongxu Yin, Karan Sapra, Yaser Yacoob, Humphrey Shi, Bryan Catanzaro, Andrew Tao, Jan Kautz, Zhiding Yu, Guilin Liu
Abstract: The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves performance on resolution-sensitive tasks, such as optical character recognition and document analysis. A number of recent MLLMs achieve this goal using a mixture of vision encoders. Despite their success, there is a lack of systematic comparisons and detailed ablation studies addressing critical aspects, such as expert selection and the integration of multiple vision experts. This study provides an extensive exploration of the design space for MLLMs using a mixture of vision encoders and resolutions. Our findings reveal several underlying principles common to various existing strategies, leading to a streamlined yet effective design approach. We discover that simply concatenating visual tokens from a set of complementary vision encoders is as effective as more complex mixing architectures or strategies. We additionally introduce Pre-Alignment to bridge the gap between vision-focused encoders and language tokens, enhancing model coherence. The resulting family of MLLMs, Eagle, surpasses other leading open-source models on major MLLM benchmarks.
Authors: Yang Zhang, Rui Zhang, Xuecheng Nie, Haochen Li, Jikun Chen, Yifan Hao, Xin Zhang, Luoqi Liu, Ling Li
Abstract: Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain multiple characters or objects, existing methods often suffer from semantic entanglement, including concept entanglement and improper attribute binding, leading to significant text-image inconsistency. We identify that semantic entanglement arises when certain regions of the latent features attend to incorrect concept and attribute tokens. In this work, we propose the Semantic Protection Diffusion Model (SPDiffusion) to address both concept entanglement and improper attribute binding using only a text prompt as input. The SPDiffusion framework introduces a novel concept region extraction method SP-Extraction to resolve region entanglement in cross-attention, along with SP-Attn, which protects concept regions from the influence of irrelevant attributes and concepts. To evaluate our method, we test it on existing benchmarks, where SPDiffusion achieves state-of-the-art results, demonstrating its effectiveness.
Authors: Yike Zhang, Jack Noble
Abstract: Cochlear Implant (CI) procedures involve performing an invasive mastoidectomy to insert an electrode array into the cochlea. In this paper, we introduce a novel pipeline that is capable of generating synthetic multi-view videos from a single CI microscope image. In our approach, we use a patient's pre-operative CT scan to predict the post-mastoidectomy surface using a method designed for this purpose. We manually align the surface with a selected microscope frame to obtain an accurate initial pose of the reconstructed CT mesh relative to the microscope. We then perform UV projection to transfer the colors from the frame to surface textures. Novel views of the textured surface can be used to generate a large dataset of synthetic frames with ground truth poses. We evaluated the quality of synthetic views rendered using Pytorch3D and PyVista. We found both rendering engines lead to similarly high-quality synthetic novel-view frames compared to ground truth with a structural similarity index for both methods averaging about 0.86. A large dataset of novel views with known poses is critical for ongoing training of a method to automatically estimate microscope pose for 2D to 3D registration with the pre-operative CT to facilitate augmented reality surgery. This dataset will empower various downstream tasks, such as integrating Augmented Reality (AR) in the OR, tracking surgical tools, and supporting other video analysis studies.
Authors: Keyne Oei, Amr Gomaa, Anna Maria Feit, Jo\~ao Belo
Abstract: Robust frame-wise embeddings are essential to perform video analysis and understanding tasks. We present a self-supervised method for representation learning based on aligning temporal video sequences. Our framework uses a transformer-based encoder to extract frame-level features and leverages them to find the optimal alignment path between video sequences. We introduce the novel Local-Alignment Contrastive (LAC) loss, which combines a differentiable local alignment loss to capture local temporal dependencies with a contrastive loss to enhance discriminative learning. Prior works on video alignment have focused on using global temporal ordering across sequence pairs, whereas our loss encourages identifying the best-scoring subsequence alignment. LAC uses the differentiable Smith-Waterman (SW) affine method, which features a flexible parameterization learned through the training phase, enabling the model to adjust the temporal gap penalty length dynamically. Evaluations show that our learned representations outperform existing state-of-the-art approaches on action recognition tasks.
Authors: Jaewoo Kim, Uehwan Kim
Abstract: While current state-of-the-art Scene Change Detection (SCD) approaches achieve impressive results in well-trained research data, they become unreliable under unseen environments and different temporal conditions; in-domain performance drops from 77.6\% to 8.0\% in a previously unseen environment and to 4.6\% under a different temporal condition -- calling for generalizable SCD and benchmark. In this work, we propose the Generalizable Scene Change Detection Framework (GeSCF), which addresses unseen domain performance and temporal consistency -- to meet the growing demand for anything SCD. Our method leverages the pre-trained Segment Anything Model (SAM) in a zero-shot manner. For this, we design Initial Pseudo-mask Generation and Geometric-Semantic Mask Matching -- seamlessly turning user-guided prompt and single-image based segmentation into scene change detection for a pair of inputs without guidance. Furthermore, we define the Generalizable Scene Change Detection (GeSCD) benchmark along with novel metrics and an evaluation protocol to facilitate SCD research in generalizability. In the process, we introduce the ChangeVPR dataset, a collection of challenging image pairs with diverse environmental scenarios -- including urban, suburban, and rural settings. Extensive experiments across various datasets demonstrate that GeSCF achieves an average performance gain of 19.2\% on existing SCD datasets and 30.0\% on the ChangeVPR dataset, nearly doubling the prior art performance. We believe our work can lay a solid foundation for robust and generalizable SCD research.
Authors: Boming Miao, Chunxiao Li, Yao Zhu, Weixiang Sun, Zizhe Wang, Xiaoyi Wang, Chuanlong Xie
Abstract: With the rapid development of deep learning, object detectors have demonstrated impressive performance; however, vulnerabilities still exist in certain scenarios. Current research exploring the vulnerabilities using adversarial patches often struggles to balance the trade-off between attack effectiveness and visual quality. To address this problem, we propose a novel framework of patch attack from semantic perspective, which we refer to as AdvLogo. Based on the hypothesis that every semantic space contains an adversarial subspace where images can cause detectors to fail in recognizing objects, we leverage the semantic understanding of the diffusion denoising process and drive the process to adversarial subareas by perturbing the latent and unconditional embeddings at the last timestep. To mitigate the distribution shift that exposes a negative impact on image quality, we apply perturbation to the latent in frequency domain with the Fourier Transform. Experimental results demonstrate that AdvLogo achieves strong attack performance while maintaining high visual quality.
Authors: Meng Chen, Jiawei Tu, Chao Qi, Yonghao Dang, Feng Zhou, Wei Wei, Jianqin Yin
Abstract: The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the adversarial robustness of embodied vision navigation is crucial, especially given the threat of 3D physical attacks that could pose risks to human safety. However, existing attack methods for embodied vision navigation often lack physical feasibility due to challenges in transferring digital perturbations into the physical world. Moreover, current physical attacks for object detection struggle to achieve both multi-view effectiveness and visual naturalness in navigation scenarios. To address this, we propose a practical attack method for embodied navigation by attaching adversarial patches to objects, where both opacity and textures are learnable. Specifically, to ensure effectiveness across varying viewpoints, we employ a multi-view optimization strategy based on object-aware sampling, which optimizes the patch's texture based on feedback from the vision-based perception model used in navigation. To make the patch inconspicuous to human observers, we introduce a two-stage opacity optimization mechanism, in which opacity is fine-tuned after texture optimization. Experimental results demonstrate that our adversarial patches decrease the navigation success rate by an average of 22.39%, outperforming previous methods in practicality, effectiveness, and naturalness. Code is available at: https://github.com/chen37058/Physical-Attacks-in-Embodied-Nav
URLs: https://github.com/chen37058/Physical-Attacks-in-Embodied-Nav
Authors: Tianqi Chen, Shujian Zhang, Mingyuan Zhou
Abstract: The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as a crucial foundation for developing safe, secure, and trustworthy GenAI models. Traditional MU methods often rely on stringent assumptions and require access to real data. This paper introduces Score Forgetting Distillation (SFD), an innovative MU approach that promotes the forgetting of undesirable information in diffusion models by aligning the conditional scores of "unsafe" classes or concepts with those of "safe" ones. To eliminate the need for real data, our SFD framework incorporates a score-based MU loss into the score distillation objective of a pretrained diffusion model. This serves as a regularization term that preserves desired generation capabilities while enabling the production of synthetic data through a one-step generator. Our experiments on pretrained label-conditional and text-to-image diffusion models demonstrate that our method effectively accelerates the forgetting of target classes or concepts during generation, while preserving the quality of other classes or concepts. This unlearned and distilled diffusion not only pioneers a novel concept in MU but also accelerates the generation speed of diffusion models. Our experiments and studies on a range of diffusion models and datasets confirm that our approach is generalizable, effective, and advantageous for MU in diffusion models. Code is available at https://github.com/tqch/score-forgetting-distillation. ($\textbf{Warning:}$ This paper contains sexually explicit imagery, discussions of pornography, racially-charged terminology, and other content that some readers may find disturbing, distressing, and/or offensive.)
URLs: https://github.com/tqch/score-forgetting-distillation.
Authors: Yi Yang, Lei Zhong, Huiping Zhuang
Abstract: We introduce a novel Recursive Fusion model, dubbed ReFu, designed to integrate point clouds and meshes for exemplar-free 3D Class-Incremental Learning, where the model learns new 3D classes while retaining knowledge of previously learned ones. Unlike existing methods that either rely on storing historical data to mitigate forgetting or focus on single data modalities, ReFu eliminates the need for exemplar storage while utilizing the complementary strengths of both point clouds and meshes. To achieve this, we introduce a recursive method which continuously accumulates knowledge by updating the regularized auto-correlation matrix. Furthermore, we propose a fusion module, featuring a Pointcloud-guided Mesh Attention Layer that learns correlations between the two modalities. This mechanism effectively integrates point cloud and mesh features, leading to more robust and stable continual learning. Experiments across various datasets demonstrate that our proposed framework outperforms existing methods in 3D class-incremental learning.
Authors: Vladimir Guzov, Yifeng Jiang, Fangzhou Hong, Gerard Pons-Moll, Richard Newcombe, C. Karen Liu, Yuting Ye, Lingni Ma
Abstract: This paper investigates the generation of realistic full-body human motion using a single head-mounted device with an outward-facing color camera and the ability to perform visual SLAM. To address the ambiguity of this setup, we present HMD^2, a novel system that balances motion reconstruction and generation. From a reconstruction standpoint, it aims to maximally utilize the camera streams to produce both analytical and learned features, including head motion, SLAM point cloud, and image embeddings. On the generative front, HMD^2 employs a multi-modal conditional motion diffusion model with a Transformer backbone to maintain temporal coherence of generated motions, and utilizes autoregressive inpainting to facilitate online motion inference with minimal latency (0.17 seconds). We show that our system provides an effective and robust solution that scales to a diverse dataset of over 200 hours of motion in complex indoor and outdoor environments.
Authors: Shilong Yang, Chulong Zhang, Qi Zang, Juan Yu, Liang Zeng, Xiao Luo, Yexuan Xing, Xin Pan, Qi Li, Xiaokun Liang, Yaoqin Xie
Abstract: Breast cancer is a significant global health issue, and the diagnosis of breast imaging has always been challenging. Mammography images typically have extremely high resolution, with lesions occupying only a very small area. Down-sampling in neural networks can easily lead to the loss of microcalcifications or subtle structures, making it difficult for traditional neural network architectures to address these issues. To tackle these challenges, we propose a Context Clustering Network with triple information fusion. Firstly, compared to CNNs or transformers, we find that Context clustering methods (1) are more computationally efficient and (2) can more easily associate structural or pathological features, making them suitable for the clinical tasks of mammography. Secondly, we propose a triple information fusion mechanism that integrates global information, feature-based local information, and patch-based local information. The proposed approach is rigorously evaluated on two public datasets, Vindr-Mammo and CBIS-DDSM, using five independent splits to ensure statistical robustness. Our method achieves an AUC of 0.828 on Vindr-Mammo and 0.805 on CBIS-DDSM, outperforming the next best method by 3.1% and 2.4%, respectively. These improvements are statistically significant (p<0.05), underscoring the benefits of Context Clustering Network with triple information fusion. Overall, our Context Clustering framework demonstrates strong potential as a scalable and cost-effective solution for large-scale mammography screening, enabling more efficient and accurate breast cancer detection. Access to our method is available at https://github.com/Sohyu1/Mammo_Clustering.
Authors: Yuanhang Li, Qi Mao, Lan Chen, Zhen Fang, Lei Tian, Xinyan Xiao, Libiao Jin, Hua Wu
Abstract: Recent advances in text-to-video (T2V) generation with diffusion models have garnered significant attention. However, they typically perform well in scenes with a single object and motion, struggling in compositional scenarios with multiple objects and distinct motions to accurately reflect the semantic content of text prompts. To address these challenges, we propose \textbf{StarVid}, a plug-and-play, training-free method that improves semantic alignment between multiple subjects, their motions, and text prompts in T2V models. StarVid first leverages the spatial reasoning capabilities of large language models (LLMs) for two-stage motion trajectory planning based on text prompts. Such trajectories serve as spatial priors, guiding a spatial-aware loss to refocus cross-attention (CA) maps into distinctive regions. Furthermore, we propose a syntax-guided contrastive constraint to strengthen the correlation between the CA maps of verbs and their corresponding nouns, enhancing motion-subject binding. Both qualitative and quantitative evaluations demonstrate that the proposed framework significantly outperforms baseline methods, delivering videos of higher quality with improved semantic consistency.
Authors: Maximilian Weiherer, Bernhard Egger
Abstract: We propose to use the family of Mat\'ern kernels for implicit surface reconstruction, building upon the recent success of kernel methods for 3D reconstruction of oriented point clouds. As we show from a theoretical and practical perspective, Mat\'ern kernels have some appealing properties which make them particularly well suited for surface reconstruction -- outperforming state-of-the-art methods based on the arc-cosine kernel while being significantly easier to implement, faster to compute, and scalable. Being stationary, we demonstrate that Mat\'ern kernels allow for tunable surface reconstruction in the same way as Fourier feature mappings help coordinate-based MLPs overcome spectral bias. Moreover, we theoretically analyze Mat\'ern kernels' connection to SIREN networks as well as their relation to previously employed arc-cosine kernels. Finally, based on recently introduced Neural Kernel Fields, we present data-dependent Mat\'ern kernels and conclude that especially the Laplace kernel (being part of the Mat\'ern family) is extremely competitive, performing almost on par with state-of-the-art methods in the noise-free case while having a more than five times shorter training time.
Authors: Peidong Li, Dixiao Cui
Abstract: End-to-End Autonomous Driving (E2EAD) methods typically rely on supervised perception tasks to extract explicit scene information (e.g., objects, maps). This reliance necessitates expensive annotations and constrains deployment and data scalability in real-time applications. In this paper, we introduce SSR, a novel framework that utilizes only 16 navigation-guided tokens as Sparse Scene Representation, efficiently extracting crucial scene information for E2EAD. Our method eliminates the need for human-designed supervised sub-tasks, allowing computational resources to concentrate on essential elements directly related to navigation intent. We further introduce a temporal enhancement module, aligning predicted future scenes with actual future scenes through self-supervision. SSR achieves a 27.2\% relative reduction in L2 error and a 51.6\% decrease in collision rate to UniAD in nuScenes, with a 10.9$\times$ faster inference speed and 13$\times$ faster training time. Moreover, SSR outperforms VAD-Base with a 48.6-point improvement on driving score in CARLA's Town05 Long benchmark. This framework represents a significant leap in real-time autonomous driving systems and paves the way for future scalable deployment. Code is available at https://github.com/PeidongLi/SSR.
Authors: Yuki Imajuku, Yoko Yamakata, Kiyoharu Aizawa
Abstract: Research on food image understanding using recipe data has been a long-standing focus due to the diversity and complexity of the data. Moreover, food is inextricably linked to people's lives, making it a vital research area for practical applications such as dietary management. Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities, not only in their vast knowledge but also in their ability to handle languages naturally. While English is predominantly used, they can also support multiple languages including Japanese. This suggests that MLLMs are expected to significantly improve performance in food image understanding tasks. We fine-tuned open MLLMs LLaVA-1.5 and Phi-3 Vision on a Japanese recipe dataset and benchmarked their performance against the closed model GPT-4o. We then evaluated the content of generated recipes, including ingredients and cooking procedures, using 5,000 evaluation samples that comprehensively cover Japanese food culture. Our evaluation demonstrates that the open models trained on recipe data outperform GPT-4o, the current state-of-the-art model, in ingredient generation. Our model achieved F1 score of 0.531, surpassing GPT-4o's F1 score of 0.481, indicating a higher level of accuracy. Furthermore, our model exhibited comparable performance to GPT-4o in generating cooking procedure text.
Authors: Chen Hu, Yian Huang, Kexuan Li, Luping Zhang, Chang Long, Yiming Zhu, Tian Pu, Zhenming Peng
Abstract: Infrared small target detection (ISTD) is widely used in civilian and military applications. However, ISTD encounters several challenges, including the tendency for small and dim targets to be obscured by complex backgrounds. To address this issue, we propose the Dynamic Attention Transformer Network (DATransNet), which aims to extract and preserve detailed information vital for small targets. DATransNet employs the Dynamic Attention Transformer (DATrans), simulating central difference convolutions (CDC) to extract gradient features. Furthermore, we propose a global feature extraction module (GFEM) that offers a comprehensive perspective to prevent the network from focusing solely on details while neglecting the global information. We compare the network with state-of-the-art (SOTA) approaches and demonstrate that our method performs effectively. Our source code is available at https://github.com/greekinRoma/DATransNet.
Authors: Qun Dai, Chunyang Yuan, Yimian Dai, Yuxuan Li, Xiang Li, Kang Ni, Jianhui Xu, Xiangbo Shu, Jian Yang
Abstract: Land Surface Temperature (LST) is a critical parameter for environmental studies, but directly obtaining high spatial resolution LST data remains challenging due to the spatio-temporal trade-off in satellite remote sensing. Guided LST downscaling has emerged as an alternative solution to overcome these limitations, but current methods often neglect spatial non-stationarity, and there is a lack of an open-source ecosystem for deep learning methods. In this paper, we propose the Modality-Conditional Large Selective Kernel (MoCoLSK) Network, a novel architecture that dynamically fuses multi-modal data through modality-conditioned projections. MoCoLSK achieves a confluence of dynamic receptive field adjustment and multi-modal feature fusion, leading to enhanced LST prediction accuracy. Furthermore, we establish the GrokLST project, a comprehensive open-source ecosystem featuring the GrokLST dataset, a high-resolution benchmark, and the GrokLST toolkit, an open-source PyTorch-based toolkit encapsulating MoCoLSK alongside 40+ state-of-the-art approaches. Extensive experimental results validate MoCoLSK's effectiveness in capturing complex dependencies and subtle variations within multispectral data, outperforming existing methods in LST downscaling. Our code, dataset, and toolkit are available at https://github.com/GrokCV/GrokLST.
Authors: Zicheng Zhang, Ziheng Jia, Haoning Wu, Chunyi Li, Zijian Chen, Yingjie Zhou, Wei Sun, Xiaohong Liu, Xiongkuo Min, Weisi Lin, Guangtao Zhai
Abstract: With the rising interest in research on Large Multi-modal Models (LMMs) for video understanding, many studies have emphasized general video comprehension capabilities, neglecting the systematic exploration into video quality understanding. To address this oversight, we introduce Q-Bench-Video in this paper, a new benchmark specifically designed to evaluate LMMs' proficiency in discerning video quality. a) To ensure video source diversity, Q-Bench-Video encompasses videos from natural scenes, AI-generated Content (AIGC), and Computer Graphics (CG). b) Building on the traditional multiple-choice questions format with the Yes-or-No and What-How categories, we include Open-ended questions to better evaluate complex scenarios. Additionally, we incorporate the video pair quality comparison question to enhance comprehensiveness. c) Beyond the traditional Technical, Aesthetic, and Temporal distortions, we have expanded our evaluation aspects to include the dimension of AIGC distortions, which addresses the increasing demand for video generation. Finally, we collect a total of 2,378 question-answer pairs and test them on 12 open-source & 5 proprietary LMMs. Our findings indicate that while LMMs have a foundational understanding of video quality, their performance remains incomplete and imprecise, with a notable discrepancy compared to human performance. Through Q-Bench-Video, we seek to catalyze community interest, stimulate further research, and unlock the untapped potential of LMMs to close the gap in video quality understanding.
Authors: Fulong Ma, Weiqing Qi, Guoyang Zhao, Ming Liu, Jun Ma
Abstract: Data augmentation is one of the most common tools in deep learning, underpinning many recent advances including tasks such as classification, detection, and semantic segmentation. The standard approach to data augmentation involves simple transformations like rotation and flipping to generate new images. However, these new images often lack diversity along the main semantic dimensions within the data. Traditional data augmentation methods cannot alter high-level semantic attributes such as the presence of vehicles, trees, and buildings in a scene to enhance data diversity. In recent years, the rapid development of generative models has injected new vitality into the field of data augmentation. In this paper, we address the lack of diversity in data augmentation for road detection task by using a pre-trained text-to-image diffusion model to parameterize image-to-image transformations. Our method involves editing images using these diffusion models to change their semantics. In essence, we achieve this goal by erasing instances of real objects from the original dataset and generating new instances with similar semantics in the erased regions using the diffusion model, thereby expanding the original dataset. We evaluate our approach on the KITTI road dataset and achieve the best results compared to other data augmentation methods, which demonstrates the effectiveness of our proposed development.
Authors: Fulong Ma, Peng Hou, Yuxuan Liu, Yang Liu, Ming Liu, Jun Ma
Abstract: Road curbs are considered as one of the crucial and ubiquitous traffic features, which are essential for ensuring the safety of autonomous vehicles. Current methods for detecting curbs primarily rely on camera imagery or LiDAR point clouds. Image-based methods are vulnerable to fluctuations in lighting conditions and exhibit poor robustness, while methods based on point clouds circumvent the issues associated with lighting variations. However, it is the typical case that significant processing delays are encountered due to the voluminous amount of 3D points contained in each frame of the point cloud data. Furthermore, the inherently unstructured characteristics of point clouds poses challenges for integrating the latest deep learning advancements into point cloud data applications. To address these issues, this work proposes an annotation-free curb detection method leveraging Altitude Difference Image (ADI), which effectively mitigates the aforementioned challenges. Given that methods based on deep learning generally demand extensive, manually annotated datasets, which are both expensive and labor-intensive to create, we present an Automatic Curb Annotator (ACA) module. This module utilizes a deterministic curb detection algorithm to automatically generate a vast quantity of training data. Consequently, it facilitates the training of the curb detection model without necessitating any manual annotation of data. Finally, by incorporating a post-processing module, we manage to achieve state-of-the-art results on the KITTI 3D curb dataset with considerably reduced processing delays compared to existing methods, which underscores the effectiveness of our approach in curb detection tasks.
Authors: Hong Li, Nanxi Li, Yuanjie Chen, Jianbin Zhu, Qinlu Guo, Cewu Lu, Yong-Lu Li
Abstract: Multi-modal Large Language Models (MLLMs) have exhibited impressive capability. However, recently many deficiencies of MLLMs have been found compared to human intelligence, $\textit{e.g.}$, hallucination. To drive the MLLMs study, the community dedicated efforts to building larger benchmarks with complex tasks. In this paper, we propose benchmarking an essential but usually overlooked intelligence: $\textbf{association}$, a human's basic capability to link observation and prior practice memory. To comprehensively investigate MLLM's performance on the association, we formulate the association task and devise a standard benchmark based on adjective and verb semantic concepts. Instead of costly data annotation and curation, we propose a convenient $\textbf{annotation-free}$ construction method transforming the general dataset for our association tasks. Simultaneously, we devise a rigorous data refinement process to eliminate confusion in the raw dataset. Building on this database, we establish three levels of association tasks: single-step, synchronous, and asynchronous associations. Moreover, we conduct a comprehensive investigation into the MLLMs' zero-shot association capabilities, addressing multiple dimensions, including three distinct memory strategies, both open-source and closed-source MLLMs, cutting-edge Mixture-of-Experts (MoE) models, and the involvement of human experts. Our systematic investigation shows that current open-source MLLMs consistently exhibit poor capability in our association tasks, even the currently state-of-the-art GPT-4V(vision) also has a significant gap compared to humans. We believe our benchmark would pave the way for future MLLM studies. $\textit{Our data and code are available at:}$ https://mvig-rhos.com/llm_inception.
Authors: S\'egol\`ene Martin, Anne Gagneux, Paul Hagemann, Gabriele Steidl
Abstract: In this paper, we introduce Plug-and-Play (PnP) Flow Matching, an algorithm for solving imaging inverse problems. PnP methods leverage the strength of pre-trained denoisers, often deep neural networks, by integrating them in optimization schemes. While they achieve state-of-the-art performance on various inverse problems in imaging, PnP approaches face inherent limitations on more generative tasks like inpainting. On the other hand, generative models such as Flow Matching pushed the boundary in image sampling yet lack a clear method for efficient use in image restoration. We propose to combine the PnP framework with Flow Matching (FM) by defining a time-dependent denoiser using a pre-trained FM model. Our algorithm alternates between gradient descent steps on the data-fidelity term, reprojections onto the learned FM path, and denoising. Notably, our method is computationally efficient and memory-friendly, as it avoids backpropagation through ODEs and trace computations. We evaluate its performance on denoising, super-resolution, deblurring, and inpainting tasks, demonstrating superior results compared to existing PnP algorithms and Flow Matching based state-of-the-art methods.
