Authors: Miaosen Zhang, Qi Dai, Yifan Yang, Jianmin Bao, Dongdong Chen, Kai Qiu, Chong Luo, Xin Geng, Baining Guo
Abstract: LMMs have shown impressive visual understanding capabilities, with the potential to be applied in agents, which demand strong reasoning and planning abilities. Nevertheless, existing benchmarks mostly assess their reasoning abilities in language part, where the chain-of-thought is entirely composed of text.We consider the scenario where visual signals are continuously updated and required along the decision making process. Such vision-in-the-chain reasoning paradigm is more aligned with the needs of multimodal agents, while being rarely evaluated. In this paper, we introduce MageBench, a reasoning capability oriented multimodal agent benchmark that, while having light-weight environments, poses significant reasoning challenges and holds substantial practical value. This benchmark currently includes three types of environments: WebUI, Sokoban, and Football, comprising a total of 483 different scenarios. It thoroughly validates the agent's knowledge and engineering capabilities, visual intelligence, and interaction skills. The results show that only a few product-level models are better than random acting, and all of them are far inferior to human-level. More specifically, we found current models severely lack the ability to modify their planning based on visual feedback, as well as visual imagination, interleaved image-text long context handling, and other abilities. We hope that our work will provide optimization directions for LMM from the perspective of being an agent. We release our code and data at https://github.com/microsoft/MageBench.
Authors: Yongkang Li, Tianheng Cheng, Wenyu Liu, Xinggang Wang
Abstract: Recent open-vocabulary segmentation methods adopt mask generators to predict segmentation masks and leverage pre-trained vision-language models, e.g., CLIP, to classify these masks via mask pooling. Although these approaches show promising results, it is counterintuitive that accurate masks often fail to yield accurate classification results through pooling CLIP image embeddings within the mask regions. In this paper, we reveal the performance limitations of mask pooling and introduce Mask-Adapter, a simple yet effective method to address these challenges in open-vocabulary segmentation. Compared to directly using proposal masks, our proposed Mask-Adapter extracts semantic activation maps from proposal masks, providing richer contextual information and ensuring alignment between masks and CLIP. Additionally, we propose a mask consistency loss that encourages proposal masks with similar IoUs to obtain similar CLIP embeddings to enhance models' robustness to varying predicted masks. Mask-Adapter integrates seamlessly into open-vocabulary segmentation methods based on mask pooling in a plug-and-play manner, delivering more accurate classification results. Extensive experiments across several zero-shot benchmarks demonstrate significant performance gains for the proposed Mask-Adapter on several well-established methods. Notably, Mask-Adapter also extends effectively to SAM and achieves impressive results on several open-vocabulary segmentation datasets. Code and models are available at \url{https://github.com/hustvl/MaskAdapter}.
Authors: Maria Mihaela Trusca, Mingxiao Li, Marie-Francine Moens
Abstract: Text-based image editing is typically approached as a static task that involves operations such as inserting, deleting, or modifying elements of an input image based on human instructions. Given the static nature of this task, in this paper, we aim to make this task dynamic by incorporating actions. By doing this, we intend to modify the positions or postures of objects in the image to depict different actions while maintaining the visual properties of the objects. To implement this challenging task, we propose a new model that is sensitive to action text instructions by learning to recognize contrastive action discrepancies. The model training is done on new datasets defined by extracting frames from videos that show the visual scenes before and after an action. We show substantial improvements in image editing using action-based text instructions and high reasoning capabilities that allow our model to use the input image as a starting scene for an action while generating a new image that shows the final scene of the action.
Authors: Daniela Ivanova, Marco Aversa, Paul Henderson, John Williamson
Abstract: Accurately detecting and classifying damage in analogue media such as paintings, photographs, textiles, mosaics, and frescoes is essential for cultural heritage preservation. While machine learning models excel in correcting degradation if the damage operator is known a priori, we show that they fail to robustly predict where the damage is even after supervised training; thus, reliable damage detection remains a challenge. Motivated by this, we introduce ARTeFACT, a dataset for damage detection in diverse types analogue media, with over 11,000 annotations covering 15 kinds of damage across various subjects, media, and historical provenance. Furthermore, we contribute human-verified text prompts describing the semantic contents of the images, and derive additional textual descriptions of the annotated damage. We evaluate CNN, Transformer, diffusion-based segmentation models, and foundation vision models in zero-shot, supervised, unsupervised and text-guided settings, revealing their limitations in generalising across media types. Our dataset is available at $\href{https://daniela997.github.io/ARTeFACT/}{https://daniela997.github.io/ARTeFACT/}$ as the first-of-its-kind benchmark for analogue media damage detection and restoration.
URLs: https://daniela997.github.io/ARTeFACT/, https://daniela997.github.io/ARTeFACT/
Authors: Ahmad Darkhalil, Rhodri Guerrier, Adam W. Harley, Dima Damen
Abstract: We introduce EgoPoints, a benchmark for point tracking in egocentric videos. We annotate 4.7K challenging tracks in egocentric sequences. Compared to the popular TAP-Vid-DAVIS evaluation benchmark, we include 9x more points that go out-of-view and 59x more points that require re-identification (ReID) after returning to view. To measure the performance of models on these challenging points, we introduce evaluation metrics that specifically monitor tracking performance on points in-view, out-of-view, and points that require re-identification. We then propose a pipeline to create semi-real sequences, with automatic ground truth. We generate 11K such sequences by combining dynamic Kubric objects with scene points from EPIC Fields. When fine-tuning point tracking methods on these sequences and evaluating on our annotated EgoPoints sequences, we improve CoTracker across all metrics, including the tracking accuracy $\delta^\star_{\text{avg}}$ by 2.7 percentage points and accuracy on ReID sequences (ReID$\delta_{\text{avg}}$) by 2.4 points. We also improve $\delta^\star_{\text{avg}}$ and ReID$\delta_{\text{avg}}$ of PIPs++ by 0.3 and 2.8 respectively.
Authors: Le Zhang, Qian Yang, Aishwarya Agrawal
Abstract: How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In this paper, we propose a direct assessment method, inspired by linear probing, to assess vision-language alignment. We identify that the degree of alignment of the SSL vision models depends on their SSL training objective, and we find that the clustering quality of SSL representations has a stronger impact on alignment performance than their linear separability. Next, we introduce Swift Alignment of Image and Language (SAIL), a efficient transfer learning framework that aligns pretrained unimodal vision and language models for downstream vision-language tasks. Since SAIL leverages the strengths of pretrained unimodal models, it requires significantly fewer (6%) paired image-text data for the multimodal alignment compared to models like CLIP which are trained from scratch. SAIL training only requires a single A100 GPU, 5 hours of training and can accommodate a batch size up to 32,768. SAIL achieves 73.4% zero-shot accuracy on ImageNet (vs. CLIP's 72.7%) and excels in zero-shot retrieval, complex reasoning, and semantic segmentation. Additionally, SAIL improves the language-compatibility of vision encoders that in turn enhance the performance of multimodal large language models. The entire codebase and model weights are open-source: https://lezhang7.github.io/sail.github.io/
Authors: Kaihua Chen, Deva Ramanan, Tarasha Khurana
Abstract: Object permanence in humans is a fundamental cue that helps in understanding persistence of objects, even when they are fully occluded in the scene. Present day methods in object segmentation do not account for this amodal nature of the world, and only work for segmentation of visible or modal objects. Few amodal methods exist; single-image segmentation methods cannot handle high-levels of occlusions which are better inferred using temporal information, and multi-frame methods have focused solely on segmenting rigid objects. To this end, we propose to tackle video amodal segmentation by formulating it as a conditional generation task, capitalizing on the foundational knowledge in video generative models. Our method is simple; we repurpose these models to condition on a sequence of modal mask frames of an object along with contextual pseudo-depth maps, to learn which object boundary may be occluded and therefore, extended to hallucinate the complete extent of an object. This is followed by a content completion stage which is able to inpaint the occluded regions of an object. We benchmark our approach alongside a wide array of state-of-the-art methods on four datasets and show a dramatic improvement of upto 13% for amodal segmentation in an object's occluded region.
Authors: Xiaohuan Pei, Tao Huang, Chang Xu
Abstract: KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from large language models (LLMs) to identify and prune irrelevant tokens. However, these approaches overlook the inherent distributional discrepancies between modalities, often leading to inaccurate token importance estimation and the over-pruning of critical visual tokens. To address this, we propose decomposing attention scores into intra-modality attention (within the same modality) and inter-modality attention (across modalities), enabling more precise KV cache pruning by independently managing these distinct attention types. Additionally, we introduce an n-softmax function to counteract distribution shifts caused by pruning, preserving the original smoothness of attention scores and ensuring stable performance. Our final training-free method, \textbf{C}ross-\textbf{S}elf \textbf{P}runing (CSP), achieves competitive performance compared to models with full KV caches while significantly outperforming previous pruning methods. Extensive evaluations on MileBench, a benchmark encompassing 29 multimodal datasets, demonstrate CSP's effectiveness, achieving up to a 41\% performance improvement on challenging tasks like conversational embodied dialogue while reducing the KV cache budget by 13.6\%. The code is available at https://github.com/TerryPei/CSP
Authors: Kasra Arabi, Benjamin Feuer, R. Teal Witter, Chinmay Hegde, Niv Cohen
Abstract: As the quality of image generators continues to improve, deepfakes become a topic of considerable societal debate. Image watermarking allows responsible model owners to detect and label their AI-generated content, which can mitigate the harm. Yet, current state-of-the-art methods in image watermarking remain vulnerable to forgery and removal attacks. This vulnerability occurs in part because watermarks distort the distribution of generated images, unintentionally revealing information about the watermarking techniques. In this work, we first demonstrate a distortion-free watermarking method for images, based on a diffusion model's initial noise. However, detecting the watermark requires comparing the initial noise reconstructed for an image to all previously used initial noises. To mitigate these issues, we propose a two-stage watermarking framework for efficient detection. During generation, we augment the initial noise with generated Fourier patterns to embed information about the group of initial noises we used. For detection, we (i) retrieve the relevant group of noises, and (ii) search within the given group for an initial noise that might match our image. This watermarking approach achieves state-of-the-art robustness to forgery and removal against a large battery of attacks.
Authors: Deepank Singh, Vedhus Hoskere, Pietro Milillo
Abstract: Timely and accurate assessments of building damage are crucial for effective response and recovery in the aftermath of earthquakes. Conventional preliminary damage assessments (PDA) often rely on manual door-to-door inspections, which are not only time-consuming but also pose significant safety risks. To safely expedite the PDA process, researchers have studied the applicability of satellite imagery processed with heuristic and machine learning approaches. These approaches output binary or, more recently, multiclass damage states at the scale of a block or a single building. However, the current performance of such approaches limits practical applicability. To address this limitation, we introduce a metadata-enriched, transformer based framework that combines high-resolution post-earthquake satellite imagery with building-specific metadata relevant to the seismic performance of the structure. Our model achieves state-of-the-art performance in multiclass post-earthquake damage identification for buildings from the Turkey-Syria earthquake on February 6, 2023. Specifically, we demonstrate that incorporating metadata, such as seismic intensity indicators, soil properties, and SAR damage proxy maps not only enhances the model's accuracy and ability to distinguish between damage classes, but also improves its generalizability across various regions. Furthermore, we conducted a detailed, class-wise analysis of feature importance to understand the model's decision-making across different levels of building damage. This analysis reveals how individual metadata features uniquely contribute to predictions for each damage class. By leveraging both satellite imagery and metadata, our proposed framework enables faster and more accurate damage assessments for precise, multiclass, building-level evaluations that can improve disaster response and accelerate recovery efforts for affected communities.
Authors: Karthik Shetty, Annette Birkhold, Bernhard Egger, Srikrishna Jaganathan, Norbert Strobel, Markus Kowarschik, Andreas Maier
Abstract: We present a novel approach for 3D human pose estimation by employing probabilistic modeling. This approach leverages the advantages of normalizing flows in non-Euclidean geometries to address uncertain poses. Specifically, our method employs normalizing flow tailored to the SO(3) rotational group, incorporating a coupling mechanism based on the M\"obius transformation. This enables the framework to accurately represent any distribution on SO(3), effectively addressing issues related to discontinuities. Additionally, we reinterpret the challenge of reconstructing 3D human figures from 2D pixel-aligned inputs as the task of mapping these inputs to a range of probable poses. This perspective acknowledges the intrinsic ambiguity of the task and facilitates a straightforward integration method for multi-view scenarios. The combination of these strategies showcases the effectiveness of probabilistic models in complex scenarios for human pose estimation techniques. Our approach notably surpasses existing methods in the field of pose estimation. We also validate our methodology on human pose estimation from RGB images as well as medical X-Ray datasets.
Authors: Kebin Peng, Haotang Li, Zhenyu Qi, Huashan Chen, Zi Wang, Wei Zhang, Sen He
Abstract: Existing self-supervised monocular depth estimation (MDE) models attempt to improve nighttime performance by using GANs to transfer nighttime images into their daytime versions. However, this can introduce inconsistencies due to the complexities of real-world daytime lighting variations, which may finally lead to inaccurate estimation results. To address this issue, we leverage physical-prior-knowledge about light wavelength and light attenuation during nighttime. Specifically, our model, Light-Attenuation-Aware Network (LAA-Net), incorporates physical insights from Rayleigh scattering theory for robust nighttime depth estimation: LAA-Net is trained based on red channel values because red light preserves more information under nighttime scenarios due to its longer wavelength. Additionally, based on Beer-Lambert law, we introduce Red Channel Attenuation (RCA) loss to guide LAA-Net's training. Experiments on the RobotCar-Night, nuScenes-Night, RobotCar-Day, and KITTI datasets demonstrate that our model outperforms SOTA models.