Authors: Wenhao Chai, Enxin Song, Yilun Du, Chenlin Meng, Vashisht Madhavan, Omer Bar-Tal, Jenq-Neng Hwang, Saining Xie, Christopher D. Manning
Abstract: Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner based on a large multimodal model. We follow the simplest architecture design without additional parameters for temporal modeling. To address the overhead caused by lengthy video sequences, we implement the token merging strategy, reducing the number of input visual tokens. Surprisingly, we found that this strategy results in little performance loss. AuroraCap shows superior performance on various video and image captioning benchmarks, for example, obtaining a CIDEr of 88.9 on Flickr30k, beating GPT-4V (55.3) and Gemini-1.5 Pro (82.2). However, existing video caption benchmarks only include simple descriptions, consisting of a few dozen words, which limits research in this field. Therefore, we develop VDC, a video detailed captioning benchmark with over one thousand carefully annotated structured captions. In addition, we propose a new LLM-assisted metric VDCscore for bettering evaluation, which adopts a divide-and-conquer strategy to transform long caption evaluation into multiple short question-answer pairs. With the help of human Elo ranking, our experiments show that this benchmark better correlates with human judgments of video detailed captioning quality.
Authors: Zichen Miao, Zhengyuan Yang, Kevin Lin, Ze Wang, Zicheng Liu, Lijuan Wang, Qiang Qiu
Abstract: Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for applications due to the low inference cost and latency, fine-tuning them with a naive diffusion objective would result in degraded and blurry outputs. An intuitive alternative is to repeat the diffusion distillation process with a fine-tuned teacher model, which produces good results but is cumbersome and computationally intensive; the distillation training usually requires magnitude higher of training compute compared to fine-tuning for specific image styles. In this paper, we present an algorithm named pairwise sample optimization (PSO), which enables the direct fine-tuning of an arbitrary timestep-distilled diffusion model. PSO introduces additional reference images sampled from the current time-step distilled model, and increases the relative likelihood margin between the training images and reference images. This enables the model to retain its few-step generation ability, while allowing for fine-tuning of its output distribution. We also demonstrate that PSO is a generalized formulation which can be flexibly extended to both offline-sampled and online-sampled pairwise data, covering various popular objectives for diffusion model preference optimization. We evaluate PSO in both preference optimization and other fine-tuning tasks, including style transfer and concept customization. We show that PSO can directly adapt distilled models to human-preferred generation with both offline and online-generated pairwise preference image data. PSO also demonstrates effectiveness in style transfer and concept customization by directly tuning timestep-distilled diffusion models.
Authors: Doohyuk Jang, Sihwan Park, June Yong Yang, Yeonsung Jung, Jihun Yun, Souvik Kundu, Sung-Yub Kim, Eunho Yang
Abstract: Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitation of AR models is their sequential nature, which processes tokens one at a time, slowing down generation compared to models like GANs or diffusion-based methods that operate more efficiently. While speculative decoding has proven effective for accelerating LLMs by generating multiple tokens in a single forward, its application in visual AR models remains largely unexplored. In this work, we identify a challenge in this setting, which we term \textit{token selection ambiguity}, wherein visual AR models frequently assign uniformly low probabilities to tokens, hampering the performance of speculative decoding. To overcome this challenge, we propose a relaxed acceptance condition referred to as LANTERN that leverages the interchangeability of tokens in latent space. This relaxation restores the effectiveness of speculative decoding in visual AR models by enabling more flexible use of candidate tokens that would otherwise be prematurely rejected. Furthermore, by incorporating a total variation distance bound, we ensure that these speed gains are achieved without significantly compromising image quality or semantic coherence. Experimental results demonstrate the efficacy of our method in providing a substantial speed-up over speculative decoding. In specific, compared to a na\"ive application of the state-of-the-art speculative decoding, LANTERN increases speed-ups by $\mathbf{1.75}\times$ and $\mathbf{1.82}\times$, as compared to greedy decoding and random sampling, respectively, when applied to LlamaGen, a contemporary visual AR model. The code is publicly available at https://github.com/jadohu/LANTERN.
Authors: Shahrokh Hamidi
Abstract: The statistical analysis of land clutter for Synthetic Aperture Radar (SAR) imaging has become an increasingly important subject for research and investigation. It is also absolutely necessary for designing robust algorithms capable of performing the task of target detection in the background clutter. Any attempt to extract the energy of the desired targets from the land clutter requires complete knowledge of the statistical properties of the background clutter. In this paper, the spatial as well as the temporal characteristics of the land clutter are studied. Since the data for each image has been collected based on a different aspect angle; therefore, the temporal analysis contains variation in the aspect angle. Consequently, the temporal analysis includes the characteristics of the radar cross section with respect to the aspect angle based on which the data has been collected. In order to perform the statistical analysis, several well-known and relevant distributions, namely, Weibull, Log-normal, Gamma, and Rayleigh are considered as prime candidates to model the land clutter. The goodness-of-fit test is based on the Kullback-Leibler (KL) Divergence metric. The detailed analysis presented in this paper demonstrates that the Weibull distribution is a more accurate fit for the temporal-aspect-angle statistical analysis while the Rayleigh distribution models the spatial characteristics of the background clutter with higher accuracy. Finally, based on the aforementioned statistical analyses and by utilizing the Constant False Alarm Rate (CFAR) algorithm, we perform target detection in land clutter. The overall verification of the analysis is performed by exploiting the Moving and Stationary Target Acquisition and Recognition (MSTAR) data-set, which has been collected in spotlight mode at X-band, and the results are presented.
Authors: Yue Zhang, Zhiyang Xu, Ying Shen, Parisa Kordjamshidi, Lifu Huang
Abstract: Integrating the 3D world into large language models (3D-based LLMs) has been a promising research direction for 3D scene understanding. However, current 3D-based LLMs fall short in situated understanding due to two key limitations: 1) existing 3D datasets are constructed from a global perspective of the 3D scenes and lack situated context. 2) the architectures of existing 3D-based LLMs lack explicit alignment between the spatial representations of 3D scenes and natural language, limiting their performance in tasks requiring precise spatial reasoning. We address these issues by introducing a scalable situated 3D dataset, named Spartun3D, that incorporates various situated spatial reasoning tasks. Furthermore, we propose Spartun3D-LLM, built on an existing 3D-based LLM but integrated with a novel situated spatial alignment module, aiming to enhance the alignment between 3D visual representations and their corresponding textual descriptions. Experimental results demonstrate that both our proposed dataset and alignment module significantly enhance the situated spatial understanding of 3D-based LLMs.
Authors: Kaifeng Zhao, Gen Li, Siyu Tang
Abstract: Text-conditioned human motion generation, which allows for user interaction through natural language, has become increasingly popular. Existing methods typically generate short, isolated motions based on a single input sentence. However, human motions are continuous and can extend over long periods, carrying rich semantics. Creating long, complex motions that precisely respond to streams of text descriptions, particularly in an online and real-time setting, remains a significant challenge. Furthermore, incorporating spatial constraints into text-conditioned motion generation presents additional challenges, as it requires aligning the motion semantics specified by text descriptions with geometric information, such as goal locations and 3D scene geometry. To address these limitations, we propose DartControl, in short DART, a Diffusion-based Autoregressive motion primitive model for Real-time Text-driven motion control. Our model effectively learns a compact motion primitive space jointly conditioned on motion history and text inputs using latent diffusion models. By autoregressively generating motion primitives based on the preceding history and current text input, DART enables real-time, sequential motion generation driven by natural language descriptions. Additionally, the learned motion primitive space allows for precise spatial motion control, which we formulate either as a latent noise optimization problem or as a Markov decision process addressed through reinforcement learning. We present effective algorithms for both approaches, demonstrating our model's versatility and superior performance in various motion synthesis tasks. Experiments show our method outperforms existing baselines in motion realism, efficiency, and controllability. Video results are available on the project page: https://zkf1997.github.io/DART/.
Authors: Yongxin Guo, Jingyu Liu, Mingda Li, Qingbin Liu, Xi Chen, Xiaoying Tang
Abstract: Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot prediction, there is a growing trend in employing video LLMs for VTG tasks. However, current video LLM-based methods rely exclusively on natural language generation, lacking the ability to model the clear structure inherent in videos, which restricts their effectiveness in tackling VTG tasks. To address this issue, this paper first formally introduces causal event modeling framework, which represents video LLM outputs as sequences of events, and predict the current event using previous events, video inputs, and textural instructions. Each event consists of three components: timestamps, salient scores, and textual captions. We then propose a novel task-interleaved video LLM called TRACE to effectively implement the causal event modeling framework in practice. The TRACE process visual frames, timestamps, salient scores, and text as distinct tasks, employing various encoders and decoding heads for each. Task tokens are arranged in an interleaved sequence according to the causal event modeling framework's formulation. Extensive experiments on various VTG tasks and datasets demonstrate the superior performance of TRACE compared to state-of-the-art video LLMs. Our model and code are available at https://github.com/gyxxyg/TRACE.
Authors: Serin Yang, Taesung Kwon, Jong Chul Ye
Abstract: Recent progress in large-scale text-to-video (T2V) and image-to-video (I2V) diffusion models has greatly enhanced video generation, especially in terms of keyframe interpolation. However, current image-to-video diffusion models, while powerful in generating videos from a single conditioning frame, need adaptation for two-frame (start & end) conditioned generation, which is essential for effective bounded interpolation. Unfortunately, existing approaches that fuse temporally forward and backward paths in parallel often suffer from off-manifold issues, leading to artifacts or requiring multiple iterative re-noising steps. In this work, we introduce a novel, bidirectional sampling strategy to address these off-manifold issues without requiring extensive re-noising or fine-tuning. Our method employs sequential sampling along both forward and backward paths, conditioned on the start and end frames, respectively, ensuring more coherent and on-manifold generation of intermediate frames. Additionally, we incorporate advanced guidance techniques, CFG++ and DDS, to further enhance the interpolation process. By integrating these, our method achieves state-of-the-art performance, efficiently generating high-quality, smooth videos between keyframes. On a single 3090 GPU, our method can interpolate 25 frames at 1024 x 576 resolution in just 195 seconds, establishing it as a leading solution for keyframe interpolation.
Authors: Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, Fabio Galasso, Pascal Mettes
Abstract: Image-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding space. Since visual and textual concepts are naturally hierarchical, recent work has shown that hyperbolic space can serve as a high-potential manifold to learn vision-language representation with strong downstream performance. In this work, for the first time we show how to fully leverage the innate hierarchical nature of hyperbolic embeddings by looking beyond individual image-text pairs. We propose Compositional Entailment Learning for hyperbolic vision-language models. The idea is that an image is not only described by a sentence but is itself a composition of multiple object boxes, each with their own textual description. Such information can be obtained freely by extracting nouns from sentences and using openly available localized grounding models. We show how to hierarchically organize images, image boxes, and their textual descriptions through contrastive and entailment-based objectives. Empirical evaluation on a hyperbolic vision-language model trained with millions of image-text pairs shows that the proposed compositional learning approach outperforms conventional Euclidean CLIP learning, as well as recent hyperbolic alternatives, with better zero-shot and retrieval generalization and clearly stronger hierarchical performance.
Authors: Jiahao Lu, Yifan Zhang, Qiuhong Shen, Xinchao Wang, Shuicheng Yan
Abstract: 3D Gaussian splatting (3DGS), known for its groundbreaking performance and efficiency, has become a dominant 3D representation and brought progress to many 3D vision tasks. However, in this work, we reveal a significant security vulnerability that has been largely overlooked in 3DGS: the computation cost of training 3DGS could be maliciously tampered by poisoning the input data. By developing an attack named Poison-splat, we reveal a novel attack surface where the adversary can poison the input images to drastically increase the computation memory and time needed for 3DGS training, pushing the algorithm towards its worst computation complexity. In extreme cases, the attack can even consume all allocable memory, leading to a Denial-of-Service (DoS) that disrupts servers, resulting in practical damages to real-world 3DGS service vendors. Such a computation cost attack is achieved by addressing a bi-level optimization problem through three tailored strategies: attack objective approximation, proxy model rendering, and optional constrained optimization. These strategies not only ensure the effectiveness of our attack but also make it difficult to defend with simple defensive measures. We hope the revelation of this novel attack surface can spark attention to this crucial yet overlooked vulnerability of 3DGS systems. Our code is available at https://github.com/jiahaolu97/poison-splat .
Authors: Haoyi Zhu, Honghui Yang, Yating Wang, Jiange Yang, Limin Wang, Tong He
Abstract: In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach leverages differentiable neural rendering on multi-view images to endow a vanilla Vision Transformer (ViT) with intrinsic spatial understanding. We present the most comprehensive evaluation of embodied representation learning to date, covering 268 tasks across 8 simulators with diverse policies in both single-task and language-conditioned multi-task scenarios. The results are compelling: SPA consistently outperforms more than 10 state-of-the-art representation methods, including those specifically designed for embodied AI, vision-centric tasks, and multi-modal applications, while using less training data. Furthermore, we conduct a series of real-world experiments to confirm its effectiveness in practical scenarios. These results highlight the critical role of 3D spatial awareness for embodied representation learning. Our strongest model takes more than 6000 GPU hours to train and we are committed to open-sourcing all code and model weights to foster future research in embodied representation learning. Project Page: https://haoyizhu.github.io/spa/.
Authors: Junkai Niu, Sheng Zhong, Xiuyuan Lu, Shaojie Shen, Guillermo Gallego, Yi Zhou
Abstract: Event-based visual odometry is a specific branch of visual Simultaneous Localization and Mapping (SLAM) techniques, which aims at solving tracking and mapping subproblems (typically in parallel), by exploiting the special working principles of neuromorphic (i.e., event-based) cameras. Due to the motion-dependent nature of event data, explicit data association (i.e., feature matching) under large-baseline view-point changes is difficult to establish, making direct methods a more rational choice. However, state-of-the-art direct methods are limited by the high computational complexity of the mapping sub-problem and the degeneracy of camera pose tracking in certain degrees of freedom (DoF) in rotation. In this paper, we tackle these issues by building an event-based stereo visual-inertial odometry system on top of a direct pipeline. Specifically, to speed up the mapping operation, we propose an efficient strategy for sampling contour points according to the local dynamics of events. The mapping performance is also improved in terms of structure completeness and local smoothness by merging the temporal stereo and static stereo results. To circumvent the degeneracy of camera pose tracking in recovering the pitch and yaw components of general 6-DoF motion, we introduce IMU measurements as motion priors via pre-integration. To this end, a compact back-end is proposed for continuously updating the IMU bias and predicting the linear velocity, enabling an accurate motion prediction for camera pose tracking. The resulting system scales well with modern high-resolution event cameras and leads to better global positioning accuracy in large-scale outdoor environments. Extensive evaluations on five publicly available datasets featuring different resolutions and scenarios justify the superior performance of the proposed system against five state-of-the-art methods.
Authors: Yifeng Xu, Zhenliang He, Shiguang Shan, Xilin Chen
Abstract: Recently, large-scale diffusion models have made impressive progress in text-to-image (T2I) generation. To further equip these T2I models with fine-grained spatial control, approaches like ControlNet introduce an extra network that learns to follow a condition image. However, for every single condition type, ControlNet requires independent training on millions of data pairs with hundreds of GPU hours, which is quite expensive and makes it challenging for ordinary users to explore and develop new types of conditions. To address this problem, we propose the CtrLoRA framework, which trains a Base ControlNet to learn the common knowledge of image-to-image generation from multiple base conditions, along with condition-specific LoRAs to capture distinct characteristics of each condition. Utilizing our pretrained Base ControlNet, users can easily adapt it to new conditions, requiring as few as 1,000 data pairs and less than one hour of single-GPU training to obtain satisfactory results in most scenarios. Moreover, our CtrLoRA reduces the learnable parameters by 90% compared to ControlNet, significantly lowering the threshold to distribute and deploy the model weights. Extensive experiments on various types of conditions demonstrate the efficiency and effectiveness of our method. Codes and model weights will be released at https://github.com/xyfJASON/ctrlora.
Authors: Muhammad Gohar Javed, Chuan Guo, Li Cheng, Xingyu Li
Abstract: Generating realistic 3D human-human interactions from textual descriptions remains a challenging task. Existing approaches, typically based on diffusion models, often produce results lacking realism and fidelity. In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space. InterMask first employs a VQ-VAE to transform each motion sequence into a 2D discrete motion token map. Unlike traditional 1D VQ token maps, it better preserves fine-grained spatio-temporal details and promotes spatial awareness within each token. Building on this representation, InterMask utilizes a generative masked modeling framework to collaboratively model the tokens of two interacting individuals. This is achieved by employing a transformer architecture specifically designed to capture complex spatio-temporal inter-dependencies. During training, it randomly masks the motion tokens of both individuals and learns to predict them. For inference, starting from fully masked sequences, it progressively fills in the tokens for both individuals. With its enhanced motion representation, dedicated architecture, and effective learning strategy, InterMask achieves state-of-the-art results, producing high-fidelity and diverse human interactions. It outperforms previous methods, achieving an FID of $5.154$ (vs $5.535$ of in2IN) on the InterHuman dataset and $0.399$ (vs $5.207$ of InterGen) on the InterX dataset. Additionally, InterMask seamlessly supports reaction generation without the need for model redesign or fine-tuning.
Authors: Jing Liang, He Yin, Xuewei Qi, Jong Jin Park, Min Sun, Rajasimman Madhivanan, Dinesh Manocha
Abstract: We introduce ET-Former, a novel end-to-end algorithm for semantic scene completion using a single monocular camera. Our approach generates a semantic occupancy map from single RGB observation while simultaneously providing uncertainty estimates for semantic predictions. By designing a triplane-based deformable attention mechanism, our approach improves geometric understanding of the scene than other SOTA approaches and reduces noise in semantic predictions. Additionally, through the use of a Conditional Variational AutoEncoder (CVAE), we estimate the uncertainties of these predictions. The generated semantic and uncertainty maps will help formulate navigation strategies that facilitate safe and permissible decision making in the future. Evaluated on the Semantic-KITTI dataset, ET-Former achieves the highest Intersection over Union (IoU) and mean IoU (mIoU) scores while maintaining the lowest GPU memory usage, surpassing state-of-the-art (SOTA) methods. It improves the SOTA scores of IoU from 44.71 to 51.49 and mIoU from 15.04 to 16.30 on SeamnticKITTI test, with a notably low training memory consumption of 10.9 GB. Project page: https://github.com/jingGM/ET-Former.git.
Authors: Luping Liu, Chao Du, Tianyu Pang, Zehan Wang, Chongxuan Li, Dong Xu
Abstract: The rapid advancement of text-to-image (T2I) diffusion models has enabled them to generate unprecedented results from given texts. However, as text inputs become longer, existing encoding methods like CLIP face limitations, and aligning the generated images with long texts becomes challenging. To tackle these issues, we propose LongAlign, which includes a segment-level encoding method for processing long texts and a decomposed preference optimization method for effective alignment training. For segment-level encoding, long texts are divided into multiple segments and processed separately. This method overcomes the maximum input length limits of pretrained encoding models. For preference optimization, we provide decomposed CLIP-based preference models to fine-tune diffusion models. Specifically, to utilize CLIP-based preference models for T2I alignment, we delve into their scoring mechanisms and find that the preference scores can be decomposed into two components: a text-relevant part that measures T2I alignment and a text-irrelevant part that assesses other visual aspects of human preference. Additionally, we find that the text-irrelevant part contributes to a common overfitting problem during fine-tuning. To address this, we propose a reweighting strategy that assigns different weights to these two components, thereby reducing overfitting and enhancing alignment. After fine-tuning $512 \times 512$ Stable Diffusion (SD) v1.5 for about 20 hours using our method, the fine-tuned SD outperforms stronger foundation models in T2I alignment, such as PixArt-$\alpha$ and Kandinsky v2.2. The code is available at https://github.com/luping-liu/LongAlign.
Authors: Yankai Jiang, Wenhui Lei, Xiaofan Zhang, Shaoting Zhang
Abstract: Recent advancements in medical vision-language pre-training models have driven significant progress in zero-shot disease recognition. However, transferring image-level knowledge to pixel-level tasks, such as lesion segmentation in 3D CT scans, remains a critical challenge. Due to the complexity and variability of pathological visual characteristics, existing methods struggle to align fine-grained lesion features not encountered during training with disease-related textual representations. In this paper, we present Malenia, a novel multi-scale lesion-level mask-attribute alignment framework, specifically designed for 3D zero-shot lesion segmentation. Malenia improves the compatibility between mask representations and their associated elemental attributes, explicitly linking the visual features of unseen lesions with the extensible knowledge learned from previously seen ones. Furthermore, we design a Cross-Modal Knowledge Injection module to enhance both visual and textual features with mutually beneficial information, effectively guiding the generation of segmentation results. Comprehensive experiments across three datasets and 12 lesion categories validate the superior performance of Malenia.
Authors: Hengwei Bian, Lingdong Kong, Haozhe Xie, Liang Pan, Yu Qiao, Ziwei Liu
Abstract: Urban scene generation has been developing rapidly recently. However, existing methods primarily focus on generating static and single-frame scenes, overlooking the inherently dynamic nature of real-world driving environments. In this work, we introduce DynamicCity, a novel 4D occupancy generation framework capable of generating large-scale, high-quality dynamic 4D scenes with semantics. DynamicCity mainly consists of two key models. 1) A VAE model for learning HexPlane as the compact 4D representation. Instead of using naive averaging operations, DynamicCity employs a novel Projection Module to effectively compress 4D features into six 2D feature maps for HexPlane construction, which significantly enhances HexPlane fitting quality (up to 12.56 mIoU gain). Furthermore, we utilize an Expansion & Squeeze Strategy to reconstruct 3D feature volumes in parallel, which improves both network training efficiency and reconstruction accuracy than naively querying each 3D point (up to 7.05 mIoU gain, 2.06x training speedup, and 70.84% memory reduction). 2) A DiT-based diffusion model for HexPlane generation. To make HexPlane feasible for DiT generation, a Padded Rollout Operation is proposed to reorganize all six feature planes of the HexPlane as a squared 2D feature map. In particular, various conditions could be introduced in the diffusion or sampling process, supporting versatile 4D generation applications, such as trajectory- and command-driven generation, inpainting, and layout-conditioned generation. Extensive experiments on the CarlaSC and Waymo datasets demonstrate that DynamicCity significantly outperforms existing state-of-the-art 4D occupancy generation methods across multiple metrics. The code and models have been released to facilitate future research.
Authors: Hao Ding, Yuqian Zhang, Wenzheng Cheng, Xinyu Wang, Xu Lian, Chenhao Yu, Hongchao Shu, Ji Woong Kim, Axel Krieger, Mathias Unberath
Abstract: Surgical phase recognition (SPR) is an integral component of surgical data science, enabling high-level surgical analysis. End-to-end trained neural networks that predict surgical phase directly from videos have shown excellent performance on benchmarks. However, these models struggle with robustness due to non-causal associations in the training set. Our goal is to improve model robustness to variations in the surgical videos by leveraging the digital twin (DT) paradigm -- an intermediary layer to separate high-level analysis (SPR) from low-level processing. As a proof of concept, we present a DT representation-based framework for SPR from videos. The framework employs vision foundation models with reliable low-level scene understanding to craft DT representation. We embed the DT representation in place of raw video inputs in the state-of-the-art SPR model. The framework is trained on the Cholec80 dataset and evaluated on out-of-distribution (OOD) and corrupted test samples. Contrary to the vulnerability of the baseline model, our framework demonstrates strong robustness on both OOD and corrupted samples, with a video-level accuracy of 80.3 on a highly corrupted Cholec80 test set, 67.9 on the challenging CRCD dataset, and 99.8 on an internal robotic surgery dataset, outperforming the baseline by 3.9, 16.8, and 90.9 respectively. We also find that using DT representation as an augmentation to the raw input can significantly improve model robustness. Our findings lend support to the thesis that DT representations are effective in enhancing model robustness. Future work will seek to improve the feature informativeness and incorporate interpretability for a more comprehensive framework.
Authors: Pratheba Selvaraju, Victoria Fernandez Abrevaya, Timo Bolkart, Rick Akkerman, Tianyu Ding, Faezeh Amjadi, Ilya Zharkov
Abstract: Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions. In addition to fewer available observations, occlusions introduce an extra source of ambiguity where multiple reconstructions can be equally valid. Despite the ubiquity of the problem, very few methods address its multi-hypothesis nature. In this paper we introduce OFER, a novel approach for single-image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces, even under strong occlusions. Specifically, we train two diffusion models to generate the shape and expression coefficients of a face parametric model, conditioned on the input image. This approach captures the multi-modal nature of the problem, generating a distribution of solutions as output. However, to maintain consistency across diverse expressions, the challenge is to select the best matching shape. To achieve this, we propose a novel ranking mechanism that sorts the outputs of the shape diffusion network based on predicted shape accuracy scores. We evaluate our method using standard benchmarks and introduce CO-545, a new protocol and dataset designed to assess the accuracy of expressive faces under occlusion. Our results show improved performance over occlusion-based methods, while also enabling the generation of diverse expressions for a given image.