Authors: Ali Abbasi, Shima Imani, Chenyang An, Gayathri Mahalingam, Harsh Shrivastava, Maurice Diesendruck, Hamed Pirsiavash, Pramod Sharma, Soheil Kolouri
Abstract: With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information from extensive datasets into a compact set of synthetic samples by solving a bilevel optimization problem. However, current methods face challenges in computational efficiency, particularly with high-resolution data and complex architectures. Recently, knowledge-distillation-based dataset condensation approaches have made this process more computationally feasible. Yet, with the recent developments of generative foundation models, there is now an opportunity to achieve even greater compression, enhance the quality of distilled data, and introduce valuable diversity into the data representation. In this work, we propose a two-stage solution. First, we compress the dataset by selecting only the most informative patches to form a coreset. Next, we leverage a generative foundation model to dynamically expand this compressed set in real-time, enhancing the resolution of these patches and introducing controlled variability to the coreset. Our extensive experiments demonstrate the robustness and efficiency of our approach across a range of dataset distillation benchmarks. We demonstrate a significant improvement of over 10% compared to the state-of-the-art on several large-scale dataset distillation benchmarks. The code will be released soon.
Authors: Haleh Damirchi, Ali Etemad, Michael Greenspan
Abstract: Pedestrian trajectory prediction remains a challenge for autonomous systems, particularly due to the intricate dynamics of social interactions. Accurate forecasting requires a comprehensive understanding not only of each pedestrian's previous trajectory but also of their interaction with the surrounding environment, an important part of which are other pedestrians moving dynamically in the scene. To learn effective socially-informed representations, we propose a model that uses a reconstructor alongside a conditional variational autoencoder-based trajectory forecasting module. This module generates pseudo-trajectories, which we use as augmentations throughout the training process. To further guide the model towards social awareness, we propose a novel social loss that aids in forecasting of more stable trajectories. We validate our approach through extensive experiments, demonstrating strong performances in comparison to state of-the-art methods on the ETH/UCY and SDD benchmarks.
Authors: Daniela Ivanova, Marco Aversa, Paul Henderson, John Williamson
Abstract: We propose an unsupervised image segmentation method using features from pre-trained text-to-image diffusion models. Inspired by classic spectral clustering approaches, we construct adjacency matrices from self-attention layers between image patches and recursively partition using Normalised Cuts. A key insight is that self-attention probability distributions, which capture semantic relations between patches, can be interpreted as a transition matrix for random walks across the image. We leverage this by first using Random Walk Normalized Cuts directly on these self-attention activations to partition the image, minimizing transition probabilities between clusters while maximizing coherence within clusters. Applied recursively, this yields a hierarchical segmentation that reflects the rich semantics in the pre-trained attention layers, without any additional training. Next, we explore other ways to build the NCuts adjacency matrix from features, and how we can use the random walk interpretation of self-attention to capture long-range relationships. Finally, we propose an approach to automatically determine the NCut cost criterion, avoiding the need to tune this manually. We quantitatively analyse the effect incorporating different features, a constant versus dynamic NCut threshold, and incorporating multi-node paths when constructing the NCuts adjacency matrix. We show that our approach surpasses all existing methods for zero-shot unsupervised segmentation, achieving state-of-the-art results on COCO-Stuff-27 and Cityscapes.
Authors: Jaihyun Lew, Soohyuk Jang, Jaehoon Lee, Seungryong Yoo, Eunji Kim, Saehyung Lee, Jisoo Mok, Siwon Kim, Sungroh Yoon
Abstract: Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision. A cornerstone of their success lies in the attention mechanism, which models relationships among tokens. While the tokenization process in NLP inherently ensures that a single token does not contain multiple semantics, the tokenization of Vision Transformer (ViT) utilizes tokens from uniformly partitioned square image patches, which may result in an arbitrary mixing of visual concepts in a token. In this work, we propose to substitute the grid-based tokenization in ViT with superpixel tokenization, which employs superpixels to generate a token that encapsulates a sole visual concept. Unfortunately, the diverse shapes, sizes, and locations of superpixels make integrating superpixels into ViT tokenization rather challenging. Our tokenization pipeline, comprised of pre-aggregate extraction and superpixel-aware aggregation, overcomes the challenges that arise in superpixel tokenization. Extensive experiments demonstrate that our approach, which exhibits strong compatibility with existing frameworks, enhances the accuracy and robustness of ViT on various downstream tasks.
Authors: Hongjin Lin, Matthew Nazari, Derek Zheng
Abstract: Reliable large-scale data on the state of forests is crucial for monitoring ecosystem health, carbon stock, and the impact of climate change. Current knowledge of tree species distribution relies heavily on manual data collection in the field, which often takes years to complete, resulting in limited datasets that cover only a small subset of the world's forests. Recent works show that state-of-the-art deep learning models using Light Detection and Ranging (LiDAR) images enable accurate and scalable classification of tree species in various ecosystems. While LiDAR images contain rich 3D information, most previous works flatten the 3D images into 2D projections to use Convolutional Neural Networks (CNNs). This paper offers three significant contributions: (1) we apply the deep learning framework for tree classification in tropical savannas; (2) we use Airborne LiDAR images, which have a lower resolution but greater scalability than Terrestrial LiDAR images used in most previous works; (3) we introduce the approach of directly feeding 3D point cloud images into a vision transformer model (PCTreeS). Our results show that the PCTreeS approach outperforms current CNN baselines with 2D projections in AUC (0.81), overall accuracy (0.72), and training time (~45 mins). This paper also motivates further LiDAR image collection and validation for accurate large-scale automatic classification of tree species.
Authors: Sunung Mun, Jinhwan Nam, Sunghyun Cho, Jungseul Ok
Abstract: Diffusion models have become a cornerstone in image editing, offering flexibility with language prompts and source images. However, a key challenge is attribute leakage, where unintended modifications occur in non-target regions or within target regions due to attribute interference. Existing methods often suffer from leakage due to naive text embeddings and inadequate handling of End-of-Sequence (EOS) token embeddings. We propose a novel framework to address attribute leakage with three components: (1) Object-Restricted Embeddings (ORE) to localize object-specific attributes in text embeddings, (2) Region-Guided Blending for Cross-Attention Masking (RGB-CAM) to align attention with target regions, and (3) Background Blending (BB) to preserve non-edited regions. Additionally, we introduce ALE-Bench, a benchmark for evaluating attribute leakage with new metrics for target-external and target-internal leakage. Experiments demonstrate that our framework significantly reduces attribute leakage while maintaining high editing quality, providing an efficient and tuning-free solution for multi-object image editing.
Authors: Wei Liu, Xin Xu, Hua Chang, Xin Yuan, Zheng Wang
Abstract: Current visible-infrared cross-modality person re-identification research has only focused on exploring the bi-modality mutual retrieval paradigm, and we propose a new and more practical mix-modality retrieval paradigm. Existing Visible-Infrared person re-identification (VI-ReID) methods have achieved some results in the bi-modality mutual retrieval paradigm by learning the correspondence between visible and infrared modalities. However, significant performance degradation occurs due to the modality confusion problem when these methods are applied to the new mix-modality paradigm. Therefore, this paper proposes a Mix-Modality person re-identification (MM-ReID) task, explores the influence of modality mixing ratio on performance, and constructs mix-modality test sets for existing datasets according to the new mix-modality testing paradigm. To solve the modality confusion problem in MM-ReID, we propose a Cross-Identity Discrimination Harmonization Loss (CIDHL) adjusting the distribution of samples in the hyperspherical feature space, pulling the centers of samples with the same identity closer, and pushing away the centers of samples with different identities while aggregating samples with the same modality and the same identity. Furthermore, we propose a Modality Bridge Similarity Optimization Strategy (MBSOS) to optimize the cross-modality similarity between the query and queried samples with the help of the similar bridge sample in the gallery. Extensive experiments demonstrate that compared to the original performance of existing cross-modality methods on MM-ReID, the addition of our CIDHL and MBSOS demonstrates a general improvement.
Authors: Keunwoo Peter Yu, Achal Dave, Rares Ambrus, Jean Mercat
Abstract: Most of the current vision-language models (VLMs) for videos struggle to understand videos longer than a few seconds. This is primarily due to the fact that they do not scale to utilizing a large number of frames. In order to address this limitation, we propose Espresso, a novel method that extracts and compresses spatial and temporal information separately. Through extensive evaluations, we show that spatial and temporal compression in Espresso each have a positive impact on the long-form video understanding capabilities; when combined, their positive impact increases. Furthermore, we show that Espresso's performance scales well with more training data, and that Espresso is far more effective than the existing projectors for VLMs in long-form video understanding. Moreover, we devise a more difficult evaluation setting for EgoSchema called "needle-in-a-haystack" that multiplies the lengths of the input videos. Espresso achieves SOTA performance on this task, outperforming the SOTA VLMs that have been trained on much more training data.
Authors: Bowei Tian, Yexiao He, Meng Liu, Yucong Dai, Ziyao Wang, Shwai He, Guoheng Sun, Zheyu Shen, Wanghao Ye, Yongkai Wu, Ang Li
Abstract: In medical image analysis, model predictions can be affected by sensitive attributes, such as race and gender, leading to fairness concerns and potential biases in diagnostic outcomes. To mitigate this, we present a causal modeling framework, which aims to reduce the impact of sensitive attributes on diagnostic predictions. Our approach introduces a novel fairness criterion, \textbf{Diagnosis Fairness}, and a unique fairness metric, leveraging path-specific fairness to control the influence of demographic attributes, ensuring that predictions are primarily informed by clinically relevant features rather than sensitive attributes. By incorporating adversarial perturbation masks, our framework directs the model to focus on critical image regions, suppressing bias-inducing information. Experimental results across multiple datasets demonstrate that our framework effectively reduces bias directly associated with sensitive attributes while preserving diagnostic accuracy. Our findings suggest that causal modeling can enhance both fairness and interpretability in AI-powered clinical decision support systems.
Authors: Sahar Rahimi Malakshan, Mohammad Saeed Ebrahimi Saadabadi, Ali Dabouei, Nasser M. Nasrabadi
Abstract: Dataset Condensation (DC) aims to reduce deep neural networks training efforts by synthesizing a small dataset such that it will be as effective as the original large dataset. Conventionally, DC relies on a costly bi-level optimization which prohibits its practicality. Recent research formulates DC as a distribution matching problem which circumvents the costly bi-level optimization. However, this efficiency sacrifices the DC performance. To investigate this performance degradation, we decomposed the dataset distribution into content and style. Our observations indicate two major shortcomings of: 1) style discrepancy between original and condensed data, and 2) limited intra-class diversity of condensed dataset. We present a simple yet effective method to match the style information between original and condensed data, employing statistical moments of feature maps as well-established style indicators. Moreover, we enhance the intra-class diversity by maximizing the Kullback-Leibler divergence within each synthetic class, i.e., content. We demonstrate the efficacy of our method through experiments on diverse datasets of varying size and resolution, achieving improvements of up to 4.1% on CIFAR10, 4.2% on CIFAR100, 4.3% on TinyImageNet, 2.0% on ImageNet-1K, 3.3% on ImageWoof, 2.5% on ImageNette, and 5.5% in continual learning accuracy.
Authors: Karan Daga, Siddharth Agarwal, Zaeem Moti, Matthew BK Lee, Munaib Din, David Wood, Marc Modat, Thomas C Booth
Abstract: Purpose: Subarachnoid haemorrhage is a potentially fatal consequence of intracranial aneurysm rupture, however, it is difficult to predict if aneurysms will rupture. Prophylactic treatment of an intracranial aneurysm also involves risk, hence identifying rupture-prone aneurysms is of substantial clinical importance. This systematic review aims to evaluate the performance of machine learning algorithms for predicting intracranial aneurysm rupture risk. Methods: MEDLINE, Embase, Cochrane Library and Web of Science were searched until December 2023. Studies incorporating any machine learning algorithm to predict the risk of rupture of an intracranial aneurysm were included. Risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). PROSPERO registration: CRD42023452509. Results: Out of 10,307 records screened, 20 studies met the eligibility criteria for this review incorporating a total of 20,286 aneurysm cases. The machine learning models gave a 0.66-0.90 range for performance accuracy. The models were compared to current clinical standards in six studies and gave mixed results. Most studies posed high or unclear risks of bias and concerns for applicability, limiting the inferences that can be drawn from them. There was insufficient homogenous data for a meta-analysis. Conclusions: Machine learning can be applied to predict the risk of rupture for intracranial aneurysms. However, the evidence does not comprehensively demonstrate superiority to existing practice, limiting its role as a clinical adjunct. Further prospective multicentre studies of recent machine learning tools are needed to prove clinical validation before they are implemented in the clinic.
Authors: Lei Fan, Junjie Huang, Donglin Di, Anyang Su, Maurice Pagnucco, Yang Song
Abstract: For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single model capable of handling multiple classes. However, directly extending early AD methods to multi-class settings often results in degraded performance. In this paper, we analyze this degradation observed in reconstruction-based methods, identifying two key issues: catastrophic forgetting and inter-class confusion. To this end, we propose a plug-and-play modification by incorporating class-aware contrastive learning (CL). By explicitly leveraging raw object category information (e.g., carpet or wood) as supervised signals, we apply local CL to fine-tune multiscale features and global CL to learn more compact feature representations of normal patterns, thereby effectively adapting the models to multi-class settings. Experiments across four datasets (over 60 categories) verify the effectiveness of our approach, yielding significant improvements and superior performance compared to advanced methods. Notably, ablation studies show that even using pseudo-class labels can achieve comparable performance.
Authors: Xueluan Gong, Bowei Tian, Meng Xue, Shuike Li, Yanjiao Chen, Qian Wang
Abstract: Vision transformers have achieved impressive performance in various vision-related tasks, but their vulnerability to backdoor attacks is under-explored. A handful of existing works focus on dirty-label attacks with wrongly-labeled poisoned training samples, which may fail if a benign model trainer corrects the labels. In this paper, we propose Megatron, an evasive clean-label backdoor attack against vision transformers, where the attacker injects the backdoor without manipulating the data-labeling process. To generate an effective trigger, we customize two loss terms based on the attention mechanism used in transformer networks, i.e., latent loss and attention diffusion loss. The latent loss aligns the last attention layer between triggered samples and clean samples of the target label. The attention diffusion loss emphasizes the attention diffusion area that encompasses the trigger. A theoretical analysis is provided to underpin the rationale behind the attention diffusion loss. Extensive experiments on CIFAR-10, GTSRB, CIFAR-100, and Tiny ImageNet demonstrate the effectiveness of Megatron. Megatron can achieve attack success rates of over 90% even when the position of the trigger is slightly shifted during testing. Furthermore, Megatron achieves better evasiveness than baselines regarding both human visual inspection and defense strategies (i.e., DBAVT, BAVT, Beatrix, TeCo, and SAGE).