Authors: S Balasubramanian, M Sai Subramaniam, Sai Sriram Talasu, Yedu Krishna P, Manepalli Pranav Phanindra Sai, Ravi Mukkamala, Darshan Gera
Abstract: Deep neural networks (DNNS) excel at learning from static datasets but struggle with continual learning, where data arrives sequentially. Catastrophic forgetting, the phenomenon of forgetting previously learned knowledge, is a primary challenge. This paper introduces EXponentially Averaged Class-wise Feature Significance (EXACFS) to mitigate this issue in the class incremental learning (CIL) setting. By estimating the significance of model features for each learned class using loss gradients, gradually aging the significance through the incremental tasks and preserving the significant features through a distillation loss, EXACFS effectively balances remembering old knowledge (stability) and learning new knowledge (plasticity). Extensive experiments on CIFAR-100 and ImageNet-100 demonstrate EXACFS's superior performance in preserving stability while acquiring plasticity.
Authors: Bryan Bo Cao, Lawrence O'Gorman, Michael Coss, Shubham Jain
Abstract: We propose Few-Class Arena (FCA), as a unified benchmark with focus on testing efficient image classification models for few classes. A wide variety of benchmark datasets with many classes (80-1000) have been created to assist Computer Vision architectural evolution. An increasing number of vision models are evaluated with these many-class datasets. However, real-world applications often involve substantially fewer classes of interest (2-10). This gap between many and few classes makes it difficult to predict performance of the few-class applications using models trained on the available many-class datasets. To date, little has been offered to evaluate models in this Few-Class Regime. We conduct a systematic evaluation of the ResNet family trained on ImageNet subsets from 2 to 1000 classes, and test a wide spectrum of Convolutional Neural Networks and Transformer architectures over ten datasets by using our newly proposed FCA tool. Furthermore, to aid an up-front assessment of dataset difficulty and a more efficient selection of models, we incorporate a difficulty measure as a function of class similarity. FCA offers a new tool for efficient machine learning in the Few-Class Regime, with goals ranging from a new efficient class similarity proposal, to lightweight model architecture design, to a new scaling law. FCA is user-friendly and can be easily extended to new models and datasets, facilitating future research work. Our benchmark is available at https://github.com/bryanbocao/fca.
Authors: Jian Chen, Ruiyi Zhang, Yufan Zhou, Tong Yu, Franck Dernoncourt, Jiuxiang Gu, Ryan A. Rossi, Changyou Chen, Tong Sun
Abstract: Multimodal large language models (MLLMs) have recently shown great progress in text-rich image understanding, yet they still struggle with complex, multi-page visually-rich documents. Traditional methods using document parsers for retrieval-augmented generation suffer from performance and efficiency limitations, while directly presenting all pages to MLLMs leads to inefficiencies, especially with lengthy ones. In this work, we present a novel framework named **S**elf-**V**isual **R**etrieval-**A**ugmented **G**eneration (SV-RAG), which can broaden horizons of any MLLM to support long-document understanding. We demonstrate that **MLLMs themselves can be an effective multimodal retriever** to fetch relevant pages and then answer user questions based on these pages. SV-RAG is implemented with two specific MLLM adapters, one for evidence page retrieval and the other for question answering. Empirical results show state-of-the-art performance on public benchmarks, demonstrating the effectiveness of SV-RAG.
Authors: Neel Dey, Benjamin Billot, Hallee E. Wong, Clinton J. Wang, Mengwei Ren, P. Ellen Grant, Adrian V. Dalca, Polina Golland
Abstract: Current volumetric biomedical foundation models struggle to generalize as public 3D datasets are small and do not cover the broad diversity of medical procedures, conditions, anatomical regions, and imaging protocols. We address this by creating a representation learning method that instead anticipates strong domain shifts at training time itself. We first propose a data engine that synthesizes highly variable training samples that would enable generalization to new biomedical contexts. To then train a single 3D network for any voxel-level task, we develop a contrastive learning method that pretrains the network to be stable against nuisance imaging variation simulated by the data engine, a key inductive bias for generalization. This network's features can be used as robust representations of input images for downstream tasks and its weights provide a strong, dataset-agnostic initialization for finetuning on new datasets. As a result, we set new standards across both multimodality registration and few-shot segmentation, a first for any 3D biomedical vision model, all without (pre-)training on any existing dataset of real images.
Authors: Muyang Li, Yujun Lin, Zhekai Zhang, Tianle Cai, Xiuyu Li, Junxian Guo, Enze Xie, Chenlin Meng, Jun-Yan Zhu, Song Han
Abstract: Diffusion models can effectively generate high-quality images. However, as they scale, rising memory demands and higher latency pose substantial deployment challenges. In this work, we aim to accelerate diffusion models by quantizing their weights and activations to 4 bits. At such an aggressive level, both weights and activations are highly sensitive, where existing post-training quantization methods like smoothing become insufficient. To overcome this limitation, we propose SVDQuant, a new 4-bit quantization paradigm. Different from smoothing, which redistributes outliers between weights and activations, our approach absorbs these outliers using a low-rank branch. We first consolidate the outliers by shifting them from activations to weights. Then, we use a high-precision, low-rank branch to take in the weight outliers with Singular Value Decomposition (SVD), while a low-bit quantized branch handles the residuals. This process eases the quantization on both sides. However, naively running the low-rank branch independently incurs significant overhead due to extra data movement of activations, negating the quantization speedup. To address this, we co-design an inference engine Nunchaku that fuses the kernels of the low-rank branch into those of the low-bit branch to cut off redundant memory access. It can also seamlessly support off-the-shelf low-rank adapters (LoRAs) without re-quantization. Extensive experiments on SDXL, PixArt-$\Sigma$, and FLUX.1 validate the effectiveness of SVDQuant in preserving image quality. We reduce the memory usage for the 12B FLUX.1 models by 3.5$\times$, achieving 3.0$\times$ speedup over the 4-bit weight-only quantization (W4A16) baseline on the 16GB laptop 4090 GPU with INT4 precision. On the latest RTX 5090 desktop with Blackwell architecture, we achieve a 3.1$\times$ speedup compared to the W4A16 model using NVFP4 precision.
Authors: Xun Huang, Jinlong Wang, Qiming Xia, Siheng Chen, Bisheng Yang, Xin Li, Cheng Wang, Chenglu Wen
Abstract: Current Vehicle-to-Everything (V2X) systems have significantly enhanced 3D object detection using LiDAR and camera data. However, these methods suffer from performance degradation in adverse weather conditions. The weatherrobust 4D radar provides Doppler and additional geometric information, raising the possibility of addressing this challenge. To this end, we present V2X-R, the first simulated V2X dataset incorporating LiDAR, camera, and 4D radar. V2X-R contains 12,079 scenarios with 37,727 frames of LiDAR and 4D radar point clouds, 150,908 images, and 170,859 annotated 3D vehicle bounding boxes. Subsequently, we propose a novel cooperative LiDAR-4D radar fusion pipeline for 3D object detection and implement it with various fusion strategies. To achieve weather-robust detection, we additionally propose a Multi-modal Denoising Diffusion (MDD) module in our fusion pipeline. MDD utilizes weather-robust 4D radar feature as a condition to prompt the diffusion model to denoise noisy LiDAR features. Experiments show that our LiDAR-4D radar fusion pipeline demonstrates superior performance in the V2X-R dataset. Over and above this, our MDD module further improved the performance of basic fusion model by up to 5.73%/6.70% in foggy/snowy conditions with barely disrupting normal performance. The dataset and code will be publicly available at: https://github.com/ylwhxht/V2X-R.
Authors: Hatef Otroshi Shahreza, S\'ebastien Marcel
Abstract: Face recognition datasets are often collected by crawling Internet and without individuals' consents, raising ethical and privacy concerns. Generating synthetic datasets for training face recognition models has emerged as a promising alternative. However, the generation of synthetic datasets remains challenging as it entails adequate inter-class and intra-class variations. While advances in generative models have made it easier to increase intra-class variations in face datasets (such as pose, illumination, etc.), generating sufficient inter-class variation is still a difficult task. In this paper, we formulate the dataset generation as a packing problem on the embedding space (represented on a hypersphere) of a face recognition model and propose a new synthetic dataset generation approach, called HyperFace. We formalize our packing problem as an optimization problem and solve it with a gradient descent-based approach. Then, we use a conditional face generator model to synthesize face images from the optimized embeddings. We use our generated datasets to train face recognition models and evaluate the trained models on several benchmarking real datasets. Our experimental results show that models trained with HyperFace achieve state-of-the-art performance in training face recognition using synthetic datasets.
Authors: Fabio Bellavia, Zhenjun Zhao, Luca Morelli, Fabio Remondino
Abstract: This paper introduces a modular, non-deep learning method for filtering and refining sparse correspondences in image matching. Assuming that motion flow within the scene can be approximated by local homography transformations, matches are aggregated into overlapping clusters corresponding to virtual planes using an iterative RANSAC-based approach, with non-conforming correspondences discarded. Moreover, the underlying planar structural design provides an explicit map between local patches associated with the matches, enabling optional refinement of keypoint positions through cross-correlation template matching after patch reprojection. Finally, to enhance robustness and fault-tolerance against violations of the piece-wise planar approximation assumption, a further strategy is designed for minimizing relative patch distortion in the plane reprojection by introducing an intermediate homography that projects both patches into a common plane. The proposed method is extensively evaluated on standard datasets and image matching pipelines, and compared with state-of-the-art approaches. Unlike other current comparisons, the proposed benchmark also takes into account the more general, real, and practical cases where camera intrinsics are unavailable. Experimental results demonstrate that our proposed non-deep learning, geometry-based approach achieves performances that are either superior to or on par with recent state-of-the-art deep learning methods. Finally, this study suggests that there are still development potential in actual image matching solutions in the considered research direction, which could be in the future incorporated in novel deep image matching architectures.
Authors: Quang P. M. Pham, Khoi T. N. Nguyen, Lan C. Ngo, Truong Do, Dezhen Song, Truong-Son Hy
Abstract: Scene graphs have proven to be highly effective for various scene understanding tasks due to their compact and explicit representation of relational information. However, current methods often overlook the critical importance of preserving symmetry when generating scene graphs from 3D point clouds, which can lead to reduced accuracy and robustness, particularly when dealing with noisy, multi-view data. Furthermore, a major limitation of prior approaches is the lack of temporal modeling to capture time-dependent relationships among dynamically evolving entities in a scene. To address these challenges, we propose Temporal Equivariant Scene Graph Neural Network (TESGNN), consisting of two key components: (1) an Equivariant Scene Graph Neural Network (ESGNN), which extracts information from 3D point clouds to generate scene graph while preserving crucial symmetry properties, and (2) a Temporal Graph Matching Network, which fuses scene graphs generated by ESGNN across multiple time sequences into a unified global representation using an approximate graph-matching algorithm. Our combined architecture TESGNN outperforms current state-of-the-art methods in scene graph generation, achieving higher accuracy and faster training convergence. Moreover, we show that leveraging the symmetry-preserving property produces a more stable and accurate global scene representation compared to existing approaches. Last but not least, it is computationally efficient and easily implementable using existing frameworks, making it well-suited for real-time applications in robotics and computer vision. This approach paves the way for more robust and scalable solutions to complex multi-view scene understanding challenges. Our source code is publicly available at: https://github.com/HySonLab/TESGraph
Authors: Vishwesh Nath, Wenqi Li, Dong Yang, Andriy Myronenko, Mingxin Zheng, Yao Lu, Zhijian Liu, Hongxu Yin, Yucheng Tang, Pengfei Guo, Can Zhao, Ziyue Xu, Yufan He, Greg Heinrich, Yee Man Law, Benjamin Simon, Stephanie Harmon, Stephen Aylward, Marc Edgar, Michael Zephyr, Song Han, Pavlo Molchanov, Baris Turkbey, Holger Roth, Daguang Xu
Abstract: Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. In traditional computer vision tasks, creative or approximate answers may be acceptable, but in healthcare, precision is paramount.Current large multimodal models like Gemini and GPT-4o are insufficient for medical tasks due to their reliance on memorized internet knowledge rather than the nuanced expertise required in healthcare. VLMs are usually trained in three stages: vision pre-training, vision-language pre-training, and instruction fine-tuning (IFT). IFT has been typically applied using a mixture of generic and healthcare data. In contrast, we propose that for medical VLMs, a fourth stage of specialized IFT is necessary, which focuses on medical data and includes information from domain expert models. Domain expert models developed for medical use are crucial because they are specifically trained for certain clinical tasks, e.g. to detect tumors and classify abnormalities through segmentation and classification, which learn fine-grained features of medical data$-$features that are often too intricate for a VLM to capture effectively especially in radiology. This paper introduces a new framework, VILA-M3, for medical VLMs that utilizes domain knowledge via expert models. Through our experiments, we show an improved state-of-the-art (SOTA) performance with an average improvement of ~9% over the prior SOTA model Med-Gemini and ~6% over models trained on the specific tasks. Our approach emphasizes the importance of domain expertise in creating precise, reliable VLMs for medical applications.
Authors: Dengsheng Chen, Jie Hu, Tiezhu Yue, Xiaoming Wei, Enhua Wu
Abstract: Recently, autoregressive models have demonstrated remarkable performance in class-conditional image generation. However, the application of next-token prediction to high-resolution text-to-image generation remains largely unexplored. In this paper, we introduce \textbf{D-JEPA$\cdot$T2I}, an autoregressive model based on continuous tokens that incorporates innovations in both architecture and training strategy to generate high-quality, photorealistic images at arbitrary resolutions, up to 4K. Architecturally, we adopt the denoising joint embedding predictive architecture (D-JEPA) while leveraging a multimodal visual transformer to effectively integrate textual and visual features. Additionally, we introduce flow matching loss alongside the proposed Visual Rotary Positional Embedding (VoPE) to enable continuous resolution learning. In terms of training strategy, we propose a data feedback mechanism that dynamically adjusts the sampling procedure based on statistical analysis and an online learning critic model. This encourages the model to move beyond its comfort zone, reducing redundant training on well-mastered scenarios and compelling it to address more challenging cases with suboptimal generation quality. For the first time, we achieve state-of-the-art high-resolution image synthesis via next-token prediction.
Authors: Yuan Ren, Guile Wu, Runhao Li, Zheyuan Yang, Yibo Liu, Xingxin Chen, Tongtong Cao, Bingbing Liu
Abstract: Urban scene reconstruction is crucial for real-world autonomous driving simulators. Although existing methods have achieved photorealistic reconstruction, they mostly focus on pinhole cameras and neglect fisheye cameras. In fact, how to effectively simulate fisheye cameras in driving scene remains an unsolved problem. In this work, we propose UniGaussian, a novel approach that learns a unified 3D Gaussian representation from multiple camera models for urban scene reconstruction in autonomous driving. Our contributions are two-fold. First, we propose a new differentiable rendering method that distorts 3D Gaussians using a series of affine transformations tailored to fisheye camera models. This addresses the compatibility issue of 3D Gaussian splatting with fisheye cameras, which is hindered by light ray distortion caused by lenses or mirrors. Besides, our method maintains real-time rendering while ensuring differentiability. Second, built on the differentiable rendering method, we design a new framework that learns a unified Gaussian representation from multiple camera models. By applying affine transformations to adapt different camera models and regularizing the shared Gaussians with supervision from different modalities, our framework learns a unified 3D Gaussian representation with input data from multiple sources and achieves holistic driving scene understanding. As a result, our approach models multiple sensors (pinhole and fisheye cameras) and modalities (depth, semantic, normal and LiDAR point clouds). Our experiments show that our method achieves superior rendering quality and fast rendering speed for driving scene simulation.
Authors: Yuncong Yang, Han Yang, Jiachen Zhou, Peihao Chen, Hongxin Zhang, Yilun Du, Chuang Gan
Abstract: Constructing compact and informative 3D scene representations is essential for effective embodied exploration and reasoning, especially in complex environments over extended periods. Existing representations, such as object-centric 3D scene graphs, oversimplify spatial relationships by modeling scenes as isolated objects with restrictive textual relationships, making it difficult to address queries requiring nuanced spatial understanding. Moreover, these representations lack natural mechanisms for active exploration and memory management, hindering their application to lifelong autonomy. In this work, we propose 3D-Mem, a novel 3D scene memory framework for embodied agents. 3D-Mem employs informative multi-view images, termed Memory Snapshots, to represent the scene and capture rich visual information of explored regions. It further integrates frontier-based exploration by introducing Frontier Snapshots-glimpses of unexplored areas-enabling agents to make informed decisions by considering both known and potential new information. To support lifelong memory in active exploration settings, we present an incremental construction pipeline for 3D-Mem, as well as a memory retrieval technique for memory management. Experimental results on three benchmarks demonstrate that 3D-Mem significantly enhances agents' exploration and reasoning capabilities in 3D environments, highlighting its potential for advancing applications in embodied AI.
Authors: Uy Dieu Tran, Minh Luu, Phong Ha Nguyen, Khoi Nguyen, Binh-Son Hua
Abstract: Existing Score Distillation Sampling (SDS)-based methods have driven significant progress in text-to-3D generation. However, 3D models produced by SDS-based methods tend to exhibit over-smoothing and low-quality outputs. These issues arise from the mode-seeking behavior of current methods, where the scores used to update the model oscillate between multiple modes, resulting in unstable optimization and diminished output quality. To address this problem, we introduce a novel image prompt score distillation loss named ISD, which employs a reference image to direct text-to-3D optimization toward a specific mode. Our ISD loss can be implemented by using IP-Adapter, a lightweight adapter for integrating image prompt capability to a text-to-image diffusion model, as a mode-selection module. A variant of this adapter, when not being prompted by a reference image, can serve as an efficient control variate to reduce variance in score estimates, thereby enhancing both output quality and optimization stability. Our experiments demonstrate that the ISD loss consistently achieves visually coherent, high-quality outputs and improves optimization speed compared to prior text-to-3D methods, as demonstrated through both qualitative and quantitative evaluations on the T3Bench benchmark suite.
Authors: Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann
Abstract: Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin on the right of a bowl". Understanding these inconsistencies is crucial for reliable image generation. In this paper, we highlight the significant role of initial noise in these inconsistencies, where certain noise patterns are more reliable for compositional prompts than others. Our analyses reveal that different initial random seeds tend to guide the model to place objects in distinct image areas, potentially adhering to specific patterns of camera angles and image composition associated with the seed. To improve the model's compositional ability, we propose a method for mining these reliable cases, resulting in a curated training set of generated images without requiring any manual annotation. By fine-tuning text-to-image models on these generated images, we significantly enhance their compositional capabilities. For numerical composition, we observe relative increases of 29.3% and 19.5% for Stable Diffusion and PixArt-{\alpha}, respectively. Spatial composition sees even larger gains, with 60.7% for Stable Diffusion and 21.1% for PixArt-{\alpha}.
Authors: Rui Zhou, Jingbin Liu, Junbin Xie, Jianyu Zhang, Yingze Hu, Jiele Zhao
Abstract: Visual-inertial odometry (VIO) is widely used in various fields, such as robots, drones, and autonomous vehicles. However, real-world scenes often feature dynamic objects, compromising the accuracy of VIO. The diversity and partial occlusion of these objects present a tough challenge for existing dynamic VIO methods. To tackle this challenge, we introduce ADUGS-VINS, which integrates an enhanced SORT algorithm along with a promptable foundation model into VIO, thereby improving pose estimation accuracy in environments with diverse dynamic objects and frequent occlusions. We evaluated our proposed method using multiple public datasets representing various scenes, as well as in a real-world scenario involving diverse dynamic objects. The experimental results demonstrate that our proposed method performs impressively in multiple scenarios, outperforming other state-of-the-art methods. This highlights its remarkable generalization and adaptability in diverse dynamic environments, showcasing its potential to handle various dynamic objects in practical applications.
Authors: Xuanyu Zhang, Zecheng Tang, Zhipei Xu, Runyi Li, Youmin Xu, Bin Chen, Feng Gao, Jian Zhang
Abstract: With the rapid growth of generative AI and its widespread application in image editing, new risks have emerged regarding the authenticity and integrity of digital content. Existing versatile watermarking approaches suffer from trade-offs between tamper localization precision and visual quality. Constrained by the limited flexibility of previous framework, their localized watermark must remain fixed across all images. Under AIGC-editing, their copyright extraction accuracy is also unsatisfactory. To address these challenges, we propose OmniGuard, a novel augmented versatile watermarking approach that integrates proactive embedding with passive, blind extraction for robust copyright protection and tamper localization. OmniGuard employs a hybrid forensic framework that enables flexible localization watermark selection and introduces a degradation-aware tamper extraction network for precise localization under challenging conditions. Additionally, a lightweight AIGC-editing simulation layer is designed to enhance robustness across global and local editing. Extensive experiments show that OmniGuard achieves superior fidelity, robustness, and flexibility. Compared to the recent state-of-the-art approach EditGuard, our method outperforms it by 4.25dB in PSNR of the container image, 20.7% in F1-Score under noisy conditions, and 14.8% in average bit accuracy.
Authors: Jiongtong Hu, Wei Zhuo, Jun Cheng, Yingying Liu, Wufeng Xue, Dong Ni
Abstract: In clinical practice of echocardiography examinations, multiple planes containing the heart structures of different view are usually required in screening, diagnosis and treatment of cardiac disease. AI models for echocardiography have to be tailored for each specific plane due to the dramatic structure differences, thus resulting in repetition development and extra complexity. Effective solution for such a multi-plane segmentation (MPS) problem is highly demanded for medical images, yet has not been well investigated. In this paper, we propose a novel solution, EchoONE, for this problem with a SAM-based segmentation architecture, a prior-composable mask learning (PC-Mask) module for semantic-aware dense prompt generation, and a learnable CNN-branch with a simple yet effective local feature fusion and adaption (LFFA) module for SAM adapting. We extensively evaluated our method on multiple internal and external echocardiography datasets, and achieved consistently state-of-the-art performance for multi-source datasets with different heart planes. This is the first time that the MPS problem is solved in one model for echocardiography data. The code will be available at https://github.com/a2502503/EchoONE.
Authors: Youssef Shoeb, Nazir Nayal, Azarm Nowzad, Fatma G\"uney, Hanno Gottschalk
Abstract: Detecting road obstacles is essential for autonomous vehicles to navigate dynamic and complex traffic environments safely. Current road obstacle detection methods typically assign a score to each pixel and apply a threshold to generate final predictions. However, selecting an appropriate threshold is challenging, and the per-pixel classification approach often leads to fragmented predictions with numerous false positives. In this work, we propose a novel method that leverages segment-level features from visual foundation models and likelihood ratios to predict road obstacles directly. By focusing on segments rather than individual pixels, our approach enhances detection accuracy, reduces false positives, and offers increased robustness to scene variability. We benchmark our approach against existing methods on the RoadObstacle and LostAndFound datasets, achieving state-of-the-art performance without needing a predefined threshold.
Authors: Morgan B. Talbot, Gabriel Kreiman, James J. DiCarlo, Guy Gaziv
Abstract: The currently leading artificial neural network models of the visual ventral stream - which are derived from a combination of performance optimization and robustification methods - have demonstrated a remarkable degree of behavioral alignment with humans on visual categorization tasks. We show that image perturbations generated by these models can enhance the ability of humans to accurately report the ground truth class. Furthermore, we find that the same models can also be used out-of-the-box to predict the proportion of correct human responses to individual images, providing a simple, human-aligned estimator of the relative difficulty of each image. Motivated by these observations, we propose to augment visual learning in humans in a way that improves human categorization accuracy at test time. Our learning augmentation approach consists of (i) selecting images based on their model-estimated recognition difficulty, and (ii) applying image perturbations that aid recognition for novice learners. We find that combining these model-based strategies leads to categorization accuracy gains of 33-72% relative to control subjects without these interventions, on unmodified, randomly selected held-out test images. Beyond the accuracy gain, the training time for the augmented learning group was also shortened by 20-23%, despite both groups completing the same number of training trials. We demonstrate the efficacy of our approach in a fine-grained categorization task with natural images, as well as two tasks in clinically relevant image domains - histology and dermoscopy - where visual learning is notoriously challenging. To the best of our knowledge, our work is the first application of artificial neural networks to increase visual learning performance in humans by enhancing category-specific image features.
Authors: Xinhao Zhong, Bin Chen, Hao Fang, Xulin Gu, Shu-Tao Xia, En-Hui Yang
Abstract: Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset. However, current dataset distillation methods often result in synthetic datasets that are excessively difficult for networks to learn from, due to the compression of a substantial amount of information from the original data through metrics measuring feature similarity, e,g., distribution matching (DM). In this work, we introduce conditional mutual information (CMI) to assess the class-aware complexity of a dataset and propose a novel method by minimizing CMI. Specifically, we minimize the distillation loss while constraining the class-aware complexity of the synthetic dataset by minimizing its empirical CMI from the feature space of pre-trained networks, simultaneously. Conducting on a thorough set of experiments, we show that our method can serve as a general regularization method to existing DD methods and improve the performance and training efficiency.
Authors: Dengyang Jiang, Haoyu Wang, Lei Zhang, Wei Wei, Guang Dai, Mengmeng Wang, Jingdong Wang, Yanning Zhang
Abstract: Pre-training backbone networks on a general annotated dataset (e.g., ImageNet) that comprises numerous manually collected images with category annotations has proven to be indispensable for enhancing the generalization capacity of downstream visual tasks. However, those manually collected images often exhibit bias, which is non-transferable across either categories or domains, thus causing the model's generalization capacity degeneration. To mitigate this problem, we present an low-biased general annotated dataset generation framework (lbGen). Instead of expensive manual collection, we aim at directly generating low-biased images with category annotations. To achieve this goal, we propose to leverage the advantage of a multimodal foundation model (e.g., CLIP), in terms of aligning images in an low-biased semantic space defined by language. Specifically, we develop a bi-level semantic alignment loss, which not only forces all generated images to be consistent with the semantic distribution of all categories belonging to the target dataset in an adversarial learning manner, but also requires each generated image to match the semantic description of its category name. In addition, we further cast an existing image quality scoring model into a quality assurance loss to preserve the quality of the generated image. By leveraging these two loss functions, we can obtain an low-biased image generation model by simply fine-tuning a pre-trained diffusion model using only all category names in the target dataset as input. Experimental results confirm that, compared with the manually labeled dataset or other synthetic datasets, the utilization of our generated low-biased datasets leads to stable generalization capacity enhancement of different backbone networks across various tasks, especially in tasks where the manually labeled samples are scarce.