Authors: Zijian Zhao, Zhijie Cai, Tingwei Chen, Xiaoyang Li, Hang Li, Guangxu Zhu
Abstract: As a key technology in Integrated Sensing and Communications (ISAC), Wi-Fi sensing has gained widespread application in various settings such as homes, offices, and public spaces. By analyzing the patterns of Channel State Information (CSI), we can obtain information about people's actions for tasks like person identification, gesture recognition, and fall detection. However, the CSI is heavily influenced by the environment, such that even minor environmental changes can significantly alter the CSI patterns. This will cause the performance deterioration and even failure when applying the Wi-Fi sensing model trained in one environment to another. To address this problem, we introduce a K-Nearest Neighbors Maximum Mean Discrepancy (KNN-MMD) model, a few-shot method for cross-domain Wi-Fi sensing. We propose a local distribution alignment method within each category, which outperforms traditional Domain Adaptation (DA) methods based on global alignment. Besides, our method can determine when to stop training, which cannot be realized by most DA methods. As a result, our method is more stable and can be better used in practice. The effectiveness of our method are evaluated in several cross-domain Wi-Fi sensing tasks, including gesture recognition, person identification, fall detection, and action recognition, using both a public dataset and a self-collected dataset. In one-shot scenario, our method achieves accuracy of 93.26%, 81.84%, 77.62%, and 75.30% in the four tasks respectively. To facilitate future research, we will make our code and dataset publicly available upon publication.
Authors: Yitian Zhang (Stephen), Huseyin Coskun (Stephen), Xu Ma (Stephen), Huan Wang (Stephen), Ke Ma (Stephen), Xi (Stephen), Chen, Derek Hao Hu, Yun Fu
Abstract: Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe that smaller ViTs are intrinsically the sub-networks of a larger ViT with different widths. Thus, we propose a general framework, named Scala, to enable a single network to represent multiple smaller ViTs with flexible inference capability, which aligns with the inherent design of ViT to vary from widths. Concretely, Scala activates several subnets during training, introduces Isolated Activation to disentangle the smallest sub-network from other subnets, and leverages Scale Coordination to ensure each sub-network receives simplified, steady, and accurate learning objectives. Comprehensive empirical validations on different tasks demonstrate that with only one-shot training, Scala learns slimmable representation without modifying the original ViT structure and matches the performance of Separate Training. Compared with the prior art, Scala achieves an average improvement of 1.6% on ImageNet-1K with fewer parameters.
Authors: Fardad Dadboud, Hamid Azad, Varun Mehta, Miodrag Bolic, Iraj Mntegh
Abstract: Dependable visual drone detection is crucial for the secure integration of drones into the airspace. However, drone detection accuracy is significantly affected by domain shifts due to environmental changes, varied points of view, and background shifts. To address these challenges, we present the DrIFT dataset, specifically developed for visual drone detection under domain shifts. DrIFT includes fourteen distinct domains, each characterized by shifts in point of view, synthetic-to-real data, season, and adverse weather. DrIFT uniquely emphasizes background shift by providing background segmentation maps to enable background-wise metrics and evaluation. Our new uncertainty estimation metric, MCDO-map, features lower postprocessing complexity, surpassing traditional methods. We use the MCDO-map in our uncertainty-aware unsupervised domain adaptation method, demonstrating superior performance to SOTA unsupervised domain adaptation techniques. The dataset is available at: https://github.com/CARG-uOttawa/DrIFT.git.
Authors: Yibin Wang, Zhiyu Tan, Junyan Wang, Xiaomeng Yang, Cheng Jin, Hao Li
Abstract: Recent advancements in text-to-video (T2V) generative models have shown impressive capabilities. However, these models are still inadequate in aligning synthesized videos with human preferences (e.g., accurately reflecting text descriptions), which is particularly difficult to address, as human preferences are inherently subjective and challenging to formalize as objective functions. Therefore, this paper proposes LiFT, a novel fine-tuning method leveraging human feedback for T2V model alignment. Specifically, we first construct a Human Rating Annotation dataset, LiFT-HRA, consisting of approximately 10k human annotations, each including a score and its corresponding rationale. Based on this, we train a reward model LiFT-Critic to learn reward function effectively, which serves as a proxy for human judgment, measuring the alignment between given videos and human expectations. Lastly, we leverage the learned reward function to align the T2V model by maximizing the reward-weighted likelihood. As a case study, we apply our pipeline to CogVideoX-2B, showing that the fine-tuned model outperforms the CogVideoX-5B across all 16 metrics, highlighting the potential of human feedback in improving the alignment and quality of synthesized videos.
Authors: Qingshan Xu, Jiequan Cui, Xuanyu Yi, Yuxuan Wang, Yuan Zhou, Yew-Soon Ong, Hanwang Zhang
Abstract: 3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients to grow Gaussians to reduce rendering loss. However, this average operation smooths the positional gradients from different viewpoints and rendering errors from different pixels, hindering the growth and optimization of many defective Gaussians. This leads to strong spurious artifacts in some areas. To address this problem, we propose Hard Gaussian Splatting, dubbed HGS, which considers multi-view significant positional gradients and rendering errors to grow hard Gaussians that fill the gaps of classical Gaussian Splatting on 3D scenes, thus achieving superior NVS results. In detail, we present positional gradient driven HGS, which leverages multi-view significant positional gradients to uncover hard Gaussians. Moreover, we propose rendering error guided HGS, which identifies noticeable pixel rendering errors and potentially over-large Gaussians to jointly mine hard Gaussians. By growing and optimizing these hard Gaussians, our method helps to resolve blurring and needle-like artifacts. Experiments on various datasets demonstrate that our method achieves state-of-the-art rendering quality while maintaining real-time efficiency.
Authors: Avinash Paliwal, Xilong Zhou, Andrii Tsarov, Nima Khademi Kalantari
Abstract: In this paper, we present PanoDreamer, a novel method for producing a coherent 360$^\circ$ 3D scene from a single input image. Unlike existing methods that generate the scene sequentially, we frame the problem as single-image panorama and depth estimation. Once the coherent panoramic image and its corresponding depth are obtained, the scene can be reconstructed by inpainting the small occluded regions and projecting them into 3D space. Our key contribution is formulating single-image panorama and depth estimation as two optimization tasks and introducing alternating minimization strategies to effectively solve their objectives. We demonstrate that our approach outperforms existing techniques in single-image 360$^\circ$ scene reconstruction in terms of consistency and overall quality.
Authors: Ying Jin, Zhuoran Zhou, Haoquan Fang, Jenq-Neng Hwang
Abstract: Medical image understanding requires meticulous examination of fine visual details, with particular regions requiring additional attention. While radiologists build such expertise over years of experience, it is challenging for AI models to learn where to look with limited amounts of training data. This limitation results in unsatisfying robustness in medical image understanding. To address this issue, we propose Diffusion-based Feature Augmentation (DAug), a portable method that improves a perception model's performance with a generative model's output. Specifically, we extend a radiology image to multiple channels, with the additional channels being the heatmaps of regions where diseases tend to develop. A diffusion-based image-to-image translation model was used to generate such heatmaps conditioned on selected disease classes. Our method is motivated by the fact that generative models learn the distribution of normal and abnormal images, and such knowledge is complementary to image understanding tasks. In addition, we propose the Image-Text-Class Hybrid Contrastive learning to utilize both text and class labels. With two novel approaches combined, our method surpasses baseline models without changing the model architecture, and achieves state-of-the-art performance on both medical image retrieval and classification tasks.
Authors: Jian Jin, Yang Shen, Zhenyong Fu, Jian Yang
Abstract: Customized generation aims to incorporate a novel concept into a pre-trained text-to-image model, enabling new generations of the concept in novel contexts guided by textual prompts. However, customized generation suffers from an inherent trade-off between concept fidelity and editability, i.e., between precisely modeling the concept and faithfully adhering to the prompts. Previous methods reluctantly seek a compromise and struggle to achieve both high concept fidelity and ideal prompt alignment simultaneously. In this paper, we propose a Divide, Conquer, then Integrate (DCI) framework, which performs a surgical adjustment in the early stage of denoising to liberate the fine-tuned model from the fidelity-editability trade-off at inference. The two conflicting components in the trade-off are decoupled and individually conquered by two collaborative branches, which are then selectively integrated to preserve high concept fidelity while achieving faithful prompt adherence. To obtain a better fine-tuned model, we introduce an Image-specific Context Optimization} (ICO) strategy for model customization. ICO replaces manual prompt templates with learnable image-specific contexts, providing an adaptive and precise fine-tuning direction to promote the overall performance. Extensive experiments demonstrate the effectiveness of our method in reconciling the fidelity-editability trade-off.
Authors: Rui Chen, Zehuan Wu, Yichen Liu, Yuxin Guo, Jingcheng Ni, Haifeng Xia, Siyu Xia
Abstract: The creation of diverse and realistic driving scenarios has become essential to enhance perception and planning capabilities of the autonomous driving system. However, generating long-duration, surround-view consistent driving videos remains a significant challenge. To address this, we present UniMLVG, a unified framework designed to generate extended street multi-perspective videos under precise control. By integrating single- and multi-view driving videos into the training data, our approach updates cross-frame and cross-view modules across three stages with different training objectives, substantially boosting the diversity and quality of generated visual content. Additionally, we employ the explicit viewpoint modeling in multi-view video generation to effectively improve motion transition consistency. Capable of handling various input reference formats (e.g., text, images, or video), our UniMLVG generates high-quality multi-view videos according to the corresponding condition constraints such as 3D bounding boxes or frame-level text descriptions. Compared to the best models with similar capabilities, our framework achieves improvements of 21.4% in FID and 36.5% in FVD.
Authors: Zilan Wang, Junfeng Guo, Jiacheng Zhu, Yiming Li, Heng Huang, Muhao Chen, Zhengzhong Tu
Abstract: Recent advances in large-scale text-to-image (T2I) diffusion models have enabled a variety of downstream applications, including style customization, subject-driven personalization, and conditional generation. As T2I models require extensive data and computational resources for training, they constitute highly valued intellectual property (IP) for their legitimate owners, yet making them incentive targets for unauthorized fine-tuning by adversaries seeking to leverage these models for customized, usually profitable applications. Existing IP protection methods for diffusion models generally involve embedding watermark patterns and then verifying ownership through generated outputs examination, or inspecting the model's feature space. However, these techniques are inherently ineffective in practical scenarios when the watermarked model undergoes fine-tuning, and the feature space is inaccessible during verification ((i.e., black-box setting). The model is prone to forgetting the previously learned watermark knowledge when it adapts to a new task. To address this challenge, we propose SleeperMark, a novel framework designed to embed resilient watermarks into T2I diffusion models. SleeperMark explicitly guides the model to disentangle the watermark information from the semantic concepts it learns, allowing the model to retain the embedded watermark while continuing to be fine-tuned to new downstream tasks. Our extensive experiments demonstrate the effectiveness of SleeperMark across various types of diffusion models, including latent diffusion models (e.g., Stable Diffusion) and pixel diffusion models (e.g., DeepFloyd-IF), showing robustness against downstream fine-tuning and various attacks at both the image and model levels, with minimal impact on the model's generative capability. The code is available at https://github.com/taco-group/SleeperMark.
Authors: Yaojie Zhang, Tianlun Huang, Weijun Wang, Wei Feng
Abstract: Traditional point cloud registration (PCR) methods for feature matching often employ the nearest neighbor policy. This leads to many-to-one matches and numerous potential inliers without any corresponding point. Recently, some approaches have framed the feature matching task as an assignment problem to achieve optimal one-to-one matches. We argue that the transition to the Assignment problem is not reliable for general correspondence-based PCR. In this paper, we propose a heuristics stable matching policy called GS-matching, inspired by the Gale-Shapley algorithm. Compared to the other matching policies, our method can perform efficiently and find more non-repetitive inliers under low overlapping conditions. Furthermore, we employ the probability theory to analyze the feature matching task, providing new insights into this research problem. Extensive experiments validate the effectiveness of our matching policy, achieving better registration recall on multiple datasets.
Authors: Lei Fan, Dongdong Fan, Zhiguang Hu, Yiwen Ding, Donglin Di, Kai Yi, Maurice Pagnucco, Yang Song
Abstract: We present MANTA, a visual-text anomaly detection dataset for tiny objects. The visual component comprises over 137.3K images across 38 object categories spanning five typical domains, of which 8.6K images are labeled as anomalous with pixel-level annotations. Each image is captured from five distinct viewpoints to ensure comprehensive object coverage. The text component consists of two subsets: Declarative Knowledge, including 875 words that describe common anomalies across various domains and specific categories, with detailed explanations for < what, why, how>, including causes and visual characteristics; and Constructivist Learning, providing 2K multiple-choice questions with varying levels of difficulty, each paired with images and corresponded answer explanations. We also propose a baseline for visual-text tasks and conduct extensive benchmarking experiments to evaluate advanced methods across different settings, highlighting the challenges and efficacy of our dataset.
Authors: Pawel Tomasz Pieta, Peter Winkel Rasmussen, Anders Bjorholm Dahl, Jeppe Revall Frisvad, Siavash Arjomand Bigdeli, Carsten Gundlach, Anders Nymark Christensen
Abstract: Influenced by the complexity of volumetric imaging, there is a shortage of established datasets useful for benchmarking volumetric deep-learning models. As a consequence, new and existing models are not easily comparable, limiting the development of architectures optimized specifically for volumetric data. To counteract this trend, we introduce MozzaVID - a large, clean, and versatile volumetric classification dataset. Our dataset contains X-ray computed tomography (CT) images of mozzarella microstructure and enables the classification of 25 cheese types and 149 cheese samples. We provide data in three different resolutions, resulting in three dataset instances containing from 591 to 37,824 images. While being general-purpose, the dataset also facilitates investigating mozzarella structure properties. The structure of food directly affects its functional properties and thus its consumption experience. Understanding food structure helps tune the production and mimicking it enables sustainable alternatives to animal-derived food products. The complex and disordered nature of food structures brings a unique challenge, where a choice of appropriate imaging method, scale, and sample size is not trivial. With this dataset we aim to address these complexities, contributing to more robust structural analysis models. The dataset can be downloaded from: https://archive.compute.dtu.dk/files/public/projects/MozzaVID/.
URLs: https://archive.compute.dtu.dk/files/public/projects/MozzaVID/.
Authors: Jixuan Fan, Wanhua Li, Yifei Han, Yansong Tang
Abstract: 3D Gaussian Splatting has demonstrated notable success in large-scale scene reconstruction, but challenges persist due to high training memory consumption and storage overhead. Hybrid representations that integrate implicit and explicit features offer a way to mitigate these limitations. However, when applied in parallelized block-wise training, two critical issues arise since reconstruction accuracy deteriorates due to reduced data diversity when training each block independently, and parallel training restricts the number of divided blocks to the available number of GPUs. To address these issues, we propose Momentum-GS, a novel approach that leverages momentum-based self-distillation to promote consistency and accuracy across the blocks while decoupling the number of blocks from the physical GPU count. Our method maintains a teacher Gaussian decoder updated with momentum, ensuring a stable reference during training. This teacher provides each block with global guidance in a self-distillation manner, promoting spatial consistency in reconstruction. To further ensure consistency across the blocks, we incorporate block weighting, dynamically adjusting each block's weight according to its reconstruction accuracy. Extensive experiments on large-scale scenes show that our method consistently outperforms existing techniques, achieving a 12.8% improvement in LPIPS over CityGaussian with much fewer divided blocks and establishing a new state of the art. Project page: https://jixuan-fan.github.io/Momentum-GS_Page/
Authors: Gouranga Bala, Anuj Gupta, Subrat Kumar Behera, Amit Sethi
Abstract: Deep learning models rely heavily on large volumes of labeled data to achieve high performance. However, real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process. Instance-dependent label noise (IDN), where the probability of a label being corrupted depends on the input features, poses a significant challenge because it is more prevalent and harder to address than instance-independent noise. In this paper, we propose a novel hybrid framework that combines self-supervised learning using SimCLR with iterative pseudo-label refinement to mitigate the effects of IDN. The self-supervised pre-training phase enables the model to learn robust feature representations without relying on potentially noisy labels, establishing a noise-agnostic foundation. Subsequently, we employ an iterative training process with pseudo-label refinement, where confidently predicted samples are identified through a multistage approach and their labels are updated to improve label quality progressively. We evaluate our method on the CIFAR-10 and CIFAR-100 datasets augmented with synthetic instance-dependent noise at varying noise levels. Experimental results demonstrate that our approach significantly outperforms several state-of-the-art methods, particularly under high noise conditions, achieving notable improvements in classification accuracy and robustness. Our findings suggest that integrating self-supervised learning with iterative pseudo-label refinement offers an effective strategy for training deep neural networks on noisy datasets afflicted by instance-dependent label noise.
Authors: Yongxin Wang, Meng Cao, Haokun Lin, Mingfei Han, Liang Ma, Jin Jiang, Yuhao Cheng, Xiaodan Liang
Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress on various visual question answering and reasoning tasks leveraging instruction fine-tuning specific datasets. They can also learn from preference data annotated by human to enhance their reasoning ability and mitigate hallucinations. Most of preference data is generated from the model itself. However, existing methods require high-quality critical labels, which are costly and rely on human or proprietary models like GPT-4V. In this work, we propose Enhancing Alignment in MLLMs via Critical Observation (EACO), which aligns MLLMs by self-generated preference data using only 5k images economically. Our approach begins with collecting and refining a Scoring Evaluation Instruction-tuning dataset to train a critical evaluation model, termed the Critic. This Critic observes model responses across multiple dimensions, selecting preferred and non-preferred outputs for refined Direct Preference Optimization (DPO) tuning. To further enhance model performance, we employ an additional supervised fine-tuning stage after preference tuning. EACO reduces the overall hallucinations by 65.6% on HallusionBench and improves the reasoning ability by 21.8% on MME-Cognition. EACO achieves an 8.5% improvement over LLaVA-v1.6-Mistral-7B across multiple benchmarks. Remarkably, EACO also shows the potential critical ability in open-source MLLMs, demonstrating that EACO is a viable path to boost the competence of MLLMs.
Authors: Khurram Azeem Hashmi, Talha Uddin Sheikh, Didier Stricker, Muhammad Zeshan Afzal
Abstract: The primary challenge in Video Object Detection (VOD) is effectively exploiting temporal information to enhance object representations. Traditional strategies, such as aggregating region proposals, often suffer from feature variance due to the inclusion of background information. We introduce a novel instance mask-based feature aggregation approach, significantly refining this process and deepening the understanding of object dynamics across video frames. We present FAIM, a new VOD method that enhances temporal Feature Aggregation by leveraging Instance Mask features. In particular, we propose the lightweight Instance Feature Extraction Module (IFEM) to learn instance mask features and the Temporal Instance Classification Aggregation Module (TICAM) to aggregate instance mask and classification features across video frames. Using YOLOX as a base detector, FAIM achieves 87.9% mAP on the ImageNet VID dataset at 33 FPS on a single 2080Ti GPU, setting a new benchmark for the speed-accuracy trade-off. Additional experiments on multiple datasets validate that our approach is robust, method-agnostic, and effective in multi-object tracking, demonstrating its broader applicability to video understanding tasks.
Authors: Xiaojie Yin, Qilong Wang, Bing Cao, Qinghua Hu
Abstract: Recently, many studies have been conducted to enhance the zero-shot generalization ability of vision-language models (e.g., CLIP) by addressing the semantic misalignment between image and text embeddings in downstream tasks. Although many efforts have been made, existing methods barely consider the fact that a class of images can be described by notably different textual concepts due to well-known lexical variation in natural language processing, which heavily affects the zero-shot generalization of CLIP. Therefore, this paper proposes a \textbf{S}ynonymous \textbf{S}emantic \textbf{S}pace ($S^3$) for each image class, rather than relying on a single textual concept, achieving more stable semantic alignment and improving the zero-shot generalization of CLIP. Specifically, our $S^3$ method first generates several synonymous concepts based on the label of each class by using large language models, and constructs a continuous yet compact synonymous semantic space based on the Vietoris-Rips complex of the generated synonymous concepts. Furthermore, we explore the effect of several point-to-space metrics on our $S^3$, while presenting a point-to-local-center metric to compute similarity between image embeddings and the synonymous semantic space of each class, accomplishing effective zero-shot predictions. Extensive experiments are conducted across 17 benchmarks, including fine-grained zero-shot classification, natural distribution zero-shot classification, and open-vocabulary segmentation, and the results show that our $S^3$ outperforms state-of-the-art methods.
Authors: Gaurav Shrivastava, Abhinav Shrivastava
Abstract: Diffusion models have made significant strides in image generation, mastering tasks such as unconditional image synthesis, text-image translation, and image-to-image conversions. However, their capability falls short in the realm of video prediction, mainly because they treat videos as a collection of independent images, relying on external constraints such as temporal attention mechanisms to enforce temporal coherence. In our paper, we introduce a novel model class, that treats video as a continuous multi-dimensional process rather than a series of discrete frames. We also report a reduction of 75\% sampling steps required to sample a new frame thus making our framework more efficient during the inference time. Through extensive experimentation, we establish state-of-the-art performance in video prediction, validated on benchmark datasets including KTH, BAIR, Human3.6M, and UCF101. Navigate to the project page https://www.cs.umd.edu/~gauravsh/cvp/supp/website.html for video results.}
URLs: https://www.cs.umd.edu/
Authors: Gaurav Shrivastava, Ser-Nam Lim, Abhinav Shrivastava
Abstract: In the evolving landscape of video enhancement and editing methodologies, a majority of deep learning techniques often rely on extensive datasets of observed input and ground truth sequence pairs for optimal performance. Such reliance often falters when acquiring data becomes challenging, especially in tasks like video dehazing and relighting, where replicating identical motions and camera angles in both corrupted and ground truth sequences is complicated. Moreover, these conventional methodologies perform best when the test distribution closely mirrors the training distribution. Recognizing these challenges, this paper introduces a novel video decomposition prior `\texttt{VDP}' framework which derives inspiration from professional video editing practices. Our methodology does not mandate task-specific external data corpus collection, instead pivots to utilizing the motion and appearance of the input video. \texttt{VDP} framework decomposes a video sequence into a set of multiple RGB layers and associated opacity levels. These set of layers are then manipulated individually to obtain the desired results. We addresses tasks such as video object segmentation, dehazing, and relighting. Moreover, we introduce a novel logarithmic video decomposition formulation for video relighting tasks, setting a new benchmark over the existing methodologies. We observe the property of relighting emerge as we optimize for our novel relighting decomposition formulation. We evaluate our approach on standard video datasets like DAVIS, REVIDE, \& SDSD and show qualitative results on a diverse array of internet videos. Project Page - https://www.cs.umd.edu/~gauravsh/video_decomposition/index.html for video results.
URLs: https://www.cs.umd.edu/
Authors: Yishuo Chen, Boran Wang, Xinyu Guo, Wenbin Zhu, Jiasheng He, Xiaobin Liu, Jing Yuan
Abstract: Object detection in poor-illumination environments is a challenging task as objects are usually not clearly visible in RGB images. As infrared images provide additional clear edge information that complements RGB images, fusing RGB and infrared images has potential to enhance the detection ability in poor-illumination environments. However, existing works involving both visible and infrared images only focus on image fusion, instead of object detection. Moreover, they directly fuse the two kinds of image modalities, which ignores the mutual interference between them. To fuse the two modalities to maximize the advantages of cross-modality, we design a dual-enhancement-based cross-modality object detection network DEYOLO, in which semantic-spatial cross modality and novel bi-directional decoupled focus modules are designed to achieve the detection-centered mutual enhancement of RGB-infrared (RGB-IR). Specifically, a dual semantic enhancing channel weight assignment module (DECA) and a dual spatial enhancing pixel weight assignment module (DEPA) are firstly proposed to aggregate cross-modality information in the feature space to improve the feature representation ability, such that feature fusion can aim at the object detection task. Meanwhile, a dual-enhancement mechanism, including enhancements for two-modality fusion and single modality, is designed in both DECAand DEPAto reduce interference between the two kinds of image modalities. Then, a novel bi-directional decoupled focus is developed to enlarge the receptive field of the backbone network in different directions, which improves the representation quality of DEYOLO. Extensive experiments on M3FD and LLVIP show that our approach outperforms SOTA object detection algorithms by a clear margin. Our code is available at https://github.com/chips96/DEYOLO.
Authors: Zehao Wang, Xinpeng Liu, Xiaoqian Wu, Yudonglin Zhang, Zhou Fang, Yifan Fang, Junfu Pu, Cewu Lu, Yong-Lu Li
Abstract: Multimodal Large Language Models (MLLMs) have garnered significant attention recently and demonstrate outstanding capabilities in various tasks such as OCR, VQA, captioning, $\textit{etc}$. However, hallucination remains a persistent issue. While numerous methods have been proposed to mitigate hallucinations, achieving notable improvements, these methods primarily focus on mitigating hallucinations about $\textbf{object/noun-related}$ concepts. Verb concepts, crucial for understanding human actions, have been largely overlooked. In this paper, to the best of our knowledge, we are the $\textbf{first}$ to investigate the $\textbf{verb hallucination}$ phenomenon of MLLMs from various perspectives. Our findings reveal that most state-of-the-art MLLMs suffer from severe verb hallucination. To assess the effectiveness of existing mitigation methods for object concept hallucination on verb hallucination, we evaluated these methods and found that they do not effectively address verb hallucination. To address this issue, we propose a novel rich verb knowledge-based tuning method to mitigate verb hallucination. The experiment results demonstrate that our method significantly reduces hallucinations related to verbs. $\textit{Our code and data will be made publicly available}$.
Authors: Michael Schwimmbeck, Serouj Khajarian, Konstantin Holzapfel, Johannes Schmidt, Stefanie Remmele
Abstract: In the context of medical Augmented Reality (AR) applications, object tracking is a key challenge and requires a significant amount of annotation masks. As segmentation foundation models like the Segment Anything Model (SAM) begin to emerge, zero-shot segmentation requires only minimal human participation obtaining high-quality object masks. We introduce a HoloLens-Object-Labeling (HOLa) Unity and Python application based on the SAM-Track algorithm that offers fully automatic single object annotation for HoloLens 2 while requiring minimal human participation. HOLa does not have to be adjusted to a specific image appearance and could thus alleviate AR research in any application field. We evaluate HOLa for different degrees of image complexity in open liver surgery and in medical phantom experiments. Using HOLa for image annotation can increase the labeling speed by more than 500 times while providing Dice scores between 0.875 and 0.982, which are comparable to human annotators. Our code is publicly available at: https://github.com/mschwimmbeck/HOLa
Authors: Xi Zhang, Zaiqiao Meng, Jake Lever, Edmond S. L. Ho
Abstract: We introduce a radiology-focused visual language model designed to generate radiology reports from chest X-rays. Building on previous findings that large language models (LLMs) can acquire multimodal capabilities when aligned with pretrained vision encoders, we demonstrate similar potential with chest X-ray images. This integration enhances the ability of model to understand and describe chest X-ray images. Our model combines an image encoder with a fine-tuned LLM based on the Vicuna-7B architecture, enabling it to generate different sections of a radiology report with notable accuracy. The training process involves a two-stage approach: (i) initial alignment of chest X-ray features with the LLM (ii) followed by fine-tuning for radiology report generation.
Authors: Peng Chen, Xiaobao Wei, Qingpo Wuwu, Xinyi Wang, Xingyu Xiao, Ming Lu
Abstract: Reconstructing high-fidelity 3D head avatars is crucial in various applications such as virtual reality. The pioneering methods reconstruct realistic head avatars with Neural Radiance Fields (NeRF), which have been limited by training and rendering speed. Recent methods based on 3D Gaussian Splatting (3DGS) significantly improve the efficiency of training and rendering. However, the surface inconsistency of 3DGS results in subpar geometric accuracy; later, 2DGS uses 2D surfels to enhance geometric accuracy at the expense of rendering fidelity. To leverage the benefits of both 2DGS and 3DGS, we propose a novel method named MixedGaussianAvatar for realistically and geometrically accurate head avatar reconstruction. Our main idea is to utilize 2D Gaussians to reconstruct the surface of the 3D head, ensuring geometric accuracy. We attach the 2D Gaussians to the triangular mesh of the FLAME model and connect additional 3D Gaussians to those 2D Gaussians where the rendering quality of 2DGS is inadequate, creating a mixed 2D-3D Gaussian representation. These 2D-3D Gaussians can then be animated using FLAME parameters. We further introduce a progressive training strategy that first trains the 2D Gaussians and then fine-tunes the mixed 2D-3D Gaussians. We demonstrate the superiority of MixedGaussianAvatar through comprehensive experiments. The code will be released at: https://github.com/ChenVoid/MGA/.