Authors: Ziyang Chen, Yiwen Ye, Feilong Tang, Yongsheng Pan, Yong Xia
Abstract: Domain generalization (DG) aims to enhance the ability of models trained on source domains to generalize effectively to unseen domains. Recently, Sharpness-Aware Minimization (SAM) has shown promise in this area by reducing the sharpness of the loss landscape to obtain more generalized models. However, SAM and its variants sometimes fail to guide the model toward a flat minimum, and their training processes exhibit limitations, hindering further improvements in model generalization. In this paper, we first propose an improved model training process aimed at encouraging the model to converge to a flat minima. To achieve this, we design a curvature metric that has a minimal effect when the model is far from convergence but becomes increasingly influential in indicating the curvature of the minima as the model approaches a local minimum. Then we derive a novel algorithm from this metric, called Meta Curvature-Aware Minimization (MeCAM), to minimize the curvature around the local minima. Specifically, the optimization objective of MeCAM simultaneously minimizes the regular training loss, the surrogate gap of SAM, and the surrogate gap of meta-learning. We provide theoretical analysis on MeCAM's generalization error and convergence rate, and demonstrate its superiority over existing DG methods through extensive experiments on five benchmark DG datasets, including PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet. Code will be available on GitHub.
Authors: Haoge Deng, Ting Pan, Haiwen Diao, Zhengxiong Luo, Yufeng Cui, Huchuan Lu, Shiguang Shan, Yonggang Qi, Xinlong Wang
Abstract: This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction and spatial set-by-set prediction. Unlike raster-scan prediction in prior autoregressive models or joint distribution modeling of fixed-length tokens in diffusion models, our approach maintains the causal property of GPT-style models for flexible in-context capabilities, while leveraging bidirectional modeling within individual frames for efficiency. With the proposed approach, we train a novel video autoregressive model without vector quantization, termed NOVA. Our results demonstrate that NOVA surpasses prior autoregressive video models in data efficiency, inference speed, visual fidelity, and video fluency, even with a much smaller model capacity, i.e., 0.6B parameters. NOVA also outperforms state-of-the-art image diffusion models in text-to-image generation tasks, with a significantly lower training cost. Additionally, NOVA generalizes well across extended video durations and enables diverse zero-shot applications in one unified model. Code and models are publicly available at https://github.com/baaivision/NOVA.
Authors: Koichi Ito, Yihan Zhu, Mahmoud Abdelrahman, Xiucheng Liang, Zicheng Fan, Yujun Hou, Tianhong Zhao, Rui Ma, Kunihiko Fujiwara, Jiani Ouyang, Matias Quintana, Filip Biljecki
Abstract: Street view imagery (SVI) has been instrumental in many studies in the past decade to understand and characterize street features and the built environment. Researchers across a variety of domains, such as transportation, health, architecture, human perception, and infrastructure have employed different methods to analyze SVI. However, these applications and image-processing procedures have not been standardized, and solutions have been implemented in isolation, often making it difficult for others to reproduce existing work and carry out new research. Using SVI for research requires multiple technical steps: accessing APIs for scalable data collection, preprocessing images to standardize formats, implementing computer vision models for feature extraction, and conducting spatial analysis. These technical requirements create barriers for researchers in urban studies, particularly those without extensive programming experience. We developed ZenSVI, a free and open-source Python package that integrates and implements the entire process of SVI analysis, supporting a wide range of use cases. Its end-to-end pipeline includes downloading SVI from multiple platforms (e.g., Mapillary and KartaView) efficiently, analyzing metadata of SVI, applying computer vision models to extract target features, transforming SVI into different projections (e.g., fish-eye and perspective) and different formats (e.g., depth map and point cloud), visualizing analyses with maps and plots, and exporting outputs to other software tools. We demonstrated its use in Singapore through a case study of data quality assessment and clustering analysis in a streamlined manner. Our software improves the transparency, reproducibility, and scalability of research relying on SVI and supports researchers in conducting urban analyses efficiently. Its modular design facilitates extensions of the package for new use cases.
Authors: Arun K. Sharma, Shubhobrata Bhattacharya, Motahar Reza, Bishakh Bhattacharya
Abstract: Traditional biometric systems have encountered significant setbacks due to various unavoidable factors, for example, face recognition-based biometrics fails due to the wearing of face masks and fingerprints create hygiene concerns. This paper proposes a novel lightweight cross-spectral vision transformer (CS-ViT) for biometric authentication using forehead subcutaneous vein patterns and periocular patterns, offering a promising alternative to traditional methods, capable of performing well even with the face masks and without any physical touch. The proposed framework comprises a cross-spectral dual-channel architecture designed to handle two distinct biometric traits and to capture inter-dependencies in terms of relative spectral patterns. Each channel consists of a Phase-Only Correlation Cross-Spectral Attention (POC-CSA) that captures their individual as well as correlated patterns. The computation of cross-spectral attention using POC extracts the phase correlation in the spatial features. Therefore, it is robust against the resolution/intensity variations and illumination of the input images, assuming both biometric traits are from the same person. The lightweight model is suitable for edge device deployment. The performance of the proposed algorithm was rigorously evaluated using the Forehead Subcutaneous Vein Pattern and Periocular Biometric Pattern (FSVP-PBP) database. The results demonstrated the superiority of the algorithm over state-of-the-art methods, achieving a remarkable classification accuracy of 98.8% with the combined vein and periocular patterns.
Authors: Nikolaos Stathoulopoulos, Christoforos Kanellakis, George Nikolakopoulos
Abstract: Typical LiDAR SLAM architectures feature a front-end for odometry estimation and a back-end for refining and optimizing the trajectory and map, commonly through loop closures. However, loop closure detection in large-scale missions presents significant computational challenges due to the need to identify, verify, and process numerous candidate pairs for pose graph optimization. Keyframe sampling bridges the front-end and back-end by selecting frames for storing and processing during global optimization. This article proposes an online keyframe sampling approach that constructs the pose graph using the most impactful keyframes for loop closure. We introduce the Minimal Subset Approach (MSA), which optimizes two key objectives: redundancy minimization and information preservation, implemented within a sliding window framework. By operating in the feature space rather than 3-D space, MSA efficiently reduces redundant keyframes while retaining essential information. In sum, evaluations on diverse public datasets show that the proposed approach outperforms naive methods in reducing false positive rates in place recognition, while delivering superior ATE and RPE in metric localization, without the need for manual parameter tuning. Additionally, MSA demonstrates efficiency and scalability by reducing memory usage and computational overhead during loop closure detection and pose graph optimization.
Authors: Xinbin Yuan, Zhaohui Zheng, Yuxuan Li, Xialei Liu, Li Liu, Xiang Li, Qibin Hou, Ming-Ming Cheng
Abstract: While witnessed with rapid development, remote sensing object detection remains challenging for detecting high aspect ratio objects. This paper shows that large strip convolutions are good feature representation learners for remote sensing object detection and can detect objects of various aspect ratios well. Based on large strip convolutions, we build a new network architecture called Strip R-CNN, which is simple, efficient, and powerful. Unlike recent remote sensing object detectors that leverage large-kernel convolutions with square shapes, our Strip R-CNN takes advantage of sequential orthogonal large strip convolutions in our backbone network StripNet to capture spatial information. In addition, we improve the localization capability of remote-sensing object detectors by decoupling the detection heads and equipping the localization branch with strip convolutions in our strip head. Extensive experiments on several benchmarks, for example DOTA, FAIR1M, HRSC2016, and DIOR, show that our Strip R-CNN can greatly improve previous work. In particular, our 30M model achieves 82.75% mAP on DOTA-v1.0, setting a new state-of-the-art record. Our code will be made publicly available.Code is available at https://github.com/YXB-NKU/Strip-R-CNN.
Authors: Shaolei Zhang, Qingkai Fang, Zhe Yang, Yang Feng
Abstract: The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and textual instructions into the context of large language models (LLMs), where large-scale parameters and numerous context tokens (predominantly vision tokens) result in substantial computational overhead. Previous efforts towards efficient LMMs always focus on replacing the LLM backbone with smaller models, while neglecting the crucial issue of token quantity. In this paper, we introduce LLaVA-Mini, an efficient LMM with minimal vision tokens. To achieve a high compression ratio of vision tokens while preserving visual information, we first analyze how LMMs understand vision tokens and find that most vision tokens only play a crucial role in the early layers of LLM backbone, where they mainly fuse visual information into text tokens. Building on this finding, LLaVA-Mini introduces modality pre-fusion to fuse visual information into text tokens in advance, thereby facilitating the extreme compression of vision tokens fed to LLM backbone into one token. LLaVA-Mini is a unified large multimodal model that can support the understanding of images, high-resolution images, and videos in an efficient manner. Experiments across 11 image-based and 7 video-based benchmarks demonstrate that LLaVA-Mini outperforms LLaVA-v1.5 with just 1 vision token instead of 576. Efficiency analyses reveal that LLaVA-Mini can reduce FLOPs by 77%, deliver low-latency responses within 40 milliseconds, and process over 10,000 frames of video on the GPU hardware with 24GB of memory.
Authors: Seungjoo Shin, Jaesik Park, Sunghyun Cho
Abstract: We present LocoGS, a locality-aware 3D Gaussian Splatting (3DGS) framework that exploits the spatial coherence of 3D Gaussians for compact modeling of volumetric scenes. To this end, we first analyze the local coherence of 3D Gaussian attributes, and propose a novel locality-aware 3D Gaussian representation that effectively encodes locally-coherent Gaussian attributes using a neural field representation with a minimal storage requirement. On top of the novel representation, LocoGS is carefully designed with additional components such as dense initialization, an adaptive spherical harmonics bandwidth scheme and different encoding schemes for different Gaussian attributes to maximize compression performance. Experimental results demonstrate that our approach outperforms the rendering quality of existing compact Gaussian representations for representative real-world 3D datasets while achieving from 54.6$\times$ to 96.6$\times$ compressed storage size and from 2.1$\times$ to 2.4$\times$ rendering speed than 3DGS. Even our approach also demonstrates an averaged 2.4$\times$ higher rendering speed than the state-of-the-art compression method with comparable compression performance.
Authors: Tingxuan Chen, Kun Yuan, Vinkle Srivastav, Nassir Navab, Nicolas Padoy
Abstract: Purpose: Surgical workflow analysis is crucial for improving surgical efficiency and safety. However, previous studies rely heavily on large-scale annotated datasets, posing challenges in cost, scalability, and reliance on expert annotations. To address this, we propose Surg-FTDA (Few-shot Text-driven Adaptation), designed to handle various surgical workflow analysis tasks with minimal paired image-label data. Methods: Our approach has two key components. First, Few-shot selection-based modality alignment selects a small subset of images and aligns their embeddings with text embeddings from the downstream task, bridging the modality gap. Second, Text-driven adaptation leverages only text data to train a decoder, eliminating the need for paired image-text data. This decoder is then applied to aligned image embeddings, enabling image-related tasks without explicit image-text pairs. Results: We evaluate our approach to generative tasks (image captioning) and discriminative tasks (triplet recognition and phase recognition). Results show that Surg-FTDA outperforms baselines and generalizes well across downstream tasks. Conclusion: We propose a text-driven adaptation approach that mitigates the modality gap and handles multiple downstream tasks in surgical workflow analysis, with minimal reliance on large annotated datasets. The code and dataset will be released in https://github.com/CAMMA-public/Surg-FTDA
Authors: Zhihe Yang, Xufang Luo, Dongqi Han, Yunjian Xu, Dongsheng Li
Abstract: Hallucination remains a major challenge for Large Vision-Language Models (LVLMs). Direct Preference Optimization (DPO) has gained increasing attention as a simple solution to hallucination issues. It directly learns from constructed preference pairs that reflect the severity of hallucinations in responses to the same prompt and image. Nonetheless, different data construction methods in existing works bring notable performance variations. We identify a crucial factor here: outcomes are largely contingent on whether the constructed data aligns on-policy w.r.t the initial (reference) policy of DPO. Theoretical analysis suggests that learning from off-policy data is impeded by the presence of KL-divergence between the updated policy and the reference policy. From the perspective of dataset distribution, we systematically summarize the inherent flaws in existing algorithms that employ DPO to address hallucination issues. To alleviate the problems, we propose On-Policy Alignment (OPA)-DPO framework, which uniquely leverages expert feedback to correct hallucinated responses and aligns both the original and expert-revised responses in an on-policy manner. Notably, with only 4.8k data, OPA-DPO achieves an additional reduction in the hallucination rate of LLaVA-1.5-7B: 13.26% on the AMBER benchmark and 5.39% on the Object-Hal benchmark, compared to the previous SOTA algorithm trained with 16k samples. Our implementation is available at https://github.com/zhyang2226/OPA-DPO.
Authors: Shibang Liu, Xuemei Xie, Guangming Shi
Abstract: Parse graphs of the human body can be obtained in the human brain to help humans complete the human Pose Estimation better (HPE). It contains a hierarchical structure, like a tree structure, and context relations among nodes. To equip models with such capabilities, many researchers predefine the parse graph of body structure to design HPE frameworks. However, these frameworks struggle to adapt to instances that deviate from the predefined parse graph and are often parameter-heavy. Unlike them, we view the feature map holistically, much like the human body. It can be optimized using parse graphs, where each node's feature is an implicit expression rather than a fixed one. This allows it to adapt to more instances, unconstrained by rigid structural features. In this paper, we design the Refinement Module based on the Parse Graph of feature map (RMPG), which includes two stages: top-down decomposition and bottom-up combination. In the first stage, the feature map is decomposed into multiple sub-feature maps along the channel. In the second stage, the context relations of sub-feature maps are calculated to obtain their respective context information and the sub-feature maps with context information are concatenated along channels to obtain the refined feature map. Additionally, we design a hierarchical network with fewer parameters using multiple RMPG modules to model the context relations and hierarchies in the parse graph of body structure for HPE, some of which are supervised to obtain context relations among body parts. Our network achieves excellent results on multiple mainstream human pose datasets. More importantly, the effectiveness of RMPG is proven on different methods. The code of RMPG will be open.
Authors: Zixuan Chen, Yujin Wang, Xin Cai, Zhiyuan You, Zheming Lu, Fan Zhang, Shi Guo, Tianfan Xue
Abstract: Capturing high dynamic range (HDR) scenes is one of the most important issues in camera design. Majority of cameras use exposure fusion technique, which fuses images captured by different exposure levels, to increase dynamic range. However, this approach can only handle images with limited exposure difference, normally 3-4 stops. When applying to very high dynamic scenes where a large exposure difference is required, this approach often fails due to incorrect alignment or inconsistent lighting between inputs, or tone mapping artifacts. In this work, we propose UltraFusion, the first exposure fusion technique that can merge input with 9 stops differences. The key idea is that we model the exposure fusion as a guided inpainting problem, where the under-exposed image is used as a guidance to fill the missing information of over-exposed highlight in the over-exposed region. Using under-exposed image as a soft guidance, instead of a hard constrain, our model is robust to potential alignment issue or lighting variations. Moreover, utilizing the image prior of the generative model, our model also generates natural tone mapping, even for very high-dynamic range scene. Our approach outperforms HDR-Transformer on latest HDR benchmarks. Moreover, to test its performance in ultra high dynamic range scene, we capture a new real-world exposure fusion benchmark, UltraFusion Dataset, with exposure difference up to 9 stops, and experiments show that \model~can generate beautiful and high-quality fusion results under various scenarios. An online demo is provided at https://openimaginglab.github.io/UltraFusion/.
Authors: Jiacheng Zuo, Haibo Hu, Zikang Zhou, Yufei Cui, Ziquan Liu, Jianping Wang, Nan Guan, Jin Wang, Chun Jason Xue
Abstract: In the pursuit of robust autonomous driving systems, models trained on real-world datasets often struggle to adapt to new environments, particularly when confronted with corner cases such as extreme weather conditions. Collecting these corner cases in the real world is non-trivial, which necessitates the use of simulators for validation. However,the high computational cost and the domain gap in data distribution have hindered the seamless transition between real and simulated driving scenarios. To tackle this challenge, we propose Retrieval-Augmented Learning for Autonomous Driving (RALAD), a novel framework designed to bridge the real-to-sim gap at a low cost. RALAD features three primary designs, including (1) domain adaptation via an enhanced Optimal Transport (OT) method that accounts for both individual and grouped image distances, (2) a simple and unified framework that can be applied to various models, and (3) efficient fine-tuning techniques that freeze the computationally expensive layers while maintaining robustness. Experimental results demonstrate that RALAD compensates for the performance degradation in simulated environments while maintaining accuracy in real-world scenarios across three different models. Taking Cross View as an example, the mIOU and mAP metrics in real-world scenarios remain stable before and after RALAD fine-tuning, while in simulated environments,the mIOU and mAP metrics are improved by 10.30% and 12.29%, respectively. Moreover, the re-training cost of our approach is reduced by approximately 88.1%. Our code is available at https://github.com/JiachengZuo/RALAD.git.
Authors: Ruicheng Zhang, Haowei Guo, Zeyu Zhang, Puxin Yan, Shen Zhao
Abstract: Multi-organ segmentation is a critical yet challenging task due to complex anatomical backgrounds, blurred boundaries, and diverse morphologies. This study introduces the Gradient-aware Adaptive Momentum Evolution Deep Snake (GAMED-Snake) model, which establishes a novel paradigm for contour-based segmentation by integrating gradient-based learning with adaptive momentum evolution mechanisms. The GAMED-Snake model incorporates three major innovations: First, the Distance Energy Map Prior (DEMP) generates a pixel-level force field that effectively attracts contour points towards the true boundaries, even in scenarios with complex backgrounds and blurred edges. Second, the Differential Convolution Inception Module (DCIM) precisely extracts comprehensive energy gradients, significantly enhancing segmentation accuracy. Third, the Adaptive Momentum Evolution Mechanism (AMEM) employs cross-attention to establish dynamic features across different iterations of evolution, enabling precise boundary alignment for diverse morphologies. Experimental results on four challenging multi-organ segmentation datasets demonstrate that GAMED-Snake improves the mDice metric by approximately 2% compared to state-of-the-art methods. Code will be available at https://github.com/SYSUzrc/GAMED-Snake.
Authors: Lianqing Zheng, Jianan Liu, Runwei Guan, Long Yang, Shouyi Lu, Yuanzhe Li, Xiaokai Bai, Jie Bai, Zhixiong Ma, Hui-Liang Shen, Xichan Zhu
Abstract: 3D object detection and occupancy prediction are critical tasks in autonomous driving, attracting significant attention. Despite the potential of recent vision-based methods, they encounter challenges under adverse conditions. Thus, integrating cameras with next-generation 4D imaging radar to achieve unified multi-task perception is highly significant, though research in this domain remains limited. In this paper, we propose Doracamom, the first framework that fuses multi-view cameras and 4D radar for joint 3D object detection and semantic occupancy prediction, enabling comprehensive environmental perception. Specifically, we introduce a novel Coarse Voxel Queries Generator that integrates geometric priors from 4D radar with semantic features from images to initialize voxel queries, establishing a robust foundation for subsequent Transformer-based refinement. To leverage temporal information, we design a Dual-Branch Temporal Encoder that processes multi-modal temporal features in parallel across BEV and voxel spaces, enabling comprehensive spatio-temporal representation learning. Furthermore, we propose a Cross-Modal BEV-Voxel Fusion module that adaptively fuses complementary features through attention mechanisms while employing auxiliary tasks to enhance feature quality. Extensive experiments on the OmniHD-Scenes, View-of-Delft (VoD), and TJ4DRadSet datasets demonstrate that Doracamom achieves state-of-the-art performance in both tasks, establishing new benchmarks for multi-modal 3D perception. Code and models will be publicly available.
Authors: Kyeongmin Yeo, Jaihoon Kim, Minhyuk Sung
Abstract: We propose a zero-shot method for generating images in arbitrary spaces (e.g., a sphere for 360{\deg} panoramas and a mesh surface for texture) using a pretrained image diffusion model. The zero-shot generation of various visual content using a pretrained image diffusion model has been explored mainly in two directions. First, Diffusion Synchronization-performing reverse diffusion processes jointly across different projected spaces while synchronizing them in the target space-generates high-quality outputs when enough conditioning is provided, but it struggles in its absence. Second, Score Distillation Sampling-gradually updating the target space data through gradient descent-results in better coherence but often lacks detail. In this paper, we reveal for the first time the interconnection between these two methods while highlighting their differences. To this end, we propose StochSync, a novel approach that combines the strengths of both, enabling effective performance with weak conditioning. Our experiments demonstrate that StochSync provides the best performance in 360{\deg} panorama generation (where image conditioning is not given), outperforming previous finetuning-based methods, and also delivers comparable results in 3D mesh texturing (where depth conditioning is provided) with previous methods.
Authors: Adil Kaan Akan, Yucel Yemez
Abstract: We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our method preserves the generative power of pretrained diffusion models, while avoiding their text-centric conditioning bias. We also incorporate an additional guidance loss into our architecture to align cross-attention from adapter layers with slot attention. This enhances the alignment of our model with the objects in the input image without using external supervision. Experimental results show that our method outperforms state-of-the-art techniques in object discovery and image generation tasks across multiple datasets, including those with real images. Furthermore, we demonstrate through experiments that our method performs remarkably well on complex real-world images for compositional generation, in contrast to other slot-based generative methods in the literature. The project page can be found at https://kaanakan.github.io/SlotAdapt/.
Authors: Muxi Chen, Chenchen Zhao, Qiang Xu
Abstract: Despite the significant success of deep learning models in computer vision, they often exhibit systematic failures on specific data subsets, known as error slices. Identifying and mitigating these error slices is crucial to enhancing model robustness and reliability in real-world scenarios. In this paper, we introduce HiBug2, an automated framework for error slice discovery and model repair. HiBug2 first generates task-specific visual attributes to highlight instances prone to errors through an interpretable and structured process. It then employs an efficient slice enumeration algorithm to systematically identify error slices, overcoming the combinatorial challenges that arise during slice exploration. Additionally, HiBug2 extends its capabilities by predicting error slices beyond the validation set, addressing a key limitation of prior approaches. Extensive experiments across multiple domains, including image classification, pose estimation, and object detection - show that HiBug2 not only improves the coherence and precision of identified error slices but also significantly enhances the model repair capabilities.
Authors: Xiangyu Gao, Yu Dai, Benliu Qiu, Lanxiao Wang, Heqian Qiu, Hongliang Li
Abstract: Owing to large-scale image-text contrastive training, pre-trained vision language model (VLM) like CLIP shows superior open-vocabulary recognition ability. Most existing open-vocabulary object detectors attempt to utilize the pre-trained VLMs to attain generalized representation. F-ViT uses the pre-trained visual encoder as the backbone network and freezes it during training. However, its frozen backbone doesn't benefit from the labeled data to strengthen the representation for detection. Therefore, we propose a novel two-branch backbone network, named as \textbf{V}iT-Feature-\textbf{M}odulated Multi-Scale \textbf{C}onvolutional Network (VMCNet), which consists of a trainable convolutional branch, a frozen pre-trained ViT branch and a VMC module. The trainable CNN branch could be optimized with labeled data while the frozen pre-trained ViT branch could keep the representation ability derived from large-scale pre-training. Then, the proposed VMC module could modulate the multi-scale CNN features with the representations from ViT branch. With this proposed mixed structure, the detector is more likely to discover objects of novel categories. Evaluated on two popular benchmarks, our method boosts the detection performance on novel category and outperforms state-of-the-art methods. On OV-COCO, the proposed method achieves 44.3 AP$_{50}^{\mathrm{novel}}$ with ViT-B/16 and 48.5 AP$_{50}^{\mathrm{novel}}$ with ViT-L/14. On OV-LVIS, VMCNet with ViT-B/16 and ViT-L/14 reaches 27.8 and 38.4 mAP$_{r}$.
Authors: Siyu Zhang, Wenzhe Liu, Yeming Chen, Yiming Wu, Heming Zheng, Cheng Cheng
Abstract: To bridge the semantic gap between vision and language (VL), it is necessary to develop a good alignment strategy, which includes handling semantic diversity, abstract representation of visual information, and generalization ability of models. Recent works use detector-based bounding boxes or patches with regular partitions to represent visual semantics. While current paradigms have made strides, they are still insufficient for fully capturing the nuanced contextual relations among various objects. This paper proposes a comprehensive visual semantic representation module, necessitating the utilization of panoptic segmentation to generate coherent fine-grained semantic features. Furthermore, we propose a novel Graph Spiking Hybrid Network (GSHN) that integrates the complementary advantages of Spiking Neural Networks (SNNs) and Graph Attention Networks (GATs) to encode visual semantic information. Intriguingly, the model not only encodes the discrete and continuous latent variables of instances but also adeptly captures both local and global contextual features, thereby significantly enhancing the richness and diversity of semantic representations. Leveraging the spatiotemporal properties inherent in SNNs, we employ contrastive learning (CL) to enhance the similarity-based representation of embeddings. This strategy alleviates the computational overhead of the model and enriches meaningful visual representations by constructing positive and negative sample pairs. We design an innovative pre-training method, Spiked Text Learning (STL), which uses text features to improve the encoding ability of discrete semantics. Experiments show that the proposed GSHN exhibits promising results on multiple VL downstream tasks.