Authors: Mohd Faiz Ansari, Rakshit Sandilya, Mohammed Javed, David Doermann
Abstract: Road anomalies can be defined as irregularities on the road surface or in the surface itself. Some may be intentional (such as speedbumps), accidental (such as materials falling off a truck), or the result of roads' excessive use or low or no maintenance, such as potholes. Despite their varying origins, these irregularities often harm vehicles substantially. Speed bumps are intentionally placed for safety but are dangerous due to their non-standard shape, size, and lack of proper markings. Potholes are unintentional and can also cause severe damage. To address the detection of these anomalies, we need an automated road monitoring system. Today, various systems exist that use visual information to track these anomalies. Still, due to poor lighting conditions and improper or missing markings, they may go undetected and have severe consequences for public transport, automated vehicles, etc. In this paper, the Enhanced Temporal-BiLSTM Network (ETLNet) is introduced as a novel approach that integrates two Temporal Convolutional Network (TCN) layers with a Bidirectional Long Short-Term Memory (BiLSTM) layer. This combination is tailored to detect anomalies effectively irrespective of lighting conditions, as it depends not on visuals but smartphone inertial sensor data. Our methodology employs accelerometer and gyroscope sensors, typically in smartphones, to gather data on road conditions. Empirical evaluations demonstrate that the ETLNet model maintains an F1-score for detecting speed bumps of 99.3%. The ETLNet model's robustness and efficiency significantly advance automated road surface monitoring technologies.
Authors: Cameron Braunstein, Hevra Petekkaya, Jan Eric Lenssen, Mariya Toneva, Eddy Ilg
Abstract: We introduce SLayR, Scene Layout Generation with Rectified flow. State-of-the-art text-to-image models achieve impressive results. However, they generate images end-to-end, exposing no fine-grained control over the process. SLayR presents a novel transformer-based rectified flow model for layout generation over a token space that can be decoded into bounding boxes and corresponding labels, which can then be transformed into images using existing models. We show that established metrics for generated images are inconclusive for evaluating their underlying scene layout, and introduce a new benchmark suite, including a carefully designed repeatable human-evaluation procedure that assesses the plausibility and variety of generated layouts. In contrast to previous works, which perform well in either high variety or plausibility, we show that our approach performs well on both of these axes at the same time. It is also at least 5x times smaller in the number of parameters and 37% faster than the baselines. Our complete text-to-image pipeline demonstrates the added benefits of an interpretable and editable intermediate representation.
Authors: Zeqing Wang, Kangye Ji, Di Wang, Fei Cheng
Abstract: Segment Anything Model (SAM) struggles with segmenting objects in the open world, especially across diverse and dynamic domains. Continual segmentation (CS) is a potential technique to solve this issue, but a significant obstacle is the intractable balance between previous domains (stability) and new domains (plasticity) during CS. Furthermore, how to utilize two kinds of features of SAM, images and prompts, in an efficient and effective CS manner remains a significant hurdle. In this work, we propose a novel CS method, termed SAMCL, to address these challenges. It is the first study to empower SAM with the CS ability across dynamic domains. SAMCL decouples stability and plasticity during CS by two components: $\textit{AugModule}$ and $\textit{Module Selector}$. Specifically, SAMCL leverages individual $\textit{AugModule}$ to effectively and efficiently learn new relationships between images and prompts in each domain. $\textit{Module Selector}$ selects the appropriate module during testing, based on the inherent ability of SAM to distinguish between different domains. These two components enable SAMCL to realize a task-agnostic method without any interference across different domains. Experimental results demonstrate that SAMCL outperforms state-of-the-art methods, achieving an exceptionally low average forgetting of just $0.5$%, along with at least a $2.5$% improvement in transferring to unseen domains. Moreover, the tunable parameter consumption in AugModule is about $0.236$MB, marking at least a $23.3$% reduction compared to other fine-tuning methods.
Authors: Piercarlo Dondi, Alessio Gullotti, Michele Inchingolo, Ilaria Senaldi, Chiara Casarotti, Luca Lombardi, Marco Piastra
Abstract: Following an earthquake, it is vital to quickly evaluate the safety of the impacted areas. Damage detection systems, powered by computer vision and deep learning, can assist experts in this endeavor. However, the lack of extensive, labeled datasets poses a challenge to the development of these systems. In this study, we introduce a technique for generating semi-synthetic images to be used as data augmentation during the training of a damage detection system. We specifically aim to generate images of cracks, which are a prevalent and indicative form of damage. The central concept is to employ parametric meta-annotations to guide the process of generating cracks on 3D models of real-word structures. The governing parameters of these meta-annotations can be adjusted iteratively to yield images that are optimally suited for improving detectors' performance. Comparative evaluations demonstrated that a crack detection system trained with a combination of real and semi-synthetic images outperforms a system trained on real images alone.
Authors: Chi-Wei Hsiao, Yu-Lun Liu, Cheng-Kun Yang, Sheng-Po Kuo, Kevin Jou, Chia-Ping Chen
Abstract: While recent works on blind face image restoration have successfully produced impressive high-quality (HQ) images with abundant details from low-quality (LQ) input images, the generated content may not accurately reflect the real appearance of a person. To address this problem, incorporating well-shot personal images as additional reference inputs could be a promising strategy. Inspired by the recent success of the Latent Diffusion Model (LDM), we propose ReF-LDM, an adaptation of LDM designed to generate HQ face images conditioned on one LQ image and multiple HQ reference images. Our model integrates an effective and efficient mechanism, CacheKV, to leverage the reference images during the generation process. Additionally, we design a timestep-scaled identity loss, enabling our LDM-based model to focus on learning the discriminating features of human faces. Lastly, we construct FFHQ-Ref, a dataset consisting of 20,405 high-quality (HQ) face images with corresponding reference images, which can serve as both training and evaluation data for reference-based face restoration models.
Authors: Wanyue Zhang, Rishabh Dabral, Vladislav Golyanik, Vasileios Choutas, Eduardo Alvarado, Thabo Beeler, Marc Habermann, Christian Theobalt
Abstract: We present BimArt, a novel generative approach for synthesizing 3D bimanual hand interactions with articulated objects. Unlike prior works, we do not rely on a reference grasp, a coarse hand trajectory, or separate modes for grasping and articulating. To achieve this, we first generate distance-based contact maps conditioned on the object trajectory with an articulation-aware feature representation, revealing rich bimanual patterns for manipulation. The learned contact prior is then used to guide our hand motion generator, producing diverse and realistic bimanual motions for object movement and articulation. Our work offers key insights into feature representation and contact prior for articulated objects, demonstrating their effectiveness in taming the complex, high-dimensional space of bimanual hand-object interactions. Through comprehensive quantitative experiments, we demonstrate a clear step towards simplified and high-quality hand-object animations that excel over the state-of-the-art in motion quality and diversity.
Authors: Zijian Zhao, Tingwei Chen, Fanyi Meng, Zhijie Cai, Hang Li, Xiaoyang Li, Guangxu Zhu
Abstract: Wi-Fi localization and tracking has shown immense potential due to its privacy-friendliness, wide coverage, permeability, independence from lighting conditions, and low cost. Current methods can be broadly categorized as model-based and data-driven approaches, where data-driven methods show better performance and have less requirement for specialized devices, but struggle with limited datasets for training. Due to limitations in current data collection methods, most datasets only provide coarse-grained ground truth (GT) or limited amount of label points, which greatly hinders the development of data-driven methods. Even though lidar can provide accurate GT, their high cost makes them inaccessible to many users. To address these challenges, we propose LoFi, a vision-aided label generator for Wi-Fi localization and tracking, which can generate ground truth position coordinates solely based on 2D images. The easy and quick data collection method also helps data-driven based methods deploy in practice, since Wi-Fi is a low-generalization modality and when using relevant methods, it always requires fine-tuning the model using newly collected data. Based on our method, we also collect a Wi-Fi tracking and localization dataset using ESP32-S3 and a webcam. To facilitate future research, we will make our code and dataset publicly available upon publication.
Authors: Nikita Gabdullin
Abstract: This paper studies a combined person reidentification (re-id) method that uses human parsing, analytical feature extraction and similarity estimation schemes. One of its prominent features is its low computational requirements so it can be implemented on edge devices. The method allows direct comparison of specific image regions using interpretable features which consist of color and texture channels. It is proposed to analyze and compare colors in CIE-Lab color space using histogram smoothing for noise reduction. A novel pre-configured latent space (LS) supervised autoencoder (SAE) is proposed for texture analysis which encodes input textures as LS points. This allows to obtain more accurate similarity measures compared to simplistic label comparison. The proposed method also does not rely upon photos or other re-id data for training, which makes it completely re-id dataset-agnostic. The viability of the proposed method is verified by computing rank-1, rank-10, and mAP re-id metrics on Market1501 dataset. The results are comparable to those of conventional deep learning methods and the potential ways to further improve the method are discussed.
Authors: Ivanna Kramer, Lara Blomenkamp, Kevin Weirauch, Sabine Bauer, Dietrich Paulus
Abstract: Spinal ligaments are crucial elements in the complex biomechanical simulation models as they transfer forces on the bony structure, guide and limit movements and stabilize the spine. The spinal ligaments encompass seven major groups being responsible for maintaining functional interrelationships among the other spinal components. Determination of the ligament origin and insertion points on the 3D vertebrae models is an essential step in building accurate and complex spine biomechanical models. In our paper, we propose a pipeline that is able to detect 66 spinal ligament attachment points by using a step-wise approach. Our method incorporates a fast vertebra registration that strategically extracts only 15 3D points to compute the transformation, and edge detection for a precise projection of the registered ligaments onto any given patient-specific vertebra model. Our method shows high accuracy, particularly in identifying landmarks on the anterior part of the vertebra with an average distance of 2.24 mm for anterior longitudinal ligament and 1.26 mm for posterior longitudinal ligament landmarks. The landmark detection requires approximately 3.0 seconds per vertebra, providing a substantial improvement over existing methods. Clinical relevance: using the proposed method, the required landmarks that represent origin and insertion points for forces in the biomechanical spine models can be localized automatically in an accurate and time-efficient manner.
Authors: Xiaofeng Tan, Hongsong Wang, Xin Geng, Pan Zhou
Abstract: Text-to-motion generation is essential for advancing the creative industry but often presents challenges in producing consistent, realistic motions. To address this, we focus on fine-tuning text-to-motion models to consistently favor high-quality, human-preferred motions, a critical yet largely unexplored problem. In this work, we theoretically investigate the DPO under both online and offline settings, and reveal their respective limitation: overfitting in offline DPO, and biased sampling in online DPO. Building on our theoretical insights, we introduce Semi-online Preference Optimization (SoPo), a DPO-based method for training text-to-motion models using "semi-online" data pair, consisting of unpreferred motion from online distribution and preferred motion in offline datasets. This method leverages both online and offline DPO, allowing each to compensate for the other's limitations. Extensive experiments demonstrate that SoPo outperforms other preference alignment methods, with an MM-Dist of 3.25% (vs e.g. 0.76% of MoDiPO) on the MLD model, 2.91% (vs e.g. 0.66% of MoDiPO) on MDM model, respectively. Additionally, the MLD model fine-tuned by our SoPo surpasses the SoTA model in terms of R-precision and MM Dist. Visualization results also show the efficacy of our SoPo in preference alignment. Our project page is https://sopo-motion.github.io.
Authors: Ruoyu Wang, Huayang Huang, Ye Zhu, Olga Russakovsky, Yu Wu
Abstract: Text-to-image synthesis (T2I) has advanced remarkably with the emergence of large-scale diffusion models. In the conventional setup, the text prompt provides explicit, user-defined guidance, directing the generation process by denoising a randomly sampled Gaussian noise. In this work, we reveal that the often-overlooked noise itself encodes inherent generative tendencies, acting as a "silent prompt" that implicitly guides the output. This implicit guidance, embedded in the noise scheduler design of diffusion model formulations and their training stages, generalizes across a wide range of T2I models and backbones. Building on this insight, we introduce NoiseQuery, a novel strategy that selects optimal initial noise from a pre-built noise library to meet diverse user needs. Our approach not only enhances high-level semantic alignment with text prompts, but also allows for nuanced adjustments of low-level visual attributes, such as texture, sharpness, shape, and color, which are typically challenging to control through text alone. Extensive experiments across various models and target attributes demonstrate the strong performance and zero-shot transferability of our approach, requiring no additional optimization.
Authors: Tiago Roxo, Joana C. Costa, Pedro R. M. In\'acio, Hugo Proen\c{c}a
Abstract: Deep learning models are widely used nowadays for their reliability in performing various tasks. However, they do not typically provide the reasoning behind their decision, which is a significant drawback, particularly for more sensitive areas such as biometrics, security and healthcare. The most commonly used approaches to provide interpretability create visual attention heatmaps of regions of interest on an image based on models gradient backpropagation. Although this is a viable approach, current methods are targeted toward image settings and default/standard deep learning models, meaning that they require significant adaptations to work on video/multi-modal settings and custom architectures. This paper proposes an approach for interpretability that is model-agnostic, based on a novel use of the Squeeze and Excitation (SE) block that creates visual attention heatmaps. By including an SE block prior to the classification layer of any model, we are able to retrieve the most influential features via SE vector manipulation, one of the key components of the SE block. Our results show that this new SE-based interpretability can be applied to various models in image and video/multi-modal settings, namely biometrics of facial features with CelebA and behavioral biometrics using Active Speaker Detection datasets. Furthermore, our proposal does not compromise model performance toward the original task, and has competitive results with current interpretability approaches in state-of-the-art object datasets, highlighting its robustness to perform in varying data aside from the biometric context.
Authors: Donald Shenaj, Ondrej Bohdal, Mete Ozay, Pietro Zanuttigh, Umberto Michieli
Abstract: Recent advancements in image generation models have enabled personalized image creation with both user-defined subjects (content) and styles. Prior works achieved personalization by merging corresponding low-rank adaptation parameters (LoRAs) through optimization-based methods, which are computationally demanding and unsuitable for real-time use on resource-constrained devices like smartphones. To address this, we introduce LoRA.rar, a method that not only improves image quality but also achieves a remarkable speedup of over $4000\times$ in the merging process. LoRA.rar pre-trains a hypernetwork on a diverse set of content-style LoRA pairs, learning an efficient merging strategy that generalizes to new, unseen content-style pairs, enabling fast, high-quality personalization. Moreover, we identify limitations in existing evaluation metrics for content-style quality and propose a new protocol using multimodal large language models (MLLM) for more accurate assessment. Our method significantly outperforms the current state of the art in both content and style fidelity, as validated by MLLM assessments and human evaluations.
Authors: Tiago Roxo, Joana C. Costa, Pedro R. M. In\'acio, Hugo Proen\c{c}a
Abstract: State-of-the-art Active Speaker Detection (ASD) approaches heavily rely on audio and facial features to perform, which is not a sustainable approach in wild scenarios. Although these methods achieve good results in the standard AVA-ActiveSpeaker set, a recent wilder ASD dataset (WASD) showed the limitations of such models and raised the need for new approaches. As such, we propose BIAS, a model that, for the first time, combines audio, face, and body information, to accurately predict active speakers in varying/challenging conditions. Additionally, we design BIAS to provide interpretability by proposing a novel use for Squeeze-and-Excitation blocks, namely in attention heatmaps creation and feature importance assessment. For a full interpretability setup, we annotate an ASD-related actions dataset (ASD-Text) to finetune a ViT-GPT2 for text scene description to complement BIAS interpretability. The results show that BIAS is state-of-the-art in challenging conditions where body-based features are of utmost importance (Columbia, open-settings, and WASD), and yields competitive results in AVA-ActiveSpeaker, where face is more influential than body for ASD. BIAS interpretability also shows the features/aspects more relevant towards ASD prediction in varying settings, making it a strong baseline for further developments in interpretable ASD models, and is available at https://github.com/Tiago-Roxo/BIAS.
Authors: Chaoda Zheng, Feng Wang, Naiyan Wang, Shuguang Cui, Zhen Li
Abstract: While 3D object bounding box (bbox) representation has been widely used in autonomous driving perception, it lacks the ability to capture the precise details of an object's intrinsic geometry. Recently, occupancy has emerged as a promising alternative for 3D scene perception. However, constructing a high-resolution occupancy map remains infeasible for large scenes due to computational constraints. Recognizing that foreground objects only occupy a small portion of the scene, we introduce object-centric occupancy as a supplement to object bboxes. This representation not only provides intricate details for detected objects but also enables higher voxel resolution in practical applications. We advance the development of object-centric occupancy perception from both data and algorithm perspectives. On the data side, we construct the first object-centric occupancy dataset from scratch using an automated pipeline. From the algorithmic standpoint, we introduce a novel object-centric occupancy completion network equipped with an implicit shape decoder that manages dynamic-size occupancy generation. This network accurately predicts the complete object-centric occupancy volume for inaccurate object proposals by leveraging temporal information from long sequences. Our method demonstrates robust performance in completing object shapes under noisy detection and tracking conditions. Additionally, we show that our occupancy features significantly enhance the detection results of state-of-the-art 3D object detectors, especially for incomplete or distant objects in the Waymo Open Dataset.
Authors: Raul Alfredo de Sousa Silva, Yasmine Belaidouni, Rabah Iguernaissi, Djamal Merad, S\'everine Dubuisson
Abstract: Understanding the behavior of laboratory animals is a key to find answers about diseases and neurodevelopmental disorders that also affects humans. One behavior of interest is the stopping, as it correlates with exploration, feeding and sleeping habits of individuals. To improve comprehension of animal's behavior, we focus on identifying trait revealing age/sex of mice through the series of stopping spots of each individual. We track 4 mice using LiveMouseTracker (LMT) system during 3 days. Then, we build a stack of 2D histograms of the stop positions. This stack of histograms passes through a shallow CNN architecture to classify mice in terms of age and sex. We observe that female mice show more recognizable behavioral patterns, reaching a classification accuracy of more than 90%, while males, which do not present as many distinguishable patterns, reach an accuracy of 62.5%. To gain explainability from the model, we look at the activation function of the convolutional layers and found that some regions of the cage are preferentially explored by females. Males, especially juveniles, present behavior patterns that oscillate between juvenile female and adult male.
Authors: Xinyi Zhang, Naiqi Li, Angela Dai
Abstract: While remarkable success has been achieved through diffusion-based 3D generative models for shapes, 4D generative modeling remains challenging due to the complexity of object deformations over time. We propose DNF, a new 4D representation for unconditional generative modeling that efficiently models deformable shapes with disentangled shape and motion while capturing high-fidelity details in the deforming objects. To achieve this, we propose a dictionary learning approach to disentangle 4D motion from shape as neural fields. Both shape and motion are represented as learned latent spaces, where each deformable shape is represented by its shape and motion global latent codes, shape-specific coefficient vectors, and shared dictionary information. This captures both shape-specific detail and global shared information in the learned dictionary. Our dictionary-based representation well balances fidelity, contiguity and compression -- combined with a transformer-based diffusion model, our method is able to generate effective, high-fidelity 4D animations.
Authors: Thomas Walker, Octave Mariotti, Amir Vaxman, Hakan Bilen
Abstract: Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction methods use a "one-size-fits-all" approach to encoding, choosing a fixed set of encoding functions, and therefore bias, across all scenes. Current state-of-the-art surface reconstruction approaches leverage grid-based multi-resolution hash encoding in order to recover high-detail geometry. We propose a learned approach which allows the network to choose its encoding basis as a function of space, by masking the contribution of features stored at separate grid resolutions. The resulting spatially adaptive approach allows the network to fit a wider range of frequencies without introducing noise. We test our approach on standard benchmark surface reconstruction datasets and achieve state-of-the-art performance on two benchmark datasets.
Authors: Chaitat Utintu, Pinaki Nath Chowdhury, Aneeshan Sain, Subhadeep Koley, Ayan Kumar Bhunia, Yi-Zhe Song
Abstract: Video colour editing is a crucial task for content creation, yet existing solutions either require painstaking frame-by-frame manipulation or produce unrealistic results with temporal artefacts. We present a practical, training-free framework that makes precise video colour editing accessible through an intuitive interface while maintaining professional-quality output. Our key insight is that by decoupling spatial and temporal aspects of colour editing, we can better align with users' natural workflow -- allowing them to focus on precise colour selection in key frames before automatically propagating changes across time. We achieve this through a novel technical framework that combines: (i) a simple point-and-click interface merging grid-based colour selection with automatic instance segmentation for precise spatial control, (ii) bidirectional colour propagation that leverages inherent video motion patterns, and (iii) motion-aware blending that ensures smooth transitions even with complex object movements. Through extensive evaluation on diverse scenarios, we demonstrate that our approach matches or exceeds state-of-the-art methods while eliminating the need for training or specialized hardware, making professional-quality video colour editing accessible to everyone.
Authors: Lishuai Gao, Yujie Zhong, Yingsen Zeng, Haoxian Tan, Dengjie Li, Zheng Zhao
Abstract: Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into video-LLMs (after being trained on video data). To better adapt image-LLMs for processing videos, we introduce two design principles: linear transformation to preserve the original visual-language alignment and representative information condensation from redundant video content. Guided by these principles, we propose a plug-and-play Linear Video Tokenizer(LinVT), which enables existing image-LLMs to understand videos. We benchmark LinVT with six recent visual LLMs: Aquila, Blip-3, InternVL2, Mipha, Molmo and Qwen2-VL, showcasing the high compatibility of LinVT. LinVT-based LLMs achieve state-of-the-art performance across various video benchmarks, illustrating the effectiveness of LinVT in multi-modal video understanding.
Authors: Yohann Perron, Vladyslav Sydorov, Adam P. Wijker, Damian Evans, Christophe Pottier, Loic Landrieu
Abstract: Airborne Laser Scanning (ALS) technology has transformed modern archaeology by unveiling hidden landscapes beneath dense vegetation. However, the lack of expert-annotated, open-access resources has hindered the analysis of ALS data using advanced deep learning techniques. We address this limitation with Archaeoscape (available at https://archaeoscape.ai), a novel large-scale archaeological ALS dataset spanning 888 km$^2$ in Cambodia with 31,141 annotated archaeological features from the Angkorian period. Archaeoscape is over four times larger than comparable datasets, and the first ALS archaeology resource with open-access data, annotations, and models. We benchmark several recent segmentation models to demonstrate the benefits of modern vision techniques for this problem and highlight the unique challenges of discovering subtle human-made structures under dense jungle canopies. By making Archaeoscape available in open access, we hope to bridge the gap between traditional archaeology and modern computer vision methods.
Authors: Xiaohui Chen, Satya Narayan Shukla, Mahmoud Azab, Aashu Singh, Qifan Wang, David Yang, ShengYun Peng, Hanchao Yu, Shen Yan, Xuewen Zhang, Baosheng He
Abstract: How well can Multimodal Large Language Models (MLLMs) understand composite images? Composite images (CIs) are synthetic visuals created by merging multiple visual elements, such as charts, posters, or screenshots, rather than being captured directly by a camera. While CIs are prevalent in real-world applications, recent MLLM developments have primarily focused on interpreting natural images (NIs). Our research reveals that current MLLMs face significant challenges in accurately understanding CIs, often struggling to extract information or perform complex reasoning based on these images. We find that existing training data for CIs are mostly formatted for question-answer tasks (e.g., in datasets like ChartQA and ScienceQA), while high-quality image-caption datasets, critical for robust vision-language alignment, are only available for NIs. To bridge this gap, we introduce Composite Captions (CompCap), a flexible framework that leverages Large Language Models (LLMs) and automation tools to synthesize CIs with accurate and detailed captions. Using CompCap, we curate CompCap-118K, a dataset containing 118K image-caption pairs across six CI types. We validate the effectiveness of CompCap-118K by supervised fine-tuning MLLMs of three sizes: xGen-MM-inst.-4B and LLaVA-NeXT-Vicuna-7B/13B. Empirical results show that CompCap-118K significantly enhances MLLMs' understanding of CIs, yielding average gains of 1.7%, 2.0%, and 2.9% across eleven benchmarks, respectively.
Authors: Fnu Neha, Deepshikha Bhati, Deepak Kumar Shukla, Md Amiruzzaman
Abstract: Object detection is a fundamental task in computer vision and image understanding, with the goal of identifying and localizing objects of interest within an image while assigning them corresponding class labels. Traditional methods, which relied on handcrafted features and shallow models, struggled with complex visual data and showed limited performance. These methods combined low-level features with contextual information and lacked the ability to capture high-level semantics. Deep learning, especially Convolutional Neural Networks (CNNs), addressed these limitations by automatically learning rich, hierarchical features directly from data. These features include both semantic and high-level representations essential for accurate object detection. This paper reviews object detection frameworks, starting with classical computer vision methods. We categorize object detection approaches into two groups: (1) classical computer vision techniques and (2) CNN-based detectors. We compare major CNN models, discussing their strengths and limitations. In conclusion, this review highlights the significant advancements in object detection through deep learning and identifies key areas for further research to improve performance.
Authors: Xiangyu Han, Zhen Jia, Boyi Li, Yan Wang, Boris Ivanovic, Yurong You, Lingjie Liu, Yue Wang, Marco Pavone, Chen Feng, Yiming Li
Abstract: Photorealistic simulators are essential for the training and evaluation of vision-centric autonomous vehicles (AVs). At their core is Novel View Synthesis (NVS), a crucial capability that generates diverse unseen viewpoints to accommodate the broad and continuous pose distribution of AVs. Recent advances in radiance fields, such as 3D Gaussian Splatting, achieve photorealistic rendering at real-time speeds and have been widely used in modeling large-scale driving scenes. However, their performance is commonly evaluated using an interpolated setup with highly correlated training and test views. In contrast, extrapolation, where test views largely deviate from training views, remains underexplored, limiting progress in generalizable simulation technology. To address this gap, we leverage publicly available AV datasets with multiple traversals, multiple vehicles, and multiple cameras to build the first Extrapolated Urban View Synthesis (EUVS) benchmark. Meanwhile, we conduct quantitative and qualitative evaluations of state-of-the-art Gaussian Splatting methods across different difficulty levels. Our results show that Gaussian Splatting is prone to overfitting to training views. Besides, incorporating diffusion priors and improving geometry cannot fundamentally improve NVS under large view changes, highlighting the need for more robust approaches and large-scale training. We have released our data to help advance self-driving and urban robotics simulation technology.
Authors: Ziyi Wu, Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov, Yuwei Fang, Varnith Chordia, Igor Gilitschenski, Sergey Tulyakov
Abstract: Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with generating multiple events described using a single prompt, such methods often ignore some of the events or fail to arrange them in the correct order. To address this limitation, we present MinT, a multi-event video generator with temporal control. Our key insight is to bind each event to a specific period in the generated video, which allows the model to focus on one event at a time. To enable time-aware interactions between event captions and video tokens, we design a time-based positional encoding method, dubbed ReRoPE. This encoding helps to guide the cross-attention operation. By fine-tuning a pre-trained video diffusion transformer on temporally grounded data, our approach produces coherent videos with smoothly connected events. For the first time in the literature, our model offers control over the timing of events in generated videos. Extensive experiments demonstrate that MinT outperforms existing open-source models by a large margin.