Authors: Joseph Fioresi, Ishan Rajendrakumar Dave, Mubarak Shah
Abstract: Bias in machine learning models can lead to unfair decision making, and while it has been well-studied in the image and text domains, it remains underexplored in action recognition. Action recognition models often suffer from background bias (i.e., inferring actions based on background cues) and foreground bias (i.e., relying on subject appearance), which can be detrimental to real-life applications such as autonomous vehicles or assisted living monitoring. While prior approaches have mainly focused on mitigating background bias using specialized augmentations, we thoroughly study both foreground and background bias. We propose ALBAR, a novel adversarial training method that mitigates foreground and background biases without requiring specialized knowledge of the bias attributes. Our framework applies an adversarial cross-entropy loss to the sampled static clip (where all the frames are the same) and aims to make its class probabilities uniform using a proposed entropy maximization loss. Additionally, we introduce a gradient penalty loss for regularization against the debiasing process. We evaluate our method on established background and foreground bias protocols, setting a new state-of-the-art and strongly improving combined debiasing performance by over 12% absolute on HMDB51. Furthermore, we identify an issue of background leakage in the existing UCF101 protocol for bias evaluation which provides a shortcut to predict actions and does not provide an accurate measure of the debiasing capability of a model. We address this issue by proposing more fine-grained segmentation boundaries for the actor, where our method also outperforms existing approaches. Project Page: https://joefioresi718.github.io/ALBAR_webpage/
Authors: Andrew Van Horn, Lauryn Smith, Mahamad Mahmoud, Michael McMaster, Clara Pinchbeck, Ina Martin, Andrew Lininger, Anthony Ingrisano, Adam Lowe, Carlos Bayod, Elizabeth Bolman, Kenneth Singer, Michael Hinczewski
Abstract: The history of art has seen significant shifts in the manner in which artworks are created, making understanding of creative processes a central question in technical art history. In the Renaissance and Early Modern period, paintings were largely produced by master painters directing workshops of apprentices who often contributed to projects. The masters varied significantly in artistic and managerial styles, meaning different combinations of artists and implements might be seen both between masters and within workshops or even individual canvases. Information on how different workshops were managed and the processes by which artworks were created remains elusive. Machine learning methods have potential to unearth new information about artists' creative processes by extending the analysis of brushwork to a microscopic scale. Analysis of workshop paintings, however, presents a challenge in that documentation of the artists and materials involved is sparse, meaning external examples are not available to train networks to recognize their contributions. Here we present a novel machine learning approach we call pairwise assignment training for classifying heterogeneity (PATCH) that is capable of identifying individual artistic practice regimes with no external training data, or "ground truth." The method achieves unsupervised results by supervised means, and outperforms both simple statistical procedures and unsupervised machine learning methods. We apply this method to two historical paintings by the Spanish Renaissance master, El Greco: The Baptism of Christ and Christ on the Cross with Landscape, and our findings regarding the former potentially challenge previous work that has assigned the painting to workshop members. Further, the results of our analyses create a measure of heterogeneity of artistic practice that can be used to characterize artworks across time and space.
Authors: Zhihao Guo, Jingxuan Su, Shenglin Wang, Jinlong Fan, Jing Zhang, Liangxiu Han, Peng Wang
Abstract: 3D Gaussian Splatting has emerged as an efficient photorealistic novel view synthesis method. However, its reliance on sparse Structure-from-Motion (SfM) point clouds consistently compromises the scene reconstruction quality. To address these limitations, this paper proposes a novel 3D reconstruction framework Gaussian Processes Gaussian Splatting (GP-GS), where a multi-output Gaussian Process model is developed to achieve adaptive and uncertainty-guided densification of sparse SfM point clouds. Specifically, we propose a dynamic sampling and filtering pipeline that adaptively expands the SfM point clouds by leveraging GP-based predictions to infer new candidate points from the input 2D pixels and depth maps. The pipeline utilizes uncertainty estimates to guide the pruning of high-variance predictions, ensuring geometric consistency and enabling the generation of dense point clouds. The densified point clouds provide high-quality initial 3D Gaussians to enhance reconstruction performance. Extensive experiments conducted on synthetic and real-world datasets across various scales validate the effectiveness and practicality of the proposed framework.
Authors: Peng-Fei Zhang, Guangdong Bai, Zi Huang
Abstract: Current adversarial attacks for evaluating the robustness of vision-language pre-trained (VLP) models in multi-modal tasks suffer from limited transferability, where attacks crafted for a specific model often struggle to generalize effectively across different models, limiting their utility in assessing robustness more broadly. This is mainly attributed to the over-reliance on model-specific features and regions, particularly in the image modality. In this paper, we propose an elegant yet highly effective method termed Meticulous Adversarial Attack (MAA) to fully exploit model-independent characteristics and vulnerabilities of individual samples, achieving enhanced generalizability and reduced model dependence. MAA emphasizes fine-grained optimization of adversarial images by developing a novel resizing and sliding crop (RScrop) technique, incorporating a multi-granularity similarity disruption (MGSD) strategy. Extensive experiments across diverse VLP models, multiple benchmark datasets, and a variety of downstream tasks demonstrate that MAA significantly enhances the effectiveness and transferability of adversarial attacks. A large cohort of performance studies is conducted to generate insights into the effectiveness of various model configurations, guiding future advancements in this domain.
Authors: Fouad Boutaleb, Emery Pierson, Nicolas Doudeau, Cl\'emence Nineuil, Ali Amad, Mohamed Daoudi
Abstract: Depression and anxiety are prevalent mental health disorders that frequently cooccur, with anxiety significantly influencing both the manifestation and treatment of depression. An accurate assessment of anxiety levels in individuals with depression is crucial to develop effective and personalized treatment plans. This study proposes a new noninvasive method for quantifying anxiety severity by analyzing head movements -- specifically speed, acceleration, and angular displacement -- during video-recorded interviews with patients suffering from severe depression. Using data from a new CALYPSO Depression Dataset, we extracted head motion characteristics and applied regression analysis to predict clinically evaluated anxiety levels. Our results demonstrate a high level of precision, achieving a mean absolute error (MAE) of 0.35 in predicting the severity of psychological anxiety based on head movement patterns. This indicates that our approach can enhance the understanding of anxiety's role in depression and assist psychiatrists in refining treatment strategies for individuals.
Authors: Youssef Shoeb, Azarm Nowzad, Hanno Gottschalk
Abstract: Advances in machine learning methods for computer vision tasks have led to their consideration for safety-critical applications like autonomous driving. However, effectively integrating these methods into the automotive development lifecycle remains challenging. Since the performance of machine learning algorithms relies heavily on the training data provided, the data and model development lifecycle play a key role in successfully integrating these components into the product development lifecycle. Existing models frequently encounter difficulties recognizing or adapting to novel instances not present in the original training dataset. This poses a significant risk for reliable deployment in dynamic environments. To address this challenge, we propose an adaptive neural network architecture and an iterative development framework that enables users to efficiently incorporate previously unknown objects into the current perception system. Our approach builds on continuous learning, emphasizing the necessity of dynamic updates to reflect real-world deployment conditions. Specifically, we introduce a pipeline with three key components: (1) a scalable network extension strategy to integrate new classes while preserving existing performance, (2) a dynamic OoD detection component that requires no additional retraining for newly added classes, and (3) a retrieval-based data augmentation process tailored for safety-critical deployments. The integration of these components establishes a pragmatic and adaptive pipeline for the continuous evolution of perception systems in the context of autonomous driving.
Authors: Yunfei Liu, Lei Zhu, Lijian Lin, Ye Zhu, Ailing Zhang, Yu Li
Abstract: 3D facial reconstruction from a single in-the-wild image is a crucial task in human-centered computer vision tasks. While existing methods can recover accurate facial shapes, there remains significant space for improvement in fine-grained expression capture. Current approaches struggle with irregular mouth shapes, exaggerated expressions, and asymmetrical facial movements. We present TEASER (Token EnhAnced Spatial modeling for Expressions Reconstruction), which addresses these challenges and enhances 3D facial geometry performance. TEASER tackles two main limitations of existing methods: insufficient photometric loss for self-reconstruction and inaccurate localization of subtle expressions. We introduce a multi-scale tokenizer to extract facial appearance information. Combined with a neural renderer, these tokens provide precise geometric guidance for expression reconstruction. Furthermore, TEASER incorporates a pose-dependent landmark loss to further improve geometric performances. Our approach not only significantly enhances expression reconstruction quality but also offers interpretable tokens suitable for various downstream applications, such as photorealistic facial video driving, expression transfer, and identity swapping. Quantitative and qualitative experimental results across multiple datasets demonstrate that TEASER achieves state-of-the-art performance in precise expression reconstruction.
Authors: Silong Yong, Venkata Nagarjun Pudureddiyur Manivannan, Bernhard Kerbl, Zifu Wan, Simon Stepputtis, Katia Sycara, Yaqi Xie
Abstract: Decomposing geometry, materials and lighting from a set of images, namely inverse rendering, has been a long-standing problem in computer vision and graphics. Recent advances in neural rendering enable photo-realistic and plausible inverse rendering results. The emergence of 3D Gaussian Splatting has boosted it to the next level by showing real-time rendering potentials. An intuitive finding is that the models used for inverse rendering do not take into account the dependency of opacity w.r.t. material properties, namely cross section, as suggested by optics. Therefore, we develop a novel approach that adds this dependency to the modeling itself. Inspired by radiative transfer, we augment the opacity term by introducing a neural network that takes as input material properties to provide modeling of cross section and a physically correct activation function. The gradients for material properties are therefore not only from color but also from opacity, facilitating a constraint for their optimization. Therefore, the proposed method incorporates more accurate physical properties compared to previous works. We implement our method into 3 different baselines that use Gaussian Splatting for inverse rendering and achieve significant improvements universally in terms of novel view synthesis and material modeling.
Authors: Shangzhan Zhang, Jianyuan Wang, Yinghao Xu, Nan Xue, Christian Rupprecht, Xiaowei Zhou, Yujun Shen, Gordon Wetzstein
Abstract: We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications. Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes. Concretely, FLARE starts with camera pose estimation, whose results condition the subsequent learning of geometric structure and appearance, optimized through the objectives of geometry reconstruction and novel-view synthesis. Utilizing large-scale public datasets for training, our method delivers state-of-the-art performance in the tasks of pose estimation, geometry reconstruction, and novel view synthesis, while maintaining the inference efficiency (i.e., less than 0.5 seconds). The project page and code can be found at: https://zhanghe3z.github.io/FLARE/
Authors: Wei Dai, Steven Wang, Jun Liu
Abstract: Efficient evaluation of three-dimensional (3D) medical images is crucial for diagnostic and therapeutic practices in healthcare. Recent years have seen a substantial uptake in applying deep learning and computer vision to analyse and interpret medical images. Traditional approaches, such as convolutional neural networks (CNNs) and vision transformers (ViTs), face significant computational challenges, prompting the need for architectural advancements. Recent efforts have led to the introduction of novel architectures like the ``Mamba'' model as alternative solutions to traditional CNNs or ViTs. The Mamba model excels in the linear processing of one-dimensional data with low computational demands. However, Mamba's potential for 3D medical image analysis remains underexplored and could face significant computational challenges as the dimension increases. This manuscript presents MobileViM, a streamlined architecture for efficient segmentation of 3D medical images. In the MobileViM network, we invent a new dimension-independent mechanism and a dual-direction traversing approach to incorporate with a vision-Mamba-based framework. MobileViM also features a cross-scale bridging technique to improve efficiency and accuracy across various medical imaging modalities. With these enhancements, MobileViM achieves segmentation speeds exceeding 90 frames per second (FPS) on a single graphics processing unit (i.e., NVIDIA RTX 4090). This performance is over 24 FPS faster than the state-of-the-art deep learning models for processing 3D images with the same computational resources. In addition, experimental evaluations demonstrate that MobileViM delivers superior performance, with Dice similarity scores reaching 92.72%, 86.69%, 80.46%, and 77.43% for PENGWIN, BraTS2024, ATLAS, and Toothfairy2 datasets, respectively, which significantly surpasses existing models.
Authors: Jiangyuan Liu, Hongxuan Ma, Yuxin Guo, Yuhao Zhao, Chi Zhang, Wei Sui, Wei Zou
Abstract: Transparent object perception is indispensable for numerous robotic tasks. However, accurately segmenting and estimating the depth of transparent objects remain challenging due to complex optical properties. Existing methods primarily delve into only one task using extra inputs or specialized sensors, neglecting the valuable interactions among tasks and the subsequent refinement process, leading to suboptimal and blurry predictions. To address these issues, we propose a monocular framework, which is the first to excel in both segmentation and depth estimation of transparent objects, with only a single-image input. Specifically, we devise a novel semantic and geometric fusion module, effectively integrating the multi-scale information between tasks. In addition, drawing inspiration from human perception of objects, we further incorporate an iterative strategy, which progressively refines initial features for clearer results. Experiments on two challenging synthetic and real-world datasets demonstrate that our model surpasses state-of-the-art monocular, stereo, and multi-view methods by a large margin of about 38.8%-46.2% with only a single RGB input. Codes and models are publicly available at https://github.com/L-J-Yuan/MODEST.
Authors: Hongchen Wei, Zhihong Tan, Yaosi Hu, Chang Wen Chen, Zhenzhong Chen
Abstract: Large Multimodal Models (LMMs) have demonstrated exceptional performance in video captioning tasks, particularly for short videos. However, as the length of the video increases, generating long, detailed captions becomes a significant challenge. In this paper, we investigate the limitations of LMMs in generating long captions for long videos. Our analysis reveals that open-source LMMs struggle to consistently produce outputs exceeding 300 words, leading to incomplete or overly concise descriptions of the visual content. This limitation hinders the ability of LMMs to provide comprehensive and detailed captions for long videos, ultimately missing important visual information. Through controlled experiments, we find that the scarcity of paired examples with long-captions during training is the primary factor limiting the model's output length. However, manually annotating long-caption examples for long-form videos is time-consuming and expensive. To overcome the annotation bottleneck, we propose the LongCaption-Agent, a framework that synthesizes long caption data by hierarchical semantic aggregation. % aggregating multi-level descriptions. Using LongCaption-Agent, we curated a new long-caption dataset, LongCaption-10K. We also develop LongCaption-Bench, a benchmark designed to comprehensively evaluate the quality of long captions generated by LMMs. By incorporating LongCaption-10K into training, we enable LMMs to generate captions exceeding 1,000 words for long-form videos, while maintaining high output quality. In LongCaption-Bench, our model achieved State-of-The-Art performance, even surpassing larger proprietary models like GPT4o.
Authors: Xiangbin Wei
Abstract: Building on recent advances in Bayesian statistics and image denoising, we propose Noise2Score3D, a fully unsupervised framework for point cloud denoising that addresses the critical challenge of limited availability of clean data. Noise2Score3D learns the gradient of the underlying point cloud distribution directly from noisy data, eliminating the need for clean data during training. By leveraging Tweedie's formula, our method performs inference in a single step, avoiding the iterative processes used in existing unsupervised methods, thereby improving both performance and efficiency. Experimental results demonstrate that Noise2Score3D achieves state-of-the-art performance on standard benchmarks, outperforming other unsupervised methods in Chamfer distance and point-to-mesh metrics, and rivaling some supervised approaches. Furthermore, Noise2Score3D demonstrates strong generalization ability beyond training datasets. Additionally, we introduce Total Variation for Point Cloud, a criterion that allows for the estimation of unknown noise parameters, which further enhances the method's versatility and real-world utility.
Authors: Mingyuan Sun, Zheng Fang, Jiaxu Wang, Junjie Jiang, Delei Kong, Chenming Hu, Yuetong Fang, Renjing Xu
Abstract: The increasing complexity and parameter count of Convolutional Neural Networks (CNNs) and Transformers pose challenges in terms of computational efficiency and resource demands. Pruning has been identified as an effective strategy to address these challenges by removing redundant elements such as neurons, channels, or connections, thereby enhancing computational efficiency without heavily compromising performance. This paper builds on the foundational work of Optimal Brain Damage (OBD) by advancing the methodology of parameter importance estimation using the Hessian matrix. Unlike previous approaches that rely on approximations, we introduce Optimal Brain Apoptosis (OBA), a novel pruning method that calculates the Hessian-vector product value directly for each parameter. By decomposing the Hessian matrix across network layers and identifying conditions under which inter-layer Hessian submatrices are non-zero, we propose a highly efficient technique for computing the second-order Taylor expansion of parameters. This approach allows for a more precise pruning process, particularly in the context of CNNs and Transformers, as validated in our experiments including VGG19, ResNet32, ResNet50, and ViT-B/16 on CIFAR10, CIFAR100 and Imagenet datasets. Our code is available at https://github.com/NEU-REAL/OBA.
Authors: Mingkun Zhang, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng
Abstract: In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts ``a photo of a
Authors: Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosong Cao, Weiyun Wang, Jiaqi Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Haodong Duan, Hua Yang, Kai Chen
Abstract: Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human preference alignment. This paper introduces OmniAlign-V, a comprehensive dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs' alignment with human preferences. We also present MM-AlignBench, a human-annotated benchmark specifically designed to evaluate MLLMs' alignment with human values. Experimental results show that finetuning MLLMs with OmniAlign-V, using Supervised Fine-Tuning (SFT) or Direct Preference Optimization (DPO), significantly enhances human preference alignment while maintaining or enhancing performance on standard VQA benchmarks, preserving their fundamental capabilities. Our datasets, benchmark, code and checkpoints have been released at https://github.com/PhoenixZ810/OmniAlign-V.
Authors: Ziheng Ouyang, Zhen Li, Qibin Hou
Abstract: Recent studies have explored combining different LoRAs to jointly generate learned style and content. However, existing methods either fail to effectively preserve both the original subject and style simultaneously or require additional training. In this paper, we argue that the intrinsic properties of LoRA can effectively guide diffusion models in merging learned subject and style. Building on this insight, we propose K-LoRA, a simple yet effective training-free LoRA fusion approach. In each attention layer, K-LoRA compares the Top-K elements in each LoRA to be fused, determining which LoRA to select for optimal fusion. This selection mechanism ensures that the most representative features of both subject and style are retained during the fusion process, effectively balancing their contributions. Experimental results demonstrate that the proposed method effectively integrates the subject and style information learned by the original LoRAs, outperforming state-of-the-art training-based approaches in both qualitative and quantitative results.
Authors: Vu Tuan Truong, Long Bao Le
Abstract: Diffusion models have emerged as state-of-the-art generative frameworks, excelling in producing high-quality multi-modal samples. However, recent studies have revealed their vulnerability to backdoor attacks, where backdoored models generate specific, undesirable outputs called backdoor target (e.g., harmful images) when a pre-defined trigger is embedded to their inputs. In this paper, we propose PureDiffusion, a dual-purpose framework that simultaneously serves two contrasting roles: backdoor defense and backdoor attack amplification. For defense, we introduce two novel loss functions to invert backdoor triggers embedded in diffusion models. The first leverages trigger-induced distribution shifts across multiple timesteps of the diffusion process, while the second exploits the denoising consistency effect when a backdoor is activated. Once an accurate trigger inversion is achieved, we develop a backdoor detection method that analyzes both the inverted trigger and the generated backdoor targets to identify backdoor attacks. In terms of attack amplification with the role of an attacker, we describe how our trigger inversion algorithm can be used to reinforce the original trigger embedded in the backdoored diffusion model. This significantly boosts attack performance while reducing the required backdoor training time. Experimental results demonstrate that PureDiffusion achieves near-perfect detection accuracy, outperforming existing defenses by a large margin, particularly against complex trigger patterns. Additionally, in an attack scenario, our attack amplification approach elevates the attack success rate (ASR) of existing backdoor attacks to nearly 100\% while reducing training time by up to 20x.
Authors: Nadya Abdel Madjid, Murad Mebrahtu, Abdelmoamen Nasser, Bilal Hassan, Naoufel Werghi, Jorge Dias, Majid Khonji
Abstract: This paper introduces the Emirates Multi-Task (EMT) dataset - the first publicly available dataset for autonomous driving collected in the Arab Gulf region. The EMT dataset captures the unique road topology, high traffic congestion, and distinctive characteristics of the Gulf region, including variations in pedestrian clothing and weather conditions. It contains over 30,000 frames from a dash-camera perspective, along with 570,000 annotated bounding boxes, covering approximately 150 kilometers of driving routes. The EMT dataset supports three primary tasks: tracking, trajectory forecasting and intention prediction. Each benchmark dataset is complemented with corresponding evaluations: (1) multi-agent tracking experiments, focusing on multi-class scenarios and occlusion handling; (2) trajectory forecasting evaluation using deep sequential and interaction-aware models; and (3) intention benchmark experiments conducted for predicting agents intentions from observed trajectories. The dataset is publicly available at avlab.io/emt-dataset, and pre-processing scripts along with evaluation models can be accessed at github.com/AV-Lab/emt-dataset.
Authors: Hu Gao, Depeng Dang
Abstract: Image deblurring aims to restore high-quality images by removing undesired degradation. Although existing methods have yielded promising results, they either overlook the varying degrees of degradation across different regions of the blurred image, or they approximate nonlinear function properties by stacking numerous nonlinear activation functions. In this paper, we propose a differential handling network (DHNet) to perform differential processing for different blur regions. Specifically, we design a Volterra block (VBlock) to integrate the nonlinear characteristics into the deblurring network, avoiding the previous operation of stacking the number of nonlinear activation functions to map complex input-output relationships. To enable the model to adaptively address varying degradation degrees in blurred regions, we devise the degradation degree recognition expert module (DDRE). This module initially incorporates prior knowledge from a well-trained model to estimate spatially variable blur information. Consequently, the router can map the learned degradation representation and allocate weights to experts according to both the degree of degradation and the size of the regions. Comprehensive experimental results show that DHNet effectively surpasses state-of-the-art (SOTA) methods on both synthetic and real-world datasets.
Authors: Reza Abbasi, Ali Nazari, Aminreza Sefid, Mohammadali Banayeeanzade, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah
Abstract: Contrastive Language-Image Pre-training (CLIP) models excel in zero-shot classification, yet face challenges in complex multi-object scenarios. This study offers a comprehensive analysis of CLIP's limitations in these contexts using a specialized dataset, ComCO, designed to evaluate CLIP's encoders in diverse multi-object scenarios. Our findings reveal significant biases: the text encoder prioritizes first-mentioned objects, and the image encoder favors larger objects. Through retrieval and classification tasks, we quantify these biases across multiple CLIP variants and trace their origins to CLIP's training process, supported by analyses of the LAION dataset and training progression. Our image-text matching experiments show substantial performance drops when object size or token order changes, underscoring CLIP's instability with rephrased but semantically similar captions. Extending this to longer captions and text-to-image models like Stable Diffusion, we demonstrate how prompt order influences object prominence in generated images. For more details and access to our dataset and analysis code, visit our project repository: https://clip-oscope.github.io.
Authors: Hengshuo Chu, Xiang Deng, Qi Lv, Xiaoyang Chen, Yinchuan Li, Jianye Hao, Liqiang Nie
Abstract: 3D Affordance detection is a challenging problem with broad applications on various robotic tasks. Existing methods typically formulate the detection paradigm as a label-based semantic segmentation task. This paradigm relies on predefined labels and lacks the ability to comprehend complex natural language, resulting in limited generalization in open-world scene. To address these limitations, we reformulate the traditional affordance detection paradigm into \textit{Instruction Reasoning Affordance Segmentation} (IRAS) task. This task is designed to output a affordance mask region given a query reasoning text, which avoids fixed categories of input labels. We accordingly propose the \textit{3D-AffordanceLLM} (3D-ADLLM), a framework designed for reasoning affordance detection in 3D open-scene. Specifically, 3D-ADLLM introduces large language models (LLMs) to 3D affordance perception with a custom-designed decoder for generating affordance masks, thus achieving open-world reasoning affordance detection. In addition, given the scarcity of 3D affordance datasets for training large models, we seek to extract knowledge from general segmentation data and transfer it to affordance detection. Thus, we propose a multi-stage training strategy that begins with a novel pre-training task, i.e., \textit{Referring Object Part Segmentation}~(ROPS). This stage is designed to equip the model with general recognition and segmentation capabilities at the object-part level. Then followed by fine-tuning with the IRAS task, 3D-ADLLM obtains the reasoning ability for affordance detection. In summary, 3D-ADLLM leverages the rich world knowledge and human-object interaction reasoning ability of LLMs, achieving approximately an 8\% improvement in mIoU on open-vocabulary affordance detection tasks.
Authors: Mingjie Wu, Chenggui Yang, Huihua Wang, Chen Xue, Yibo Wang, Haoyu Wang, Yansong Wang, Can Peng, Yuqi Han, Ruoyu Li, Lijun Yun, Zaiqing Chen, Yuelong Xia
Abstract: The UAV technology is gradually maturing and can provide extremely powerful support for smart agriculture and precise monitoring. Currently, there is no dataset related to green walnuts in the field of agricultural computer vision. Thus, in order to promote the algorithm design in the field of agricultural computer vision, we used UAV to collect remote-sensing data from 8 walnut sample plots. Considering that green walnuts are subject to various lighting conditions and occlusion, we constructed a large-scale dataset with a higher-granularity of target features - WalnutData. This dataset contains a total of 30,240 images and 706,208 instances, and there are 4 target categories: being illuminated by frontal light and unoccluded (A1), being backlit and unoccluded (A2), being illuminated by frontal light and occluded (B1), and being backlit and occluded (B2). Subsequently, we evaluated many mainstream algorithms on WalnutData and used these evaluation results as the baseline standard. The dataset and all evaluation results can be obtained at https://github.com/1wuming/WalnutData.
Authors: Ziang Guo, Konstantin Gubernatorov, Selamawit Asfaw, Zakhar Yagudin, Dzmitry Tsetserukou
Abstract: In autonomous driving, dynamic environment and corner cases pose significant challenges to the robustness of ego vehicle's decision-making. To address these challenges, commencing with the representation of state-action mapping in the end-to-end autonomous driving paradigm, we introduce a novel pipeline, VDT-Auto. Leveraging the advancement of the state understanding of Visual Language Model (VLM), incorporating with diffusion Transformer-based action generation, our VDT-Auto parses the environment geometrically and contextually for the conditioning of the diffusion process. Geometrically, we use a bird's-eye view (BEV) encoder to extract feature grids from the surrounding images. Contextually, the structured output of our fine-tuned VLM is processed into textual embeddings and noisy paths. During our diffusion process, the added noise for the forward process is sampled from the noisy path output of the fine-tuned VLM, while the extracted BEV feature grids and embedded texts condition the reverse process of our diffusion Transformers. Our VDT-Auto achieved 0.52m on average L2 errors and 21% on average collision rate in the nuScenes open-loop planning evaluation. Moreover, the real-world demonstration exhibited prominent generalizability of our VDT-Auto. The code and dataset will be released after acceptance.
Authors: Luis Marquez-Carpintero, Sergio Suescun-Ferrandiz, Carolina Lorenzo \'Alvarez, Jorge Fernandez-Herrero, Diego Viejo, Rosabel Roig-Vila, Miguel Cazorla
Abstract: In this paper, a novel dataset is introduced, designed to assess student attention within in-person classroom settings. This dataset encompasses RGB camera data, featuring multiple cameras per student to capture both posture and facial expressions, in addition to smartwatch sensor data for each individual. This dataset allows machine learning algorithms to be trained to predict attention and correlate it with emotion. A comprehensive suite of attention and emotion labels for each student is provided, generated through self-reporting as well as evaluations by four different experts. Our dataset uniquely combines facial and environmental camera data, smartwatch metrics, and includes underrepresented ethnicities in similar datasets, all within in-the-wild, in-person settings, making it the most comprehensive dataset of its kind currently available. The dataset presented offers an extensive and diverse collection of data pertaining to student interactions across different educational contexts, augmented with additional metadata from other tools. This initiative addresses existing deficiencies by offering a valuable resource for the analysis of student attention and emotion in face-to-face lessons.
Authors: Jingqiu Zhou, Lue Fan, Linjiang Huang, Xiaoyu Shi, Si Liu, Zhaoxiang Zhang, Hongsheng Li
Abstract: Driving scene reconstruction and rendering have advanced significantly using the 3D Gaussian Splatting. However, most prior research has focused on the rendering quality along a pre-recorded vehicle path and struggles to generalize to out-of-path viewpoints, which is caused by the lack of high-quality supervision in those out-of-path views. To address this issue, we introduce an Inverse View Warping technique to create compact and high-quality images as supervision for the reconstruction of the out-of-path views, enabling high-quality rendering results for those views. For accurate and robust inverse view warping, a depth bootstrap strategy is proposed to obtain on-the-fly dense depth maps during the optimization process, overcoming the sparsity and incompleteness of LiDAR depth data. Our method achieves superior in-path and out-of-path reconstruction and rendering performance on the widely used Waymo Open dataset. In addition, a simulator-based benchmark is proposed to obtain the out-of-path ground truth and quantitatively evaluate the performance of out-of-path rendering, where our method outperforms previous methods by a significant margin.
Authors: Jiuyang Dong, Junjun Jiang, Kui Jiang, Jiahan Li, Yongbing Zhang
Abstract: Although multi-instance learning (MIL) has succeeded in pathological image classification, it faces the challenge of high inference costs due to processing numerous patches from gigapixel whole slide images (WSIs). To address this, we propose HDMIL, a hierarchical distillation multi-instance learning framework that achieves fast and accurate classification by eliminating irrelevant patches. HDMIL consists of two key components: the dynamic multi-instance network (DMIN) and the lightweight instance pre-screening network (LIPN). DMIN operates on high-resolution WSIs, while LIPN operates on the corresponding low-resolution counterparts. During training, DMIN are trained for WSI classification while generating attention-score-based masks that indicate irrelevant patches. These masks then guide the training of LIPN to predict the relevance of each low-resolution patch. During testing, LIPN first determines the useful regions within low-resolution WSIs, which indirectly enables us to eliminate irrelevant regions in high-resolution WSIs, thereby reducing inference time without causing performance degradation. In addition, we further design the first Chebyshev-polynomials-based Kolmogorov-Arnold classifier in computational pathology, which enhances the performance of HDMIL through learnable activation layers. Extensive experiments on three public datasets demonstrate that HDMIL outperforms previous state-of-the-art methods, e.g., achieving improvements of 3.13% in AUC while reducing inference time by 28.6% on the Camelyon16 dataset.
Authors: Otto Brookes, Maksim Kukushkin, Majid Mirmehdi, Colleen Stephens, Paula Dieguez, Thurston C. Hicks, Sorrel Jones, Kevin Lee, Maureen S. McCarthy, Amelia Meier, Emmanuelle Normand, Erin G. Wessling, Roman M. Wittig, Kevin Langergraber, Klaus Zuberb\"uhler, Lukas Boesch, Thomas Schmid, Mimi Arandjelovic, Hjalmar K\"uhl, Tilo Burghardt
Abstract: Computer vision analysis of camera trap video footage is essential for wildlife conservation, as captured behaviours offer some of the earliest indicators of changes in population health. Recently, several high-impact animal behaviour datasets and methods have been introduced to encourage their use; however, the role of behaviour-correlated background information and its significant effect on out-of-distribution generalisation remain unexplored. In response, we present the PanAf-FGBG dataset, featuring 20 hours of wild chimpanzee behaviours, recorded at over 350 individual camera locations. Uniquely, it pairs every video with a chimpanzee (referred to as a foreground video) with a corresponding background video (with no chimpanzee) from the same camera location. We present two views of the dataset: one with overlapping camera locations and one with disjoint locations. This setup enables, for the first time, direct evaluation of in-distribution and out-of-distribution conditions, and for the impact of backgrounds on behaviour recognition models to be quantified. All clips come with rich behavioural annotations and metadata including unique camera IDs and detailed textual scene descriptions. Additionally, we establish several baselines and present a highly effective latent-space normalisation technique that boosts out-of-distribution performance by +5.42% mAP for convolutional and +3.75% mAP for transformer-based models. Finally, we provide an in-depth analysis on the role of backgrounds in out-of-distribution behaviour recognition, including the so far unexplored impact of background durations (i.e., the count of background frames within foreground videos).
Authors: Nita Mulliqi (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden), Anders Blilie (Department of Pathology, Stavanger University Hospital, Stavanger, Norway, Faculty of Health Sciences, University of Stavanger, Stavanger, Norway), Xiaoyi Ji (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden), Kelvin Szolnoky (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden), Henrik Olsson (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden), Sol Erika Boman (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden, Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden), Matteo Titus (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden), Geraldine Martinez Gonzalez (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden), Julia Anna Mielcarz (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden), Masi Valkonen (Institute of Biomedicine, University of Turku, Turku, Finland), Einar Gudlaugsson (Department of Pathology, Stavanger University Hospital, Stavanger, Norway), Svein R. Kjosavik (The General Practice and Care Coordination Research Group, Stavanger University Hospital, Norway, Department of Global Public Health and Primary Care, Faculty of Medicine, University of Bergen, Norway), Jos\'e Asenjo (Department of Pathology, Synlab, Madrid, Spain), Marcello Gambacorta (Department of Pathology, Synlab, Brescia, Italy), Paolo Libretti (Department of Pathology, Synlab, Brescia, Italy), Marcin Braun (Department of Pathology, Chair of Oncology, Medical University of Lodz, Lodz, Poland), Radzislaw Kordek (Department of Pathology, Chair of Oncology, Medical University of Lodz, Lodz, Poland), Roman {\L}owicki (1st Department of Urology, Medical University of Lodz, Lodz, Poland), Kristina Hotakainen (Department of Clinical Chemistry and Hematology, University of Helsinki, Helsinki, Finland, Laboratory Services, Mehil\"ainen Oy, Helsinki, Finland), P\"aivi V\"are (Department of Pathology, Mehil\"ainen L\"ansi-Pohja Hospital, Kemi, Finland), Bodil Ginnerup Pedersen (Department of Radiology, Aarhus University Hospital, Aarhus, Denmark, Department of Clinical Medicine, Aarhus University, Aarhus, Denmark), Karina Dalsgaard S{\o}rensen (Department of Clinical Medicine, Aarhus University, Aarhus, Denmark, Department of Molecular Medicine, Aarhus University Hospital, Aarhus, Denmark), Benedicte Parm Ulh{\o}i (Department of Pathology, Aarhus University Hospital, Aarhus, Denmark), Pekka Ruusuvuori (Institute of Biomedicine, University of Turku, Turku, Finland, InFLAMES Research Flagship, University of Turku, Turku, Finland, Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland), Brett Delahunt (Malaghan Institute of Medical Research, Wellington, New Zealand, Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden), Hemamali Samaratunga (Aquesta Uropathology and University of Queensland, QLD, Brisbane, Australia), Toyonori Tsuzuki (Department of Surgical Pathology, School of Medicine, Aichi Medical University, Nagoya, Japan), Emilius A. M. Janssen (Department of Pathology, Stavanger University Hospital, Stavanger, Norway, Department of Chemistry, Bioscience and Environmental Engineering, University of Stavanger, Stavanger, Norway, Institute for Biomedicine and Glycomics, Griffith University, Queensland, Australia), Lars Egevad (Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden), Martin Eklund (Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden), Kimmo Kartasalo (Department of Medical Epidemiology and Biostatistics, SciLifeLab, Karolinska Institutet, Stockholm, Sweden)
Abstract: The role of artificial intelligence (AI) in pathology has evolved from aiding diagnostics to uncovering predictive morphological patterns in whole slide images (WSIs). Recently, foundation models (FMs) leveraging self-supervised pre-training have been widely advocated as a universal solution for diverse downstream tasks. However, open questions remain about their clinical applicability and generalization advantages over end-to-end learning using task-specific (TS) models. Here, we focused on AI with clinical-grade performance for prostate cancer diagnosis and Gleason grading. We present the largest validation of AI for this task, using over 100,000 core needle biopsies from 7,342 patients across 15 sites in 11 countries. We compared two FMs with a fully end-to-end TS model in a multiple instance learning framework. Our findings challenge assumptions that FMs universally outperform TS models. While FMs demonstrated utility in data-scarce scenarios, their performance converged with - and was in some cases surpassed by - TS models when sufficient labeled training data were available. Notably, extensive task-specific training markedly reduced clinically significant misgrading, misdiagnosis of challenging morphologies, and variability across different WSI scanners. Additionally, FMs used up to 35 times more energy than the TS model, raising concerns about their sustainability. Our results underscore that while FMs offer clear advantages for rapid prototyping and research, their role as a universal solution for clinically applicable medical AI remains uncertain. For high-stakes clinical applications, rigorous validation and consideration of task-specific training remain critically important. We advocate for integrating the strengths of FMs and end-to-end learning to achieve robust and resource-efficient AI pathology solutions fit for clinical use.
Authors: Xueyun Tian, Wei Li, Bingbing Xu, Yige Yuan, Yuanzhuo Wang, Huawei Shen
Abstract: Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and poor generalization. However, both tasks require capturing complex visual variations while maintaining consistency between inputs and outputs. Therefore, we propose MIGE, a unified framework that standardizes task representations using multimodal instructions. It treats subject-driven generation as creation on a blank canvas and instruction-based editing as modification of an existing image, establishing a shared input-output formulation. MIGE introduces a novel multimodal encoder that maps free-form multimodal instructions into a unified vision-language space, integrating visual and semantic features through a feature fusion mechanism. This unification enables joint training of both tasks, providing two key advantages: (1) Cross-Task Enhancement: By leveraging shared visual and semantic representations, joint training improves instruction adherence and visual consistency in both subject-driven generation and instruction-based editing. (2) Generalization: Learning in a unified format facilitates cross-task knowledge transfer, enabling MIGE to generalize to novel compositional tasks, including instruction-based subject-driven editing. Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a state-of-the-art in the new task of instruction-based subject-driven editing. Code and model have been publicly available at https://github.com/Eureka-Maggie/MIGE.
Authors: Haoran You, Zhihan Lu, Zijian Zhou, Yonggan Fu, Yingyan Celine Lin
Abstract: Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art deep learning model for representation learning on graphs. However, it remains notoriously challenging to train and inference GCNs over large graph datasets, limiting their application to large real-world graphs and hindering the exploration of deeper and more sophisticated GCN graphs. This is because as the graph size grows, the sheer number of node features and the large adjacency matrix can easily explode the required memory and data movements. To tackle the aforementioned challenges, we explore the possibility of drawing lottery tickets when sparsifying GCN graphs, i.e., subgraphs that largely shrink the adjacency matrix yet are capable of achieving accuracy comparable to or even better than their full graphs. Specifically, we for the first time discover the existence of graph early-bird (GEB) tickets that emerge at the very early stage when sparsifying GCN graphs, and propose a simple yet effective detector to automatically identify the emergence of such GEB tickets. Furthermore, we advocate graph-model co-optimization and develop a generic efficient GCN early-bird training framework dubbed GEBT that can significantly boost the efficiency of GCN training by (1) drawing joint early-bird tickets between the GCN graphs and models and (2) enabling simultaneously sparsification of both the GCN graphs and models. Experiments on various GCN models and datasets consistently validate our GEB finding and the effectiveness of our GEBT, e.g., our GEBT achieves up to 80.2% ~ 85.6% and 84.6% ~ 87.5% savings of GCN training and inference costs while offering a comparable or even better accuracy as compared to state-of-the-art methods. Our source code and supplementary appendix are available at https://github.com/RICE-EIC/Early-Bird-GCN.
Authors: Khashayar Namdar, Matthias W. Wagner, Birgit B. Ertl-Wagner, Farzad Khalvati
Abstract: Background: As an important branch of machine learning pipelines in medical imaging, radiomics faces two major challenges namely reproducibility and accessibility. In this work, we introduce open-radiomics, a set of radiomics datasets along with a comprehensive radiomics pipeline based on our proposed technical protocol to improve the reproducibility of the results. Methods: We curated large-scale radiomics datasets based on three open-source datasets; BraTS 2020 for high-grade glioma (HGG) versus low-grade glioma (LGG) classification and survival analysis, BraTS 2023 for O6-methylguanine-DNA methyltransferase classification, and non-small cell lung cancer survival analysis from the Cancer Imaging Archive. Using BraTS 2020 Magnetic Resonance Imaging (MRI) dataset, we applied our protocol to 369 brain tumor patients (76 LGG, 293 HGG). Leveraging PyRadiomics for LGG vs. HGG classification, we generated 288 datasets from 4 MRI sequences, 3 binWidths, 6 normalization methods, and 4 tumor subregions. Random Forest classifiers were trained and validated (60%,20%,20%) across 100 different data splits (28,800 test results), evaluating Area Under the Receiver Operating Characteristic Curve (AUROC). Results: Unlike binWidth and image normalization, tumor subregion and imaging sequence significantly affected performance of the models. T1 contrast-enhanced sequence and the union of Necrotic and the non-enhancing tumor core subregions resulted in the highest AUROCs (average test AUROC 0.951, 95% confidence interval of (0.949, 0.952)). Although several settings and data splits (28 out of 28800) yielded test AUROC of 1, they were irreproducible. Conclusion: Our experiments demonstrate the sources of variability in radiomics pipelines (e.g., tumor subregion) can have a significant impact on the results, which may lead to superficial perfect performances that are irreproducible.
Authors: Yiming Li, Linghui Zhu, Xiaojun Jia, Yang Bai, Yong Jiang, Shu-Tao Xia, Xiaochun Cao, Kui Ren
Abstract: Currently, deep neural networks (DNNs) are widely adopted in different applications. Despite its commercial values, training a well-performing DNN is resource-consuming. Accordingly, the well-trained model is valuable intellectual property for its owner. However, recent studies revealed the threats of model stealing, where the adversaries can obtain a function-similar copy of the victim model, even when they can only query the model. In this paper, we propose an effective and harmless model ownership verification (MOVE) to defend against different types of model stealing simultaneously, without introducing new security risks. In general, we conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features. Specifically, we embed the external features by modifying a few training samples with style transfer. We then train a meta-classifier to determine whether a model is stolen from the victim. This approach is inspired by the understanding that the stolen models should contain the knowledge of features learned by the victim model. In particular, \revision{we develop our MOVE method under both white-box and black-box settings and analyze its theoretical foundation to provide comprehensive model protection.} Extensive experiments on benchmark datasets verify the effectiveness of our method and its resistance to potential adaptive attacks. The codes for reproducing the main experiments of our method are available at https://github.com/THUYimingLi/MOVE.
Authors: Haoran You, Zhanyi Sun, Huihong Shi, Zhongzhi Yu, Yang Zhao, Yongan Zhang, Chaojian Li, Baopu Li, Yingyan Celine Lin
Abstract: Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing accelerators dedicated to NLP Transformers are not optimal for ViTs. This is because there is a large difference between ViTs and NLP Transformers: ViTs have a relatively fixed number of input tokens, whose attention maps can be pruned by up to 90% even with fixed sparse patterns; while NLP Transformers need to handle input sequences of varying numbers of tokens and rely on on-the-fly predictions of dynamic sparse attention patterns for each input to achieve a decent sparsity (e.g., >=50%). To this end, we propose a dedicated algorithm and accelerator co-design framework dubbed ViTCoD for accelerating ViTs. Specifically, on the algorithm level, ViTCoD prunes and polarizes the attention maps to have either denser or sparser fixed patterns for regularizing two levels of workloads without hurting the accuracy, largely reducing the attention computations while leaving room for alleviating the remaining dominant data movements; on top of that, we further integrate a lightweight and learnable auto-encoder module to enable trading the dominant high-cost data movements for lower-cost computations. On the hardware level, we develop a dedicated accelerator to simultaneously coordinate the enforced denser/sparser workloads and encoder/decoder engines for boosted hardware utilization. Extensive experiments and ablation studies validate that ViTCoD largely reduces the dominant data movement costs, achieving speedups of up to 235.3x, 142.9x, 86.0x, 10.1x, and 6.8x over general computing platforms CPUs, EdgeGPUs, GPUs, and prior-art Transformer accelerators SpAtten and Sanger under an attention sparsity of 90%, respectively.
Authors: Ruoyu Feng, Yixin Gao, Xin Jin, Runsen Feng, Zhibo Chen
Abstract: Image compression techniques typically focus on compressing rectangular images for human consumption, however, resulting in transmitting redundant content for downstream applications. To overcome this limitation, some previous works propose to semantically structure the bitstream, which can meet specific application requirements by selective transmission and reconstruction. Nevertheless, they divide the input image into multiple rectangular regions according to semantics and ignore avoiding information interaction among them, causing waste of bitrate and distorted reconstruction of region boundaries. In this paper, we propose to decouple an image into multiple groups with irregular shapes based on a customized group mask and compress them independently. Our group mask describes the image at a finer granularity, enabling significant bitrate saving by reducing the transmission of redundant content. Moreover, to ensure the fidelity of selective reconstruction, this paper proposes the concept of group-independent transform that maintain the independence among distinct groups. And we instantiate it by the proposed Group-Independent Swin-Block (GI Swin-Block). Experimental results demonstrate that our framework structures the bitstream with negligible cost, and exhibits superior performance on both visual quality and intelligent task supporting.
Authors: Jaemin Yoo, Lingxiao Zhao, Leman Akoglu
Abstract: Self-supervised learning (SSL) has emerged as a promising paradigm that presents supervisory signals to real-world problems, bypassing the extensive cost of manual labeling. Consequently, self-supervised anomaly detection (SSAD) has seen a recent surge of interest, since SSL is especially attractive for unsupervised tasks. However, recent works have reported that the choice of a data augmentation function has significant impact on the accuracy of SSAD, posing augmentation search as an essential but nontrivial problem with the lack of labeled validation data. In this paper, we introduce ST-SSAD, the first systematic approach for rigorous augmentation tuning on SSAD. To this end, our work presents two key contributions. The first is a new unsupervised validation loss that quantifies the alignment between augmented training data and unlabeled validation data. The second is new differentiable augmentation functions, allowing data augmentation hyperparameter(s) to be tuned in an end-to-end manner. Experiments on two testbeds with semantic class anomalies and subtle industrial defects show that ST-SSAD gives significant performance gains over existing works.
Authors: Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, Dan Hendrycks
Abstract: In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience. RepE places population-level representations, rather than neurons or circuits, at the center of analysis, equipping us with novel methods for monitoring and manipulating high-level cognitive phenomena in deep neural networks (DNNs). We provide baselines and an initial analysis of RepE techniques, showing that they offer simple yet effective solutions for improving our understanding and control of large language models. We showcase how these methods can provide traction on a wide range of safety-relevant problems, including honesty, harmlessness, power-seeking, and more, demonstrating the promise of top-down transparency research. We hope that this work catalyzes further exploration of RepE and fosters advancements in the transparency and safety of AI systems.
Authors: Benjamin Salmon, Alexander Krull
Abstract: Accurate analysis of microscopy images is hindered by the presence of noise. This noise is usually signal-dependent and often additionally correlated along rows or columns of pixels. Current self- and unsupervised denoisers can address signal-dependent noise, but none can reliably remove noise that is also row- or column-correlated. Here, we present the first fully unsupervised deep learning-based denoiser capable of handling imaging noise that is row-correlated as well as signal-dependent. Our approach uses a Variational Autoencoder (VAE) with a specially designed autoregressive decoder. This decoder is capable of modeling row-correlated and signal-dependent noise but is incapable of independently modeling underlying clean signal. The VAE therefore produces latent variables containing only clean signal information, and these are mapped back into image space using a proposed second decoder network. Our method does not require a pre-trained noise model and can be trained from scratch using unpaired noisy data. We benchmark our approach on microscopy datatsets from a range of imaging modalities and sensor types, each with row- or column-correlated, signal-dependent noise, and show that it outperforms existing self- and unsupervised denoisers.
Authors: Liangchen Li, Jiajun He
Abstract: Diffusion models (DMs) are capable of generating remarkably high-quality samples by iteratively denoising a random vector, a process that corresponds to moving along the probability flow ordinary differential equation (PF ODE). Interestingly, DMs can also invert an input image to noise by moving backward along the PF ODE, a key operation for downstream tasks such as interpolation and image editing. However, the iterative nature of this process restricts its speed, hindering its broader application. Recently, Consistency Models (CMs) have emerged to address this challenge by approximating the integral of the PF ODE, largely reducing the number of iterations. Yet, the absence of an explicit ODE solver complicates the inversion process. To resolve this, we introduce Bidirectional Consistency Model (BCM), which learns a single neural network that enables both forward and backward traversal along the PF ODE, efficiently unifying generation and inversion tasks within one framework. We can train BCM from scratch or tune it using a pretrained consistency model, which reduces the training cost and increases scalability. We demonstrate that BCM enables one-step generation and inversion while also allowing the use of additional steps to enhance generation quality or reduce reconstruction error. We further showcase BCM's capability in downstream tasks, such as interpolation and inpainting. Our code and weights are available at https://github.com/Mosasaur5526/BCM-iCT-torch.
Authors: Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey
Abstract: Low-rank decomposition has emerged as a vital tool for enhancing parameter efficiency in neural network architectures, gaining traction across diverse applications in machine learning. These techniques significantly lower the number of parameters, striking a balance between compactness and performance. However, a common challenge has been the compromise between parameter efficiency and the accuracy of the model, where reduced parameters often lead to diminished accuracy compared to their full-rank counterparts. In this work, we propose a novel theoretical framework that integrates a sinusoidal function within the low-rank decomposition process. This approach not only preserves the benefits of the parameter efficiency characteristic of low-rank methods but also increases the decomposition's rank, thereby enhancing model performance. Our method proves to be a plug in enhancement for existing low-rank models, as evidenced by its successful application in Vision Transformers (ViT), Large Language Models (LLMs), Neural Radiance Fields (NeRF) and 3D shape modelling.
Authors: Ted Edward Holmberg, Mahdi Abdelguerfi, Elias Ioup
Abstract: Spatiotemporal networks' observational capabilities are crucial for accurate data gathering and informed decisions across multiple sectors. This study focuses on the Spatiotemporal Ranged Observer-Observable Bipartite Network (STROOBnet), linking observational nodes (e.g., surveillance cameras) to events within defined geographical regions, enabling efficient monitoring. Using data from Real-Time Crime Camera (RTCC) systems and Calls for Service (CFS) in New Orleans, where RTCC combats rising crime amidst reduced police presence, we address the network's initial observational imbalances. Aiming for uniform observational efficacy, we propose the Proximal Recurrence approach. It outperformed traditional clustering methods like k-means and DBSCAN by offering holistic event frequency and spatial consideration, enhancing observational coverage.