Authors: Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, Lixin Gu, Xuehui Wang, Qingyun Li, Yimin Ren, Zixuan Chen, Jiapeng Luo, Jiahao Wang, Tan Jiang, Bo Wang, Conghui He, Botian Shi, Xingcheng Zhang, Han Lv, Yi Wang, Wenqi Shao, Pei Chu, Zhongying Tu, Tong He, Zhiyong Wu, Huipeng Deng, Jiaye Ge, Kai Chen, Min Dou, Lewei Lu, Xizhou Zhu, Tong Lu, Dahua Lin, Yu Qiao, Jifeng Dai, Wenhai Wang
Abstract: We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. In this work, we delve into the relationship between model scaling and performance, systematically exploring the performance trends in vision encoders, language models, dataset sizes, and test-time configurations. Through extensive evaluations on a wide range of benchmarks, including multi-discipline reasoning, document understanding, multi-image / video understanding, real-world comprehension, multimodal hallucination detection, visual grounding, multilingual capabilities, and pure language processing, InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. Notably, our model is the first open-source MLLMs to surpass 70% on the MMMU benchmark, achieving a 3.7-point improvement through Chain-of-Thought (CoT) reasoning and showcasing strong potential for test-time scaling. We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems. HuggingFace demo see https://huggingface.co/spaces/OpenGVLab/InternVL
Authors: Jiahua Dong, Tong Wu, Rui Qian, Jiaqi Wang
Abstract: The 3D contrastive learning paradigm has demonstrated remarkable performance in downstream tasks through pretraining on point cloud data. Recent advances involve additional 2D image priors associated with 3D point clouds for further improvement. Nonetheless, these existing frameworks are constrained by the restricted range of available point cloud datasets, primarily due to the high costs of obtaining point cloud data. To this end, we propose SimC3D, a simple but effective 3D contrastive learning framework, for the first time, pretraining 3D backbones from pure RGB image data. SimC3D performs contrastive 3D pretraining with three appealing properties. (1) Pure image data: SimC3D simplifies the dependency of costly 3D point clouds and pretrains 3D backbones using solely RBG images. By employing depth estimation and suitable data processing, the monocular synthesized point cloud shows great potential for 3D pretraining. (2) Simple framework: Traditional multi-modal frameworks facilitate 3D pretraining with 2D priors by utilizing an additional 2D backbone, thereby increasing computational expense. In this paper, we empirically demonstrate that the primary benefit of the 2D modality stems from the incorporation of locality information. Inspired by this insightful observation, SimC3D directly employs 2D positional embeddings as a stronger contrastive objective, eliminating the necessity for 2D backbones and leading to considerable performance improvements. (3) Strong performance: SimC3D outperforms previous approaches that leverage ground-truth point cloud data for pretraining in various downstream tasks. Furthermore, the performance of SimC3D can be further enhanced by combining multiple image datasets, showcasing its significant potential for scalability. The code will be available at https://github.com/Dongjiahua/SimC3D.
Authors: Tuna Han Salih Meral, Hidir Yesiltepe, Connor Dunlop, Pinar Yanardag
Abstract: Text-to-video models have demonstrated impressive capabilities in producing diverse and captivating video content, showcasing a notable advancement in generative AI. However, these models generally lack fine-grained control over motion patterns, limiting their practical applicability. We introduce MotionFlow, a novel framework designed for motion transfer in video diffusion models. Our method utilizes cross-attention maps to accurately capture and manipulate spatial and temporal dynamics, enabling seamless motion transfers across various contexts. Our approach does not require training and works on test-time by leveraging the inherent capabilities of pre-trained video diffusion models. In contrast to traditional approaches, which struggle with comprehensive scene changes while maintaining consistent motion, MotionFlow successfully handles such complex transformations through its attention-based mechanism. Our qualitative and quantitative experiments demonstrate that MotionFlow significantly outperforms existing models in both fidelity and versatility even during drastic scene alterations.
Authors: Hyesu Lim, Jinho Choi, Jaegul Choo, Steffen Schneider
Abstract: Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new Sparse Autoencoder (SAE) for the CLIP vision transformer, named PatchSAE, to extract interpretable concepts at granular levels (e.g. shape, color, or semantics of an object) and their patch-wise spatial attributions. We explore how these concepts influence the model output in downstream image classification tasks and investigate how recent state-of-the-art prompt-based adaptation techniques change the association of model inputs to these concepts. While activations of concepts slightly change between adapted and non-adapted models, we find that the majority of gains on common adaptation tasks can be explained with the existing concepts already present in the non-adapted foundation model. This work provides a concrete framework to train and use SAEs for Vision Transformers and provides insights into explaining adaptation mechanisms.
Authors: Hee Jae Kim, Kathakoli Sengupta, Masaki Kuribayashi, Hernisa Kacorri, Eshed Ohn-Bar
Abstract: People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection, blind individuals may have different patterns of movement, such as veering more from a straight path or using touch-based exploration around curbs and obstacles. These behaviors may appear less predictable to motion models embedded in technologies such as autonomous vehicles. Yet, the ability of 3D motion models to capture such behavior has not been previously studied, as existing datasets for 3D human motion currently lack diversity and are biased toward people who are sighted. In this work, we introduce BlindWays, the first multimodal motion benchmark for pedestrians who are blind. We collect 3D motion data using wearable sensors with 11 blind participants navigating eight different routes in a real-world urban setting. Additionally, we provide rich textual descriptions that capture the distinctive movement characteristics of blind pedestrians and their interactions with both the navigation aid (e.g., a white cane or a guide dog) and the environment. We benchmark state-of-the-art 3D human prediction models, finding poor performance with off-the-shelf and pre-training-based methods for our novel task. To contribute toward safer and more reliable systems that can seamlessly reason over diverse human movements in their environments, our text-and-motion benchmark is available at https://blindways.github.io.
Authors: Chen Geng, Yunzhi Zhang, Shangzhe Wu, Jiajun Wu
Abstract: We study the problem of generating temporal object intrinsics -- temporally evolving sequences of object geometry, reflectance, and texture, such as a blooming rose -- from pre-trained 2D foundation models. Unlike conventional 3D modeling and animation techniques that require extensive manual effort and expertise, we introduce a method that generates such assets with signals distilled from pre-trained 2D diffusion models. To ensure the temporal consistency of object intrinsics, we propose Neural Templates for temporal-state-guided distillation, derived automatically from image features from self-supervised learning. Our method can generate high-quality temporal object intrinsics for several natural phenomena and enable the sampling and controllable rendering of these dynamic objects from any viewpoint, under any environmental lighting conditions, at any time of their lifespan. Project website: https://chen-geng.com/rose4d
Authors: Susung Hong, Johanna Karras, Ricardo Martin-Brualla, Ira Kemelmacher-Shlizerman
Abstract: The fields of 3D reconstruction and text-based 3D editing have advanced significantly with the evolution of text-based diffusion models. While existing 3D editing methods excel at modifying color, texture, and style, they struggle with extensive geometric or appearance changes, thus limiting their applications. We propose Perturb-and-Revise, which makes possible a variety of NeRF editing. First, we perturb the NeRF parameters with random initializations to create a versatile initialization. We automatically determine the perturbation magnitude through analysis of the local loss landscape. Then, we revise the edited NeRF via generative trajectories. Combined with the generative process, we impose identity-preserving gradients to refine the edited NeRF. Extensive experiments demonstrate that Perturb-and-Revise facilitates flexible, effective, and consistent editing of color, appearance, and geometry in 3D. For 360{\deg} results, please visit our project page: https://susunghong.github.io/Perturb-and-Revise.
Authors: Lening Wang, Wenzhao Zheng, Dalong Du, Yunpeng Zhang, Yilong Ren, Han Jiang, Zhiyong Cui, Haiyang Yu, Jie Zhou, Jiwen Lu, Shanghang Zhang
Abstract: 4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant challenges remain in view transformation and spatial-temporal dynamic modeling. To address these limitations, we propose a Spatial-Temporal simulAtion for drivinG (Stag-1) model to reconstruct real-world scenes and design a controllable generative network to achieve 4D simulation. Stag-1 constructs continuous 4D point cloud scenes using surround-view data from autonomous vehicles. It decouples spatial-temporal relationships and produces coherent keyframe videos. Additionally, Stag-1 leverages video generation models to obtain photo-realistic and controllable 4D driving simulation videos from any perspective. To expand the range of view generation, we train vehicle motion videos based on decomposed camera poses, enhancing modeling capabilities for distant scenes. Furthermore, we reconstruct vehicle camera trajectories to integrate 3D points across consecutive views, enabling comprehensive scene understanding along the temporal dimension. Following extensive multi-level scene training, Stag-1 can simulate from any desired viewpoint and achieve a deep understanding of scene evolution under static spatial-temporal conditions. Compared to existing methods, our approach shows promising performance in multi-view scene consistency, background coherence, and accuracy, and contributes to the ongoing advancements in realistic autonomous driving simulation. Code: https://github.com/wzzheng/Stag.
Authors: Qi Zheng, Yibo Fan, Leilei Huang, Tianyu Zhu, Jiaming Liu, Zhijian Hao, Shuo Xing, Chia-Ju Chen, Xiongkuo Min, Alan C. Bovik, Zhengzhong Tu
Abstract: Video quality assessment (VQA) is an important processing task, aiming at predicting the quality of videos in a manner highly consistent with human judgments of perceived quality. Traditional VQA models based on natural image and/or video statistics, which are inspired both by models of projected images of the real world and by dual models of the human visual system, deliver only limited prediction performances on real-world user-generated content (UGC), as exemplified in recent large-scale VQA databases containing large numbers of diverse video contents crawled from the web. Fortunately, recent advances in deep neural networks and Large Multimodality Models (LMMs) have enabled significant progress in solving this problem, yielding better results than prior handcrafted models. Numerous deep learning-based VQA models have been developed, with progress in this direction driven by the creation of content-diverse, large-scale human-labeled databases that supply ground truth psychometric video quality data. Here, we present a comprehensive survey of recent progress in the development of VQA algorithms and the benchmarking studies and databases that make them possible. We also analyze open research directions on study design and VQA algorithm architectures.
Authors: Byeonghyeon Lee, Youbin Kim, Yongjae Jo, Hyunsu Kim, Hyemi Park, Yangkyu Kim, Debabrata Mandal, Praneeth Chakravarthula, Inki Kim, Eunbyung Park
Abstract: Metalens is an emerging optical system with an irreplaceable merit in that it can be manufactured in ultra-thin and compact sizes, which shows great promise of various applications such as medical imaging and augmented/virtual reality (AR/VR). Despite its advantage in miniaturization, its practicality is constrained by severe aberrations and distortions, which significantly degrade the image quality. Several previous arts have attempted to address different types of aberrations, yet most of them are mainly designed for the traditional bulky lens and not convincing enough to remedy harsh aberrations of the metalens. While there have existed aberration correction methods specifically for metalens, they still fall short of restoration quality. In this work, we propose MetaFormer, an aberration correction framework for metalens-captured images, harnessing Vision Transformers (ViT) that has shown remarkable restoration performance in diverse image restoration tasks. Specifically, we devise a Multiple Adaptive Filters Guidance (MAFG), where multiple Wiener filters enrich the degraded input images with various noise-detail balances, enhancing output restoration quality. In addition, we introduce a Spatial and Transposed self-Attention Fusion (STAF) module, which aggregates features from spatial self-attention and transposed self-attention modules to further ameliorate aberration correction. We conduct extensive experiments, including correcting aberrated images and videos, and clean 3D reconstruction from the degraded images. The proposed method outperforms the previous arts by a significant margin. We further fabricate a metalens and verify the practicality of MetaFormer by restoring the images captured with the manufactured metalens in the wild. Code and pre-trained models are available at https://benhenryl.github.io/MetaFormer
Authors: Putri A. van der Linden, Alejandro Garc\'ia-Castellanos, Sharvaree Vadgama, Thijs P. Kuipers, Erik J. Bekkers
Abstract: Group equivariance has emerged as a valuable inductive bias in deep learning, enhancing generalization, data efficiency, and robustness. Classically, group equivariant methods require the groups of interest to be known beforehand, which may not be realistic for real-world data. Additionally, baking in fixed group equivariance may impose overly restrictive constraints on model architecture. This highlights the need for methods that can dynamically discover and apply symmetries as soft constraints. For neural network architectures, equivariance is commonly achieved through group transformations of a canonical weight tensor, resulting in weight sharing over a given group $G$. In this work, we propose to learn such a weight-sharing scheme by defining a collection of learnable doubly stochastic matrices that act as soft permutation matrices on canonical weight tensors, which can take regular group representations as a special case. This yields learnable kernel transformations that are jointly optimized with downstream tasks. We show that when the dataset exhibits strong symmetries, the permutation matrices will converge to regular group representations and our weight-sharing networks effectively become regular group convolutions. Additionally, the flexibility of the method enables it to effectively pick up on partial symmetries.
Authors: Marc Vornehm, Chong Chen, Muhammad Ahmad Sultan, Syed Murtaza Arshad, Yuchi Han, Florian Knoll, Rizwan Ahmad
Abstract: Cardiovascular magnetic resonance imaging is a powerful diagnostic tool for assessing cardiac structure and function. Traditional breath-held imaging protocols, however, pose challenges for patients with arrhythmias or limited breath-holding capacity. We introduce Motion-Guided Deep Image prior (M-DIP), a novel unsupervised reconstruction framework for accelerated real-time cardiac MRI. M-DIP employs a spatial dictionary to synthesize a time-dependent template image, which is further refined using time-dependent deformation fields that model cardiac and respiratory motion. Unlike prior DIP-based methods, M-DIP simultaneously captures physiological motion and frame-to-frame content variations, making it applicable to a wide range of dynamic applications. We validate M-DIP using simulated MRXCAT cine phantom data as well as free-breathing real-time cine and single-shot late gadolinium enhancement data from clinical patients. Comparative analyses against state-of-the-art supervised and unsupervised approaches demonstrate M-DIP's performance and versatility. M-DIP achieved better image quality metrics on phantom data, as well as higher reader scores for in-vivo patient data.
Authors: Rui Zhou, Yanxia Zhang, Chenyang Yuan, Frank Permenter, Nikos Arechiga, Matt Klenk, Faez Ahmed
Abstract: This paper introduces a generative model designed for multimodal control over text-to-image foundation generative AI models such as Stable Diffusion, specifically tailored for engineering design synthesis. Our model proposes parametric, image, and text control modalities to enhance design precision and diversity. Firstly, it handles both partial and complete parametric inputs using a diffusion model that acts as a design autocomplete co-pilot, coupled with a parametric encoder to process the information. Secondly, the model utilizes assembly graphs to systematically assemble input component images, which are then processed through a component encoder to capture essential visual data. Thirdly, textual descriptions are integrated via CLIP encoding, ensuring a comprehensive interpretation of design intent. These diverse inputs are synthesized through a multimodal fusion technique, creating a joint embedding that acts as the input to a module inspired by ControlNet. This integration allows the model to apply robust multimodal control to foundation models, facilitating the generation of complex and precise engineering designs. This approach broadens the capabilities of AI-driven design tools and demonstrates significant advancements in precise control based on diverse data modalities for enhanced design generation.