Authors: Yueen Ma, Zixing Song, Yuzheng Zhuang, Jianye Hao, Irwin King
Abstract: Embodied AI is widely recognized as a key element of artificial general intelligence because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models and vision-language models, a new category of multimodal models -- referred to as vision-language-action models (VLAs) -- has emerged to address language-conditioned robotic tasks in embodied AI by leveraging their distinct ability to generate actions. In recent years, a myriad of VLAs have been developed, making it imperative to capture the rapidly evolving landscape through a comprehensive survey. To this end, we present the first survey on VLAs for embodied AI. This work provides a detailed taxonomy of VLAs, organized into three major lines of research. The first line focuses on individual components of VLAs. The second line is dedicated to developing control policies adept at predicting low-level actions. The third line comprises high-level task planners capable of decomposing long-horizon tasks into a sequence of subtasks, thereby guiding VLAs to follow more general user instructions. Furthermore, we provide an extensive summary of relevant resources, including datasets, simulators, and benchmarks. Finally, we discuss the challenges faced by VLAs and outline promising future directions in embodied AI. We have created a project associated with this survey, which is available at https://github.com/yueen-ma/Awesome-VLA.
Authors: Linlin Yu, Bowen Yang, Tianhao Wang, Kangshuo Li, Feng Chen
Abstract: The fusion of raw sensor data to create a Bird's Eye View (BEV) representation is critical for autonomous vehicle planning and control. Despite the growing interest in using deep learning models for BEV semantic segmentation, anticipating segmentation errors and enhancing the explainability of these models remain underexplored. This paper introduces a comprehensive benchmark for predictive uncertainty quantification in BEV segmentation, evaluating multiple uncertainty quantification methods across three popular datasets with three representative network architectures. Our study focuses on the effectiveness of quantified uncertainty in detecting misclassified and out-of-distribution (OOD) pixels while also improving model calibration. Through empirical analysis, we uncover challenges in existing uncertainty quantification methods and demonstrate the potential of evidential deep learning techniques, which capture both aleatoric and epistemic uncertainty. To address these challenges, we propose a novel loss function, Uncertainty-Focal-Cross-Entropy (UFCE), specifically designed for highly imbalanced data, along with a simple uncertainty-scaling regularization term that improves both uncertainty quantification and model calibration for BEV segmentation.
Authors: Amith Ananthram, Elias Stengel-Eskin, Mohit Bansal, Kathleen McKeown
Abstract: Vision-language models (VLMs) can respond to queries about images in many languages. However, beyond language, culture affects how we see things. For example, individuals from Western cultures focus more on the central figure in an image while individuals from East Asian cultures attend more to scene context. In this work, we characterize the Western bias of VLMs in image understanding and investigate the role that language plays in this disparity. We evaluate VLMs across subjective and objective visual tasks with culturally diverse images and annotations. We find that VLMs perform better on the Western split than on the East Asian split of each task. Through controlled experimentation, we trace one source of this bias in image understanding to the lack of diversity in language model construction. While inference in a language nearer to a culture can lead to reductions in bias, we show it is much more effective when that language was well-represented during text-only pre-training. Interestingly, this yields bias reductions even when prompting in English. Our work highlights the importance of richer representation of all languages in building equitable VLMs.
Authors: Lorenzo Basile, Santiago Acevedo, Luca Bortolussi, Fabio Anselmi, Alex Rodriguez
Abstract: To gain insight into the mechanisms behind machine learning methods, it is crucial to establish connections among the features describing data points. However, these correlations often exhibit a high-dimensional and strongly nonlinear nature, which makes them challenging to detect using standard methods. This paper exploits the entanglement between intrinsic dimensionality and correlation to propose a metric that quantifies the (potentially nonlinear) correlation between high-dimensional manifolds. We first validate our method on synthetic data in controlled environments, showcasing its advantages and drawbacks compared to existing techniques. Subsequently, we extend our analysis to large-scale applications in neural network representations. Specifically, we focus on latent representations of multimodal data, uncovering clear correlations between paired visual and textual embeddings, whereas existing methods struggle significantly in detecting similarity. Our results indicate the presence of highly nonlinear correlation patterns between latent manifolds.
Authors: Omar S. EL-Assiouti, Ghada Hamed, Dina Khattab, Hala M. Ebied
Abstract: Vision Transformers (ViTs) have achieved significant advancement in computer vision tasks due to their powerful modeling capacity. However, their performance notably degrades when trained with insufficient data due to lack of inherent inductive biases. Distilling knowledge and inductive biases from a Convolutional Neural Network (CNN) teacher has emerged as an effective strategy for enhancing the generalization of ViTs on limited datasets. Previous approaches to Knowledge Distillation (KD) have pursued two primary paths: some focused solely on distilling the logit distribution from CNN teacher to ViT student, neglecting the rich semantic information present in intermediate features due to the structural differences between them. Others integrated feature distillation along with logit distillation, yet this introduced alignment operations that limits the amount of knowledge transferred due to mismatched architectures and increased the computational overhead. To this end, this paper presents Hybrid Data-efficient Knowledge Distillation (HDKD) paradigm which employs a CNN teacher and a hybrid student. The choice of hybrid student serves two main aspects. First, it leverages the strengths of both convolutions and transformers while sharing the convolutional structure with the teacher model. Second, this shared structure enables the direct application of feature distillation without any information loss or additional computational overhead. Additionally, we propose an efficient light-weight convolutional block named Mobile Channel-Spatial Attention (MBCSA), which serves as the primary convolutional block in both teacher and student models. Extensive experiments on two medical public datasets showcase the superiority of HDKD over other state-of-the-art models and its computational efficiency. Source code at: https://github.com/omarsherif200/HDKD
Authors: Yuetan Chu, Yilan Zhang, Zhongyi Han, Changchun Yang, Longxi Zhou, Gongning Luo, Chao Huang, Xin Gao
Abstract: Foundation models have recently attracted significant attention for their impressive generalizability across diverse downstream tasks. However, these models are demonstrated to exhibit great limitations in representing high-frequency components and fine-grained details. In many medical imaging tasks, the precise representation of such information is crucial due to the inherently intricate anatomical structures, sub-visual features, and complex boundaries involved. Consequently, the limited representation of prevalent foundation models can result in significant performance degradation or even failure in these tasks. To address these challenges, we propose a novel pretraining strategy, named Frequency-advanced Representation Autoencoder (Frepa). Through high-frequency masking and low-frequency perturbation combined with adversarial learning, Frepa encourages the encoder to effectively represent and preserve high-frequency components in the image embeddings. Additionally, we introduce an innovative histogram-equalized image masking strategy, extending the Masked Autoencoder approach beyond ViT to other architectures such as Swin Transformer and convolutional networks. We develop Frepa across nine medical modalities and validate it on 32 downstream tasks for both 2D images and 3D volume data. Without fine-tuning, Frepa can outperform other self-supervised pretraining methods and, in some cases, even surpasses task-specific trained models. This improvement is particularly significant for tasks involving fine-grained details, such as achieving up to a +15% increase in DSC for retina vessel segmentation and a +7% increase in IoU for lung nodule detection. Further experiments quantitatively reveal that Frepa enables superior high-frequency representations and preservation in the embeddings, underscoring its potential for developing more generalized and universal medical image foundation models.
Authors: Muhammad Arbab Arshad, Talukder Zaki Jubery, Tirtho Roy, Rim Nassiri, Asheesh K. Singh, Arti Singh, Chinmay Hegde, Baskar Ganapathysubramanian, Aditya Balu, Adarsh Krishnamurthy, Soumik Sarkar
Abstract: As Vision Language Models (VLMs) become increasingly accessible to farmers and agricultural experts, there is a growing need to evaluate their potential in specialized tasks. We present AgEval, a comprehensive benchmark for assessing VLMs' capabilities in plant stress phenotyping, offering a solution to the challenge of limited annotated data in agriculture. Our study explores how general-purpose VLMs can be leveraged for domain-specific tasks with only a few annotated examples, providing insights into their behavior and adaptability. AgEval encompasses 12 diverse plant stress phenotyping tasks, evaluating zero-shot and few-shot in-context learning performance of state-of-the-art models including Claude, GPT, Gemini, and LLaVA. Our results demonstrate VLMs' rapid adaptability to specialized tasks, with the best-performing model showing an increase in F1 scores from 46.24% to 73.37% in 8-shot identification. To quantify performance disparities across classes, we introduce metrics such as the coefficient of variation (CV), revealing that VLMs' training impacts classes differently, with CV ranging from 26.02% to 58.03%. We also find that strategic example selection enhances model reliability, with exact category examples improving F1 scores by 15.38% on average. AgEval establishes a framework for assessing VLMs in agricultural applications, offering valuable benchmarks for future evaluations. Our findings suggest that VLMs, with minimal few-shot examples, show promise as a viable alternative to traditional specialized models in plant stress phenotyping, while also highlighting areas for further refinement. Results and benchmark details are available at: https://github.com/arbab-ml/AgEval
Authors: Uri Berger, Gabriel Stanovsky, Omri Abend, Lea Frermann
Abstract: The task of image captioning has recently been gaining popularity, and with it the complex task of evaluating the quality of image captioning models. In this work, we present the first survey and taxonomy of over 70 different image captioning metrics and their usage in hundreds of papers, specifically designed to help users select the most suitable metric for their needs. We find that despite the diversity of proposed metrics, the vast majority of studies rely on only five popular metrics, which we show to be weakly correlated with human ratings. We hypothesize that combining a diverse set of metrics can enhance correlation with human ratings. As an initial step, we demonstrate that a linear regression-based ensemble method, which we call EnsembEval, trained on one human ratings dataset, achieves improved correlation across five additional datasets, showing there is a lot of room for improvement by leveraging a diverse set of metrics.
Authors: Junwon Lee, Jaekwon Im, Dabin Kim, Juhan Nam
Abstract: Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video both temporally and semantically. Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges. Systems lacking explicit temporal features suffer from poor alignment and controllability, while timestamp-based models require costly and subjective human annotation. We propose Video-Foley, a video-to-sound system using Root Mean Square (RMS) as an intuitive condition with semantic timbre prompts (audio or text). RMS, a frame-level intensity envelope closely related to audio semantics, acts as a temporal event feature to guide audio generation from video. The annotation-free self-supervised learning framework consists of two stages, Video2RMS and RMS2Sound, incorporating novel ideas including RMS discretization and RMS-ControlNet with a pretrained text-to-audio model. Our extensive evaluation shows that Video-Foley achieves state-of-the-art performance in audio-visual alignment and controllability for sound timing, intensity, timbre, and nuance. Source code, model weights and demos are available on our companion website. (https://jnwnlee.github.io/video-foley-demo)
Authors: Be\~nat Froemming-Aldanondo, Tatiana Rastoskueva, Michael Evans, Marcial Machado, Anna Vadella, Rickey Johnson, Luis Escamilla, Milan Jostes, Devson Butani, Ryan Kaddis, Chan-Jin Chung, Joshua Siegel
Abstract: Reliable lane-following is essential for automated and assisted driving, yet existing solutions often rely on models that require extensive computational resources, limiting their deployment in compute-constrained vehicles. We evaluate five low-resource lane-following algorithms designed for real-time operation on vehicles with limited computing resources. Performance was assessed through simulation and deployment on real drive-by-wire electric vehicles, with evaluation metrics including reliability, comfort, speed, and adaptability. The top-performing methods used unsupervised learning to detect and separate lane lines with processing time under 10 ms per frame, outperforming compute-intensive and poor generalizing deep learning approaches. These approaches demonstrated robustness across lighting conditions, road textures, and lane geometries. The findings highlight the potential for efficient lane detection approaches to enhance the accessibility and reliability of autonomous vehicle technologies. Reducing computing requirements enables lane keeping to be widely deployed in vehicles as part of lower-level automation, including active safety systems.
Authors: Ninad Khargonkar, Luis Felipe Casas, Balakrishnan Prabhakaran, Yu Xiang
Abstract: We introduce a novel grasp representation named the Unified Gripper Coordinate Space (UGCS) for grasp synthesis and grasp transfer. Our representation leverages spherical coordinates to create a shared coordinate space across different robot grippers, enabling it to synthesize and transfer grasps for both novel objects and previously unseen grippers. The strength of this representation lies in the ability to map palm and fingers of a gripper and the unified coordinate space. Grasp synthesis is formulated as predicting the unified spherical coordinates on object surface points via a conditional variational autoencoder. The predicted unified gripper coordinates establish exact correspondences between the gripper and object points, which is used to optimize grasp pose and joint values. Grasp transfer is facilitated through the point-to-point correspondence between any two (potentially unseen) grippers and solved via a similar optimization. Extensive simulation and real-world experiments showcase the efficacy of the unified grasp representation for grasp synthesis in generating stable and diverse grasps. Similarly, we showcase real-world grasp transfer from human demonstrations across different objects.
Authors: Sai Haneesh Allu, Itay Kadosh, Tyler Summers, Yu Xiang
Abstract: We introduce a new robotic system that enables a mobile robot to autonomously explore an unknown environment, build a semantic map of the environment, and subsequently update the semantic map to reflect environment changes, such as location changes of objects. Our system leverages a LiDAR scanner for 2D occupancy grid mapping and an RGB-D camera for object perception. We introduce a semantic map representation that combines a 2D occupancy grid map for geometry with a topological map for object semantics. This map representation enables us to effectively update the semantics by deleting or adding nodes to the topological map. Our system has been tested on a Fetch robot, semantically mapping a 93m x 90m and a 9m x 13m indoor environment and updating their semantic maps once objects are moved in the environments
Authors: Haojie Huang, Haotian Liu, Dian Wang, Robin Walters, Robert Platt
Abstract: Many manipulation tasks require the robot to rearrange objects relative to one another. Such tasks can be described as a sequence of relative poses between parts of a set of rigid bodies. In this work, we propose MATCH POLICY, a simple but novel pipeline for solving high-precision pick and place tasks. Instead of predicting actions directly, our method registers the pick and place targets to the stored demonstrations. This transfers action inference into a point cloud registration task and enables us to realize nontrivial manipulation policies without any training. MATCH POLICY is designed to solve high-precision tasks with a key-frame setting. By leveraging the geometric interaction and the symmetries of the task, it achieves extremely high sample efficiency and generalizability to unseen configurations. We demonstrate its state-of-the-art performance across various tasks on RLBench benchmark compared with several strong baselines and test it on a real robot with six tasks.
Authors: Ricardo Garcia, Shizhe Chen, Cordelia Schmid
Abstract: Generalizing language-conditioned robotic policies to new tasks remains a significant challenge, hampered by the lack of suitable simulation benchmarks. In this paper, we address this gap by introducing GemBench, a novel benchmark to assess generalization capabilities of vision-language robotic manipulation policies. GemBench incorporates seven general action primitives and four levels of generalization, spanning novel placements, rigid and articulated objects, and complex long-horizon tasks. We evaluate state-of-the-art approaches on GemBench and also introduce a new method. Our approach 3D-LOTUS leverages rich 3D information for action prediction conditioned on language. While 3D-LOTUS excels in both efficiency and performance on seen tasks, it struggles with novel tasks. To address this, we present 3D-LOTUS++, a framework that integrates 3D-LOTUS's motion planning capabilities with the task planning capabilities of LLMs and the object grounding accuracy of VLMs. 3D-LOTUS++ achieves state-of-the-art performance on novel tasks of GemBench, setting a new standard for generalization in robotic manipulation. The benchmark, codes and trained models are available at https://www.di.ens.fr/willow/research/gembench/.
Authors: Sabine Muzellec, Drew Linsley, Alekh K. Ashok, Ennio Mingolla, Girik Malik, Rufin VanRullen, Thomas Serre
Abstract: Objects we encounter often change appearance as we interact with them. Changes in illumination (shadows), object pose, or the movement of non-rigid objects can drastically alter available image features. How do biological visual systems track objects as they change? One plausible mechanism involves attentional mechanisms for reasoning about the locations of objects independently of their appearances -- a capability that prominent neuroscience theories have associated with computing through neural synchrony. Here, we describe a novel deep learning circuit that can learn to precisely control attention to features separately from their location in the world through neural synchrony: the complex-valued recurrent neural network (CV-RNN). Next, we compare object tracking in humans, the CV-RNN, and other deep neural networks (DNNs), using FeatureTracker: a large-scale challenge that asks observers to track objects as their locations and appearances change in precisely controlled ways. While humans effortlessly solved FeatureTracker, state-of-the-art DNNs did not. In contrast, our CV-RNN behaved similarly to humans on the challenge, providing a computational proof-of-concept for the role of phase synchronization as a neural substrate for tracking appearance-morphing objects as they move about.
Authors: Tianchi Xie, Jiangning Zhu, Guozu Ma, Minzhi Lin, Wei Chen, Weikai Yang, Shixia Liu
Abstract: Sample selection improves the efficiency and effectiveness of machine learning models by providing informative and representative samples. Typically, samples can be modeled as a sample graph, where nodes are samples and edges represent their similarities. Most existing methods are based on local information, such as the training difficulty of samples, thereby overlooking global information, such as connectivity patterns. This oversight can result in suboptimal selection because global information is crucial for ensuring that the selected samples well represent the structural properties of the graph. To address this issue, we employ structural entropy to quantify global information and losslessly decompose it from the whole graph to individual nodes using the Shapley value. Based on the decomposition, we present $\textbf{S}$tructural-$\textbf{E}$ntropy-based sample $\textbf{S}$election ($\textbf{SES}$), a method that integrates both global and local information to select informative and representative samples. SES begins by constructing a $k$NN-graph among samples based on their similarities. It then measures sample importance by combining structural entropy (global metric) with training difficulty (local metric). Finally, SES applies importance-biased blue noise sampling to select a set of diverse and representative samples. Comprehensive experiments on three learning scenarios -- supervised learning, active learning, and continual learning -- clearly demonstrate the effectiveness of our method.
Authors: Genta Indra Winata, David Anugraha, Lucky Susanto, Garry Kuwanto, Derry Tanti Wijaya
Abstract: Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metric captures the diverse aspects of these preferences, as metrics often excel in one particular area but not across all dimensions. To address this, it is essential to systematically calibrate metrics to specific aspects of human preference, catering to the unique characteristics of each aspect. We introduce MetaMetrics, a calibrated meta-metric designed to evaluate generation tasks across different modalities in a supervised manner. MetaMetrics optimizes the combination of existing metrics to enhance their alignment with human preferences. Our metric demonstrates flexibility and effectiveness in both language and vision downstream tasks, showing significant benefits across various multilingual and multi-domain scenarios. MetaMetrics aligns closely with human preferences and is highly extendable and easily integrable into any application. This makes MetaMetrics a powerful tool for improving the evaluation of generation tasks, ensuring that metrics are more representative of human judgment across diverse contexts.
Authors: Rayhan Zirvi, Bahareh Tolooshams, Anima Anandkumar
Abstract: Recent advancements in diffusion models have been effective in learning data priors for solving inverse problems. They leverage diffusion sampling steps for inducing a data prior while using a measurement guidance gradient at each step to impose data consistency. For general inverse problems, approximations are needed when an unconditionally trained diffusion model is used since the measurement likelihood is intractable, leading to inaccurate posterior sampling. In other words, due to their approximations, these methods fail to preserve the generation process on the data manifold defined by the diffusion prior, leading to artifacts in applications such as image restoration. To enhance the performance and robustness of diffusion models in solving inverse problems, we propose Diffusion State-Guided Projected Gradient (DiffStateGrad), which projects the measurement gradient onto a subspace that is a low-rank approximation of an intermediate state of the diffusion process. DiffStateGrad, as a module, can be added to a wide range of diffusion-based inverse solvers to improve the preservation of the diffusion process on the prior manifold and filter out artifact-inducing components. We highlight that DiffStateGrad improves the robustness of diffusion models in terms of the choice of measurement guidance step size and noise while improving the worst-case performance. Finally, we demonstrate that DiffStateGrad improves upon the state-of-the-art on linear and nonlinear image restoration inverse problems. Our code is available at https://github.com/neuraloperator/DiffStateGrad.
Authors: Haokun Chen, Hang Li, Yao Zhang, Jinhe Bi, Gengyuan Zhang, Yueqi Zhang, Philip Torr, Jindong Gu, Denis Krompass, Volker Tresp
Abstract: One-Shot Federated Learning (OSFL), a special decentralized machine learning paradigm, has recently gained significant attention. OSFL requires only a single round of client data or model upload, which reduces communication costs and mitigates privacy threats compared to traditional FL. Despite these promising prospects, existing methods face challenges due to client data heterogeneity and limited data quantity when applied to real-world OSFL systems. Recently, Latent Diffusion Models (LDM) have shown remarkable advancements in synthesizing high-quality images through pretraining on large-scale datasets, thereby presenting a potential solution to overcome these issues. However, directly applying pretrained LDM to heterogeneous OSFL results in significant distribution shifts in synthetic data, leading to performance degradation in classification models trained on such data. This issue is particularly pronounced in rare domains, such as medical imaging, which are underrepresented in LDM's pretraining data. To address this challenge, we propose Federated Bi-Level Personalization (FedBiP), which personalizes the pretrained LDM at both instance-level and concept-level. Hereby, FedBiP synthesizes images following the client's local data distribution without compromising the privacy regulations. FedBiP is also the first approach to simultaneously address feature space heterogeneity and client data scarcity in OSFL. Our method is validated through extensive experiments on three OSFL benchmarks with feature space heterogeneity, as well as on challenging medical and satellite image datasets with label heterogeneity. The results demonstrate the effectiveness of FedBiP, which substantially outperforms other OSFL methods.
Authors: Boyu Gou, Ruohan Wang, Boyuan Zheng, Yanan Xie, Cheng Chang, Yiheng Shu, Huan Sun, Yu Su
Abstract: Multimodal large language models (MLLMs) are transforming the capabilities of graphical user interface (GUI) agents, facilitating their transition from controlled simulations to complex, real-world applications across various platforms. However, the effectiveness of these agents hinges on the robustness of their grounding capability. Current GUI agents predominantly utilize text-based representations such as HTML or accessibility trees, which, despite their utility, often introduce noise, incompleteness, and increased computational overhead. In this paper, we advocate a human-like embodiment for GUI agents that perceive the environment entirely visually and directly perform pixel-level operations on the GUI. The key is visual grounding models that can accurately map diverse referring expressions of GUI elements to their coordinates on the GUI across different platforms. We show that a simple recipe, which includes web-based synthetic data and slight adaptation of the LLaVA architecture, is surprisingly effective for training such visual grounding models. We collect the largest dataset for GUI visual grounding so far, containing 10M GUI elements and their referring expressions over 1.3M screenshots, and use it to train UGround, a strong universal visual grounding model for GUI agents. Empirical results on six benchmarks spanning three categories (grounding, offline agent, and online agent) show that 1) UGround substantially outperforms existing visual grounding models for GUI agents, by up to 20% absolute, and 2) agents with UGround outperform state-of-the-art agents, despite the fact that existing agents use additional text-based input while ours only uses visual perception. These results provide strong support for the feasibility and promises of GUI agents that navigate the digital world as humans do.
Authors: Yepeng Liu, Yiren Song, Hai Ci, Yu Zhang, Haofan Wang, Mike Zheng Shou, Yuheng Bu
Abstract: Image watermark techniques provide an effective way to assert ownership, deter misuse, and trace content sources, which has become increasingly essential in the era of large generative models. A critical attribute of watermark techniques is their robustness against various manipulations. In this paper, we introduce a watermark removal approach capable of effectively nullifying state-of-the-art watermarking techniques. Our primary insight involves regenerating the watermarked image starting from a clean Gaussian noise via a controllable diffusion model, utilizing the extracted semantic and spatial features from the watermarked image. The semantic control adapter and the spatial control network are specifically trained to control the denoising process towards ensuring image quality and enhancing consistency between the cleaned image and the original watermarked image. To achieve a smooth trade-off between watermark removal performance and image consistency, we further propose an adjustable and controllable regeneration scheme. This scheme adds varying numbers of noise steps to the latent representation of the watermarked image, followed by a controlled denoising process starting from this noisy latent representation. As the number of noise steps increases, the latent representation progressively approaches clean Gaussian noise, facilitating the desired trade-off. We apply our watermark removal methods across various watermarking techniques, and the results demonstrate that our methods offer superior visual consistency/quality and enhanced watermark removal performance compared to existing regeneration approaches. Our code is available at https://github.com/yepengliu/CtrlRegen.
Authors: Stephen Hausler, Peyman Moghadam
Abstract: In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images are from the same place or not. The network only comprises Vision Transformer components for both the encoder and the pair classifier, and both components are trained using their respective class tokens. In existing VPR methods, typically the network is initialized using pre-trained weights from a generic image dataset such as ImageNet. In this work we propose an alternative pre-training strategy, by using Siamese Masked Image Modelling as a pre-training task. We propose a Place-aware image sampling procedure from a collection of large VPR datasets for pre-training our model, to learn visual features tuned specifically for VPR. By re-using the Mask Image Modelling encoder and decoder weights in the second stage of training, Pair-VPR can achieve state-of-the-art VPR performance across five benchmark datasets with a ViT-B encoder, along with further improvements in localization recall with larger encoders. The Pair-VPR website is: https://csiro-robotics.github.io/Pair-VPR.
Authors: Songming Liu, Lingxuan Wu, Bangguo Li, Hengkai Tan, Huayu Chen, Zhengyi Wang, Ke Xu, Hang Su, Jun Zhu
Abstract: Bimanual manipulation is essential in robotics, yet developing foundation models is extremely challenging due to the inherent complexity of coordinating two robot arms (leading to multi-modal action distributions) and the scarcity of training data. In this paper, we present the Robotics Diffusion Transformer (RDT), a pioneering diffusion foundation model for bimanual manipulation. RDT builds on diffusion models to effectively represent multi-modality, with innovative designs of a scalable Transformer to deal with the heterogeneity of multi-modal inputs and to capture the nonlinearity and high frequency of robotic data. To address data scarcity, we further introduce a Physically Interpretable Unified Action Space, which can unify the action representations of various robots while preserving the physical meanings of original actions, facilitating learning transferrable physical knowledge. With these designs, we managed to pre-train RDT on the largest collection of multi-robot datasets to date and scaled it up to 1.2B parameters, which is the largest diffusion-based foundation model for robotic manipulation. We finally fine-tuned RDT on a self-created multi-task bimanual dataset with over 6K+ episodes to refine its manipulation capabilities. Experiments on real robots demonstrate that RDT significantly outperforms existing methods. It exhibits zero-shot generalization to unseen objects and scenes, understands and follows language instructions, learns new skills with just 1~5 demonstrations, and effectively handles complex, dexterous tasks. We refer to https://rdt-robotics.github.io/rdt-robotics/ for the code and videos.
Authors: Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
Abstract: Retrieval-augmented generation (RAG) is an effective technique that enables large language models (LLMs) to utilize external knowledge sources for generation. However, current RAG systems are solely based on text, rendering it impossible to utilize vision information like layout and images that play crucial roles in real-world multi-modality documents. In this paper, we introduce VisRAG, which tackles this issue by establishing a vision-language model (VLM)-based RAG pipeline. In this pipeline, instead of first parsing the document to obtain text, the document is directly embedded using a VLM as an image and then retrieved to enhance the generation of a VLM. Compared to traditional text-based RAG, VisRAG maximizes the retention and utilization of the data information in the original documents, eliminating the information loss introduced during the parsing process. We collect both open-source and synthetic data to train the retriever in VisRAG and explore a variety of generation methods. Experiments demonstrate that VisRAG outperforms traditional RAG in both the retrieval and generation stages, achieving a 20--40% end-to-end performance gain over traditional text-based RAG pipeline. Further analysis reveals that VisRAG is efficient in utilizing training data and demonstrates strong generalization capability, positioning it as a promising solution for RAG on multi-modality documents. Our code and data are available at https://github.com/openbmb/visrag.
Authors: Peng Xia, Kangyu Zhu, Haoran Li, Tianze Wang, Weijia Shi, Sheng Wang, Linjun Zhang, James Zou, Huaxiu Yao
Abstract: Artificial Intelligence (AI) has demonstrated significant potential in healthcare, particularly in disease diagnosis and treatment planning. Recent progress in Medical Large Vision-Language Models (Med-LVLMs) has opened up new possibilities for interactive diagnostic tools. However, these models often suffer from factual hallucination, which can lead to incorrect diagnoses. Fine-tuning and retrieval-augmented generation (RAG) have emerged as methods to address these issues. However, the amount of high-quality data and distribution shifts between training data and deployment data limit the application of fine-tuning methods. Although RAG is lightweight and effective, existing RAG-based approaches are not sufficiently general to different medical domains and can potentially cause misalignment issues, both between modalities and between the model and the ground truth. In this paper, we propose a versatile multimodal RAG system, MMed-RAG, designed to enhance the factuality of Med-LVLMs. Our approach introduces a domain-aware retrieval mechanism, an adaptive retrieved contexts selection method, and a provable RAG-based preference fine-tuning strategy. These innovations make the RAG process sufficiently general and reliable, significantly improving alignment when introducing retrieved contexts. Experimental results across five medical datasets (involving radiology, ophthalmology, pathology) on medical VQA and report generation demonstrate that MMed-RAG can achieve an average improvement of 43.8% in the factual accuracy of Med-LVLMs. Our data and code are available in https://github.com/richard-peng-xia/MMed-RAG.
Authors: Jan Witowski, Ken G. Zeng, Joseph Cappadona, Jailan Elayoubi, Khalil Choucair, Elena Diana Chiru, Nancy Chan, Young-Joon Kang, Frederick Howard, Irina Ostrovnaya, Carlos Fernandez-Granda, Freya Schnabel, Zoe Steinsnyder, Ugur Ozerdem, Kangning Liu, Waleed Abdulsattar, Yu Zong, Lina Daoud, Rafic Beydoun, Anas Saad, Nitya Thakore, Mohammad Sadic, Frank Yeung, Elisa Liu, Theodore Hill, Benjamin Swett, Danielle Rigau, Andrew Clayburn, Valerie Speirs, Marcus Vetter, Lina Sojak, Simone Soysal, Daniel Baumhoer, Jia-Wern Pan, Haslina Makmur, Soo-Hwang Teo, Linda Ma Pak, Victor Angel, Dovile Zilenaite-Petrulaitiene, Arvydas Laurinavicius, Natalie Klar, Brian D. Piening, Carlo Bifulco, Sun-Young Jun, Jae Pak Yi, Su Hyun Lim, Adam Brufsky, Francisco J. Esteva, Lajos Pusztai, Yann LeCun, Krzysztof J. Geras
Abstract: Treatment selection in breast cancer is guided by molecular subtypes and clinical characteristics. However, current tools including genomic assays lack the accuracy required for optimal clinical decision-making. We developed a novel artificial intelligence (AI)-based approach that integrates digital pathology images with clinical data, providing a more robust and effective method for predicting the risk of cancer recurrence in breast cancer patients. Specifically, we utilized a vision transformer pan-cancer foundation model trained with self-supervised learning to extract features from digitized H&E-stained slides. These features were integrated with clinical data to form a multi-modal AI test predicting cancer recurrence and death. The test was developed and evaluated using data from a total of 8,161 female breast cancer patients across 15 cohorts originating from seven countries. Of these, 3,502 patients from five cohorts were used exclusively for evaluation, while the remaining patients were used for training. Our test accurately predicted our primary endpoint, disease-free interval, in the five evaluation cohorts (C-index: 0.71 [0.68-0.75], HR: 3.63 [3.02-4.37, p<0.001]). In a direct comparison (n=858), the AI test was more accurate than Oncotype DX, the standard-of-care 21-gene assay, achieving a C-index of 0.67 [0.61-0.74] versus 0.61 [0.49-0.73], respectively. Additionally, the AI test added independent prognostic information to Oncotype DX in a multivariate analysis (HR: 3.11 [1.91-5.09, p<0.001)]). The test demonstrated robust accuracy across major molecular breast cancer subtypes, including TNBC (C-index: 0.71 [0.62-0.81], HR: 3.81 [2.35-6.17, p=0.02]), where no diagnostic tools are currently recommended by clinical guidelines. These results suggest that our AI test improves upon the accuracy of existing prognostic tests, while being applicable to a wider range of patients.
Authors: Yichao Liang, Nishanth Kumar, Hao Tang, Adrian Weller, Joshua B. Tenenbaum, Tom Silver, Jo\~ao F. Henriques, Kevin Ellis
Abstract: Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a first-order abstraction language that combines the strengths of symbolic and neural knowledge representations. We outline an online algorithm for inventing such predicates and learning abstract world models. We compare our approach to hierarchical reinforcement learning, vision-language model planning, and symbolic predicate invention approaches, on both in- and out-of-distribution tasks across five simulated robotic domains. Results show that our approach offers better sample complexity, stronger out-of-distribution generalization, and improved interpretability.
Authors: Chenrui Tie, Yue Chen, Ruihai Wu, Boxuan Dong, Zeyi Li, Chongkai Gao, Hao Dong
Abstract: Imitation learning, e.g., diffusion policy, has been proven effective in various robotic manipulation tasks. However, extensive demonstrations are required for policy robustness and generalization. To reduce the demonstration reliance, we leverage spatial symmetry and propose ET-SEED, an efficient trajectory-level SE(3) equivariant diffusion model for generating action sequences in complex robot manipulation tasks. Further, previous equivariant diffusion models require the per-step equivariance in the Markov process, making it difficult to learn policy under such strong constraints. We theoretically extend equivariant Markov kernels and simplify the condition of equivariant diffusion process, thereby significantly improving training efficiency for trajectory-level SE(3) equivariant diffusion policy in an end-to-end manner. We evaluate ET-SEED on representative robotic manipulation tasks, involving rigid body, articulated and deformable object. Experiments demonstrate superior data efficiency and manipulation proficiency of our proposed method, as well as its ability to generalize to unseen configurations with only a few demonstrations. Website: https://et-seed.github.io/
Authors: Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees G. M. Snoek, Jan-Jakob Sonke, Efstratios Gavves
Abstract: In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without long-term strategic and cooperative planning, leading to redundant steps, failures, and even serious repercussions in complex tasks like search-and-rescue missions where discussion and cooperative plan are crucial. To solve this issue, we propose Cooperative Plan Optimization (CaPo) to enhance the cooperation efficiency of LLM-based embodied agents. Inspired by human cooperation schemes, CaPo improves cooperation efficiency with two phases: 1) meta-plan generation, and 2) progress-adaptive meta-plan and execution. In the first phase, all agents analyze the task, discuss, and cooperatively create a meta-plan that decomposes the task into subtasks with detailed steps, ensuring a long-term strategic and coherent plan for efficient coordination. In the second phase, agents execute tasks according to the meta-plan and dynamically adjust it based on their latest progress (e.g., discovering a target object) through multi-turn discussions. This progress-based adaptation eliminates redundant actions, improving the overall cooperation efficiency of agents. Experimental results on the ThreeDworld Multi-Agent Transport and Communicative Watch-And-Help tasks demonstrate that CaPo achieves much higher task completion rate and efficiency compared with state-of-the-arts.The code is released at https://github.com/jliu4ai/CaPo.
Authors: Pascal Janetzky, Tobias Schlagenhauf, Stefan Feuerriegel
Abstract: A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in CL. Our framework exploits an implicit bias of gradient-based neural networks due to which these converge to margin maximization points. Such convergence points allow us to reconstruct old data from previous tasks, which we then combine with the current training data. Our framework is flexible and can be applied on top of existing, state-of-the-art CL methods. We further demonstrate the performance gain from our framework across a large series of experiments, including two challenging CL scenarios (class incremental and domain incremental learning), different datasets (MNIST, CIFAR10, TinyImagenet), and different network architectures. Across all experiments, we find large performance gains through ReCL. To the best of our knowledge, our framework is the first to address catastrophic forgetting by leveraging models in CL as their own memory buffers.
Authors: Sonia Raychaudhuri, Duy Ta, Katrina Ashton, Angel X. Chang, Jiuguang Wang, Bernadette Bucher
Abstract: Large scale scenes such as multifloor homes can be robustly and efficiently mapped with a 3D graph of landmarks estimated jointly with robot poses in a factor graph, a technique commonly used in commercial robots such as drones and robot vacuums. In this work, we propose Language-Inferred Factor Graph for Instruction Following (LIFGIF), a zero-shot method to ground natural language instructions in such a map. LIFGIF also includes a policy for following natural language navigation instructions in a novel environment while the map is constructed, enabling robust navigation performance in the physical world. To evaluate LIFGIF, we present a new dataset, Object-Centric VLN (OC-VLN), in order to evaluate grounding of object-centric natural language navigation instructions. We compare to two state-of-the-art zero-shot baselines from related tasks, Object Goal Navigation and Vision Language Navigation, to demonstrate that LIFGIF outperforms them across all our evaluation metrics on OCVLN. Finally, we successfully demonstrate the effectiveness of LIFGIF for performing zero-shot object-centric instruction following in the real world on a Boston Dynamics Spot robot.
Authors: Hao Ding, Zhongpai Gao, Benjamin Planche, Tianyu Luan, Abhishek Sharma, Meng Zheng, Ange Lou, Terrence Chen, Mathias Unberath, Ziyan Wu
Abstract: Surgical phase recognition (SPR) is crucial for applications in workflow optimization, performance evaluation, and real-time intervention guidance. However, current deep learning models often struggle with fragmented predictions, failing to capture the sequential nature of surgical workflows. We propose the Neural Finite-State Machine (NFSM), a novel approach that enforces temporal coherence by integrating classical state-transition priors with modern neural networks. NFSM leverages learnable global state embeddings as unique phase identifiers and dynamic transition tables to model phase-to-phase progressions. Additionally, a future phase forecasting mechanism employs repeated frame padding to anticipate upcoming transitions. Implemented as a plug-and-play module, NFSM can be integrated into existing SPR pipelines without changing their core architectures. We demonstrate state-of-the-art performance across multiple benchmarks, including a significant improvement on the BernBypass70 dataset - raising video-level accuracy by 0.9 points and phase-level precision, recall, F1-score, and mAP by 3.8, 3.1, 3.3, and 4.1, respectively. Ablation studies confirm each component's effectiveness and the module's adaptability to various architectures. By unifying finite-state principles with deep learning, NFSM offers a robust path toward consistent, long-term surgical video analysis.
Authors: Saksham Sharma, Akshit Raizada, Suresh Sundaram
Abstract: Autonomous off-road navigation is required for applications in agriculture, construction, search and rescue and defence. Traditional on-road autonomous methods struggle with dynamic terrains, leading to poor vehicle control in off-road conditions. Recent deep-learning models have used perception sensors along with kinesthetic feedback for navigation on such terrains. However, this approach has out-of-domain uncertainty. Factors like change in time of day and weather impacts the performance of the model. We propose a multi modal fusion network "IRisPath" capable of using Thermal and RGB images to provide robustness against dynamic weather and light conditions. To aid further works in this domain, we also open-source a day-night dataset with Thermal and RGB images along with pseudo-labels for traversability. In order to co-register for fusion model we also develop a novel method for targetless extrinsic calibration of Thermal, LiDAR and RGB cameras with translation accuracy of +/-1.7cm and rotation accuracy of +/-0.827degrees.
Authors: Yik Lung Pang, Alessio Xompero, Changjae Oh, Andrea Cavallaro
Abstract: Jointly estimating hand and object shape facilitates the grasping task in human-to-robot handovers. However, relying on hand-crafted prior knowledge about the geometric structure of the object fails when generalising to unseen objects, and depth sensors fail to detect transparent objects such as drinking glasses. In this work, we propose a stereo-based method for hand-object reconstruction that combines single-view reconstructions probabilistically to form a coherent stereo reconstruction. We learn 3D shape priors from a large synthetic hand-object dataset to ensure that our method is generalisable, and use RGB inputs to better capture transparent objects. We show that our method reduces the object Chamfer distance compared to existing RGB based hand-object reconstruction methods on single view and stereo settings. We process the reconstructed hand-object shape with a projection-based outlier removal step and use the output to guide a human-to-robot handover pipeline with wide-baseline stereo RGB cameras. Our hand-object reconstruction enables a robot to successfully receive a diverse range of household objects from the human.
Authors: Runci Bai, Guibao Xu, Yanze Shi
Abstract: Brain tumors can lead to neurological dysfunction, cognitive and psychological changes, increased intracranial pressure, and seizures, posing significant risks to health. The You Only Look Once (YOLO) series has shown superior accuracy in medical imaging object detection. This paper presents a novel SCC-YOLO architecture that integrates the SCConv module into YOLOv9. The SCConv module optimizes convolutional efficiency by reducing spatial and channel redundancy, enhancing image feature learning. We examine the effects of different attention mechanisms with YOLOv9 for brain tumor detection using the Br35H dataset and our custom dataset (Brain_Tumor_Dataset). Results indicate that SCC-YOLO improved mAP50 by 0.3% on the Br35H dataset and by 0.5% on our custom dataset compared to YOLOv9. SCC-YOLO achieves state-of-the-art performance in brain tumor detection.
Authors: Michael Toker, Ido Galil, Hadas Orgad, Rinon Gal, Yoad Tewel, Gal Chechik, Yonatan Belinkov
Abstract: Text-to-image (T2I) diffusion models rely on encoded prompts to guide the image generation process. Typically, these prompts are extended to a fixed length by adding padding tokens before text encoding. Despite being a default practice, the influence of padding tokens on the image generation process has not been investigated. In this work, we conduct the first in-depth analysis of the role padding tokens play in T2I models. We develop two causal techniques to analyze how information is encoded in the representation of tokens across different components of the T2I pipeline. Using these techniques, we investigate when and how padding tokens impact the image generation process. Our findings reveal three distinct scenarios: padding tokens may affect the model's output during text encoding, during the diffusion process, or be effectively ignored. Moreover, we identify key relationships between these scenarios and the model's architecture (cross or self-attention) and its training process (frozen or trained text encoder). These insights contribute to a deeper understanding of the mechanisms of padding tokens, potentially informing future model design and training practices in T2I systems.
Authors: Yansong Qu, Dian Chen, Xinyang Li, Xiaofan Li, Shengchuan Zhang, Liujuan Cao, Rongrong Ji
Abstract: Recent advancements in 3D scene editing have been propelled by the rapid development of generative models. Existing methods typically utilize generative models to perform text-guided editing on 3D representations, such as 3D Gaussian Splatting (3DGS). However, these methods are often limited to texture modifications and fail when addressing geometric changes, such as editing a character's head to turn around. Moreover, such methods lack accurate control over the spatial position of editing results, as language struggles to precisely describe the extent of edits. To overcome these limitations, we introduce DYG, an effective 3D drag-based editing method for 3D Gaussian Splatting. It enables users to conveniently specify the desired editing region and the desired dragging direction through the input of 3D masks and pairs of control points, thereby enabling precise control over the extent of editing. DYG integrates the strengths of the implicit triplane representation to establish the geometric scaffold of the editing results, effectively overcoming suboptimal editing outcomes caused by the sparsity of 3DGS in the desired editing regions. Additionally, we incorporate a drag-based Latent Diffusion Model into our method through the proposed Drag-SDS loss function, enabling flexible, multi-view consistent, and fine-grained editing. Extensive experiments demonstrate that DYG conducts effective drag-based editing guided by control point prompts, surpassing other baselines in terms of editing effect and quality, both qualitatively and quantitatively. Visit our project page at https://quyans.github.io/Drag-Your-Gaussian.
Authors: Minh Le, Anh Nguyen, Huy Nguyen, Chau Nguyen, Nhat Ho
Abstract: Visual Prompt Tuning (VPT) has recently emerged as a powerful method for adapting pre-trained vision models to downstream tasks. By introducing learnable prompt tokens as task-specific instructions, VPT effectively guides pre-trained transformer models with minimal overhead. Despite its empirical success, a comprehensive theoretical understanding of VPT remains an active area of research. Building on recent insights into the connection between mixture of experts and prompt-based approaches, we identify a key limitation in VPT: the restricted functional expressiveness in prompt formulation. To address this limitation, we propose Visual Adaptive Prompt Tuning (VAPT), a new generation of prompts that redefines prompts as adaptive functions of the input. Our theoretical analysis shows that this simple yet intuitive approach achieves optimal sample efficiency. Empirical results on VTAB-1K and FGVC further demonstrate VAPT's effectiveness, with performance gains of 7.34% and 1.04% over fully fine-tuning baselines, respectively. Notably, VAPT also surpasses VPT by a substantial margin while using fewer parameters. These results highlight both the effectiveness and efficiency of our method and pave the way for future research to explore the potential of adaptive prompts.
Authors: Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen, Serge Belongie, Jenq-Neng Hwang, Lei Li
Abstract: Diffusion-based algorithms have emerged as promising techniques for weight generation, particularly in scenarios like multi-task learning that require frequent weight updates. However, existing solutions suffer from limited cross-task transferability. In addition, they only utilize optimal weights as training samples, ignoring the value of other weights in the optimization process. To address these issues, we propose Lt-Di, which integrates the diffusion algorithm with meta-learning to generate weights for unseen tasks. Furthermore, we extend the vanilla diffusion algorithm into a trajectory diffusion algorithm to utilize other weights along the optimization trajectory. Trajectory diffusion decomposes the entire diffusion chain into multiple shorter ones, improving training and inference efficiency. We analyze the convergence properties of the weight generation paradigm and improve convergence efficiency without additional time overhead. Our experiments demonstrate Lt-Di's higher accuracy while reducing computational overhead across various tasks, including zero-shot and few-shot learning, multi-domain generalization, and large-scale language model fine-tuning.Our code is released at https://anonymous.4open.science/r/Lt-Di-0E51.
Authors: Mingtian Zhang, Jiajun He, Wenlin Chen, Zijing Ou, Jos\'e Miguel Hern\'andez-Lobato, Bernhard Sch\"olkopf, David Barber
Abstract: Recent advances in one-step generative models typically follow a two-stage process: first training a teacher diffusion model and then distilling it into a one-step student model. This distillation process traditionally relies on both the teacher model's score function to compute the distillation loss and its weights for student initialization. In this paper, we explore whether one-step generative models can be trained directly without this distillation process. First, we show that the teacher's score function is not essential and propose a family of distillation methods that achieve competitive results without relying on score estimation. Next, we demonstrate that initialization from teacher weights is indispensable in successful training. Surprisingly, we find that this benefit is not due to improved ``input-output" mapping but rather the learned feature representations, which dominate distillation quality. Our findings provide a better understanding of the role of initialization in one-step model training and its impact on distillation quality.
Authors: Zihan Wang, Yaohui Zhu, Gim Hee Lee, Yachun Fan
Abstract: Vision-and-Language Navigation (VLN) is an essential skill for embodied agents, allowing them to navigate in 3D environments following natural language instructions. High-performance navigation models require a large amount of training data, the high cost of manually annotating data has seriously hindered this field. Therefore, some previous methods translate trajectory videos into step-by-step instructions for expanding data, but such instructions do not match well with users' communication styles that briefly describe destinations or state specific needs. Moreover, local navigation trajectories overlook global context and high-level task planning. To address these issues, we propose NavRAG, a retrieval-augmented generation (RAG) framework that generates user demand instructions for VLN. NavRAG leverages LLM to build a hierarchical scene description tree for 3D scene understanding from global layout to local details, then simulates various user roles with specific demands to retrieve from the scene tree, generating diverse instructions with LLM. We annotate over 2 million navigation instructions across 861 scenes and evaluate the data quality and navigation performance of trained models.
Authors: Zeliang Zhang, Susan Liang, Daiki Shimada, Chenliang Xu
Abstract: While audio-visual learning equips models with a richer understanding of the real world by leveraging multiple sensory modalities, this integration also introduces new vulnerabilities to adversarial attacks. In this paper, we present a comprehensive study of the adversarial robustness of audio-visual models, considering both temporal and modality-specific vulnerabilities. We propose two powerful adversarial attacks: 1) a temporal invariance attack that exploits the inherent temporal redundancy across consecutive time segments and 2) a modality misalignment attack that introduces incongruence between the audio and visual modalities. These attacks are designed to thoroughly assess the robustness of audio-visual models against diverse threats. Furthermore, to defend against such attacks, we introduce a novel audio-visual adversarial training framework. This framework addresses key challenges in vanilla adversarial training by incorporating efficient adversarial perturbation crafting tailored to multi-modal data and an adversarial curriculum strategy. Extensive experiments in the Kinetics-Sounds dataset demonstrate that our proposed temporal and modality-based attacks in degrading model performance can achieve state-of-the-art performance, while our adversarial training defense largely improves the adversarial robustness as well as the adversarial training efficiency.
Authors: Yichi Zhang, Yici Yan, Alex Schwing, Zhizhen Zhao
Abstract: We formulate a hierarchical rectified flow to model data distributions. It hierarchically couples multiple ordinary differential equations (ODEs) and defines a time-differentiable stochastic process that generates a data distribution from a known source distribution. Each ODE resembles the ODE that is solved in a classic rectified flow, but differs in its domain, i.e., location, velocity, acceleration, etc. Unlike the classic rectified flow formulation, which formulates a single ODE in the location domain and only captures the expected velocity field (sufficient to capture a multi-modal data distribution), the hierarchical rectified flow formulation models the multi-modal random velocity field, acceleration field, etc., in their entirety. This more faithful modeling of the random velocity field enables integration paths to intersect when the underlying ODE is solved during data generation. Intersecting paths in turn lead to integration trajectories that are more straight than those obtained in the classic rectified flow formulation, where integration paths cannot intersect. This leads to modeling of data distributions with fewer neural function evaluations. We empirically verify this on synthetic 1D and 2D data as well as MNIST, CIFAR-10, and ImageNet-32 data. Our code is available at: https://riccizz.github.io/HRF/.
Authors: Jingtao Zhan, Jiahao Zhao, Jiayu Li, Yiqun Liu, Bo Zhang, Qingyao Ai, Jiaxin Mao, Hongning Wang, Min Zhang, Shaoping Ma
Abstract: Intelligence is a crucial trait for species to find solutions within a limited number of trial-and-error attempts. Building on this idea, we introduce Survival Game as a framework to evaluate intelligence based on the number of failed attempts in a trial-and-error process. Fewer failures indicate higher intelligence. When the expectation and variance of failure counts are both finite, it signals the ability to consistently find solutions to new challenges, which we define as the Autonomous Level of intelligence. Using Survival Game, we comprehensively evaluate existing AI systems. Our results show that while AI systems achieve the Autonomous Level in simple tasks, they are still far from it in more complex tasks, such as vision, search, recommendation, and language. While scaling current AI technologies might help, this would come at an astronomical cost. Projections suggest that achieving the Autonomous Level for general tasks would require $10^{26}$ parameters. To put this into perspective, loading such a massive model requires so many H100 GPUs that their total value is $10^{7}$ times that of Apple Inc.'s market value. Even with Moore's Law, supporting such a parameter scale would take $70$ years. This staggering cost highlights the complexity of human tasks and the inadequacies of current AI technologies. To further investigate this phenomenon, we conduct a theoretical analysis of Survival Game and its experimental results. Our findings suggest that human tasks possess a criticality property. As a result, Autonomous Level requires a deep understanding of the task's underlying mechanisms. Current AI systems, however, do not fully grasp these mechanisms and instead rely on superficial mimicry, making it difficult for them to reach an autonomous level. We believe Survival Game can not only guide the future development of AI but also offer profound insights into human intelligence.