Authors: Inju Ha, Donghun Ryou, Seonguk Seo, Bohyung Han
Abstract: Deep learning-based image denoising techniques often struggle with poor generalization performance to out-of-distribution real-world noise. To tackle this challenge, we propose a novel noise translation framework that performs denoising on an image with translated noise rather than directly denoising an original noisy image. Specifically, our approach translates complex, unknown real-world noise into Gaussian noise, which is spatially uncorrelated and independent of image content, through a noise translation network. The translated noisy images are then processed by an image denoising network pretrained to effectively remove Gaussian noise, enabling robust and consistent denoising performance. We also design well-motivated loss functions and architectures for the noise translation network by leveraging the mathematical properties of Gaussian noise. Experimental results demonstrate that the proposed method substantially improves robustness and generalizability, outperforming state-of-the-art methods across diverse benchmarks. Visualized denoising results and the source code are available on our project page.
Authors: Anika Shrivastava, Renu Rameshan, Samar Agnihotri
Abstract: Understanding the latent spaces learned by deep learning models is crucial in exploring how they represent and generate complex data. Autoencoders (AEs) have played a key role in the area of representation learning, with numerous regularization techniques and training principles developed not only to enhance their ability to learn compact and robust representations, but also to reveal how different architectures influence the structure and smoothness of the lower-dimensional non-linear manifold. We strive to characterize the structure of the latent spaces learned by different autoencoders including convolutional autoencoders (CAEs), denoising autoencoders (DAEs), and variational autoencoders (VAEs) and how they change with the perturbations in the input. By characterizing the matrix manifolds corresponding to the latent spaces, we provide an explanation for the well-known observation that the latent spaces of CAE and DAE form non-smooth manifolds, while that of VAE forms a smooth manifold. We also map the points of the matrix manifold to a Hilbert space using distance preserving transforms and provide an alternate view in terms of the subspaces generated in the Hilbert space as a function of the distortion in the input. The results show that the latent manifolds of CAE and DAE are stratified with each stratum being a smooth product manifold, while the manifold of VAE is a smooth product manifold of two symmetric positive definite matrices and a symmetric positive semi-definite matrix.
Authors: Shadab Ahamed, Eldad Haber
Abstract: Inverse problems, which involve estimating parameters from incomplete or noisy observations, arise in various fields such as medical imaging, geophysics, and signal processing. These problems are often ill-posed, requiring regularization techniques to stabilize the solution. In this work, we employ $\textit{Stochastic Interpolation}$ (SI), a generative framework that integrates both deterministic and stochastic processes to map a simple reference distribution, such as a Gaussian, to the target distribution. Our method $\textbf{DAWN-SI}$: $\textbf{D}$ata-$\textbf{AW}$are and $\textbf{N}$oise-informed $\textbf{S}$tochastic $\textbf{I}$nterpolation incorporates data and noise embedding, allowing the model to access representations about the measured data explicitly and also account for noise in the observations, making it particularly robust in scenarios where data is noisy or incomplete. By learning a time-dependent velocity field, SI not only provides accurate solutions but also enables uncertainty quantification by generating multiple plausible outcomes. Unlike pre-trained diffusion models, which may struggle in highly ill-posed settings, our approach is trained specifically for each inverse problem and adapts to varying noise levels. We validate the effectiveness and robustness of our method through extensive numerical experiments on tasks such as image deblurring and tomography.
Authors: Songcheng Du, Yang Zou, Zixu Wang, Xingyuan Li, Ying Li, Qiang Shen
Abstract: Hyperspectral Image Fusion (HIF) aims to fuse low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) to reconstruct high spatial and high spectral resolution images. Current methods typically apply direct fusion from the two modalities without valid supervision, failing to fully perceive the deep modality-complementary information and hence, resulting in a superficial understanding of inter-modality connections. To bridge this gap, we propose a simple and effective solution for unsupervised HIF with an assumption that modality decoupling is essential for HIF. We introduce the modality clustering loss that ensures clear guidance of the modality, decoupling towards modality-shared features while steering clear of modality-complementary ones. Also, we propose an end-to-end Modality-Decoupled Spatial-Spectral Fusion (MossFuse) framework that decouples shared and complementary information across modalities and aggregates a concise representation of the LR-HSI and HR-MSI to reduce the modality redundancy. Systematic experiments over multiple datasets demonstrate that our simple and effective approach consistently outperforms the existing HIF methods while requiring considerably fewer parameters with reduced inference time.
Authors: Zeynel A. Samak, Philip Clatworthy, Majid Mirmehdi
Abstract: Stroke is a major global health problem that causes mortality and morbidity. Predicting the outcomes of stroke intervention can facilitate clinical decision-making and improve patient care. Engaging and developing deep learning techniques can help to analyse large and diverse medical data, including brain scans, medical reports and other sensor information, such as EEG, ECG, EMG and so on. Despite the common data standardisation challenge within medical image analysis domain, the future of deep learning in stroke outcome prediction lie in using multimodal information, including final infarct data, to achieve better prediction of long-term functional outcomes. This article provides a broad review of recent advances and applications of deep learning in the prediction of stroke outcomes, including (i) the data and models used, (ii) the prediction tasks and measures of success, (iii) the current challenges and limitations, and (iv) future directions and potential benefits. This comprehensive review aims to provide researchers, clinicians, and policy makers with an up-to-date understanding of this rapidly evolving and promising field.
Authors: Ran Tian, Yilin Wu, Chenfeng Xu, Masayoshi Tomizuka, Jitendra Malik, Andrea Bajcsy
Abstract: Visuomotor robot policies, increasingly pre-trained on large-scale datasets, promise significant advancements across robotics domains. However, aligning these policies with end-user preferences remains a challenge, particularly when the preferences are hard to specify. While reinforcement learning from human feedback (RLHF) has become the predominant mechanism for alignment in non-embodied domains like large language models, it has not seen the same success in aligning visuomotor policies due to the prohibitive amount of human feedback required to learn visual reward functions. To address this limitation, we propose Representation-Aligned Preference-based Learning (RAPL), an observation-only method for learning visual rewards from significantly less human preference feedback. Unlike traditional RLHF, RAPL focuses human feedback on fine-tuning pre-trained vision encoders to align with the end-user's visual representation and then constructs a dense visual reward via feature matching in this aligned representation space. We first validate RAPL through simulation experiments in the X-Magical benchmark and Franka Panda robotic manipulation, demonstrating that it can learn rewards aligned with human preferences, more efficiently uses preference data, and generalizes across robot embodiments. Finally, our hardware experiments align pre-trained Diffusion Policies for three object manipulation tasks. We find that RAPL can fine-tune these policies with 5x less real human preference data, taking the first step towards minimizing human feedback while maximizing visuomotor robot policy alignment.
Authors: Eric L. Wisotzky, Alexander Schill, Anna Hilsmann, Peter Eisert, Michael Knoke
Abstract: In head and neck surgery, continuous intraoperative tissue differentiation is of great importance to avoid injury to sensitive structures such as nerves and vessels. Hyperspectral imaging (HSI) with neural network analysis could support the surgeon in tissue differentiation. A 3D Convolutional Neural Network with hyperspectral data in the range of $400-1000$ nm is used in this work. The acquisition system consisted of two multispectral snapshot cameras creating a stereo-HSI-system. For the analysis, 27 images with annotations of glandular tissue, nerve, muscle, skin and vein in 18 patients undergoing parotidectomy are included. Three patients are removed for evaluation following the leave-one-subject-out principle. The remaining images are used for training, with the data randomly divided into a training group and a validation group. In the validation, an overall accuracy of $98.7\%$ is achieved, indicating robust training. In the evaluation on the excluded patients, an overall accuracy of $83.4\%$ has been achieved showing good detection and identification abilities. The results clearly show that it is possible to achieve robust intraoperative tissue differentiation using hyperspectral imaging. Especially the high sensitivity in parotid or nerve tissue is of clinical importance. It is interesting to note that vein was often confused with muscle. This requires further analysis and shows that a very good and comprehensive data basis is essential. This is a major challenge, especially in surgery.
Authors: Niloufar Delfan, Pardis Ketabi Moghadam, Mohammad Khoshnevisan, Mehdi Hosseini Chagahi, Behzad Hatami, Melika Asgharzadeh, Mohammadreza Zali, Behzad Moshiri, Amin Momeni Moghaddam, Mohammad Amin Khalafi, Khosrow Dehnad
Abstract: Non-alcoholic fatty liver disease (NAFLD) is one of the most widespread liver disorders on a global scale, posing a significant threat of progressing to more severe conditions like nonalcoholic steatohepatitis (NASH), liver fibrosis, cirrhosis, and hepatocellular carcinoma. Diagnosing and staging NAFLD presents challenges due to its non-specific symptoms and the invasive nature of liver biopsies. Our research introduces a novel artificial intelligence cascade model employing ensemble learning and feature fusion techniques. We developed a non-invasive, robust, and reliable diagnostic artificial intelligence tool that utilizes anthropometric and laboratory parameters, facilitating early detection and intervention in NAFLD progression. Our novel artificial intelligence achieved an 86% accuracy rate for the NASH steatosis staging task (non-NASH, steatosis grade 1, steatosis grade 2, and steatosis grade 3) and an impressive 96% AUC-ROC for distinguishing between NASH (steatosis grade 1, grade 2, and grade3) and non-NASH cases, outperforming current state-of-the-art models. This notable improvement in diagnostic performance underscores the potential application of artificial intelligence in the early diagnosis and treatment of NAFLD, leading to better patient outcomes and a reduced healthcare burden associated with advanced liver disease.
Authors: Mahek Kantharia, Neeraj Badal, Zankhana Shah
Abstract: Pansharpening is a crucial task in remote sensing, enabling the generation of high-resolution multispectral images by fusing low-resolution multispectral data with high-resolution panchromatic images. This paper provides a comprehensive analysis of traditional and deep learning-based pansharpening methods. While state-of-the-art deep learning methods have significantly improved image quality, issues like spectral distortions persist. To address this, we propose enhancements to the PSGAN framework by introducing novel regularization techniques for the generator loss function. Experimental results on images from the Worldview-3 dataset demonstrate that the proposed modifications improve spectral fidelity and achieve superior performance across multiple quantitative metrics while delivering visually superior results.
Authors: Yixin Gao, Xin Li, Xiaohan Pan, Runsen Feng, Zongyu Guo, Yiting Lu, Yulin Ren, Zhibo Chen
Abstract: We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneously through excavating cross-modality generative priors. Unlike most existing works that need to design and optimize image codecs from scratch, our UniMIC introduces the visual codec repository, which incorporates amounts of representative image codecs and directly uses them as the basic codecs for various practical applications. Moreover, we propose multi-grained textual coding, where variable-length content prompt and compression prompt are designed and encoded to assist the perceptual reconstruction through the multi-modality conditional generation. In particular, a universal perception compensator is proposed to improve the perception quality of decoded images from all basic codecs at the decoder side by reusing text-assisted diffusion priors from stable diffusion. With the cooperation of the above three strategies, our UniMIC achieves a significant improvement of RDP optimization for different compression codecs, e.g., traditional and learnable codecs, and different compression costs, e.g., ultra-low bitrates. The code will be available in https://github.com/Amygyx/UniMIC .
Authors: Mohammad Mohaiminul Islam, Coen de Vente, Bart Liefers, Caroline Klaver, Erik J Bekkers, Clara I. S\'anchez
Abstract: In this paper, we present a new approach for uncertainty-aware retinal layer segmentation in Optical Coherence Tomography (OCT) scans using probabilistic signed distance functions (SDF). Traditional pixel-wise and regression-based methods primarily encounter difficulties in precise segmentation and lack of geometrical grounding respectively. To address these shortcomings, our methodology refines the segmentation by predicting a signed distance function (SDF) that effectively parameterizes the retinal layer shape via level set. We further enhance the framework by integrating probabilistic modeling, applying Gaussian distributions to encapsulate the uncertainty in the shape parameterization. This ensures a robust representation of the retinal layer morphology even in the presence of ambiguous input, imaging noise, and unreliable segmentations. Both quantitative and qualitative evaluations demonstrate superior performance when compared to other methods. Additionally, we conducted experiments on artificially distorted datasets with various noise types-shadowing, blinking, speckle, and motion-common in OCT scans to showcase the effectiveness of our uncertainty estimation. Our findings demonstrate the possibility to obtain reliable segmentation of retinal layers, as well as an initial step towards the characterization of layer integrity, a key biomarker for disease progression. Our code is available at \url{https://github.com/niazoys/RLS_PSDF}.
Authors: Blessing Austin-Gabriel, Cristian Noriega Monsalve, Aparna S. Varde
Abstract: In this research, we propose a hybrid model for power plant detection to assist energy estimation applications, by pipelining GIS (Geographical Information Systems) having Remote Sensing capabilities with CNN (Convolutional Neural Networks) and ViT (Vision Transformers). Our proposed approach enables real-time analysis with multiple data types on a common map via the GIS, entails feature-extraction abilities due to the CNN, and captures long-range dependencies through the ViT. This hybrid approach is found to enhance classification, thus helping in the monitoring and operational management of power plants; hence assisting energy estimation and sustainable energy planning in the future. It exemplifies adequate deployment of machine learning methods in conjunction with domain-specific approaches to enhance performance.
Authors: ZeinabSadat Taghavi, Hossein Mirzaei
Abstract: There have been several efforts in backdoor attacks, but these have primarily focused on the closed-set performance of classifiers (i.e., classification). This has left a gap in addressing the threat to classifiers' open-set performance, referred to as outlier detection in the literature. Reliable outlier detection is crucial for deploying classifiers in critical real-world applications such as autonomous driving and medical image analysis. First, we show that existing backdoor attacks fall short in affecting the open-set performance of classifiers, as they have been specifically designed to confuse intra-closed-set decision boundaries. In contrast, an effective backdoor attack for outlier detection needs to confuse the decision boundary between the closed and open sets. Motivated by this, in this study, we propose BATOD, a novel Backdoor Attack targeting the Outlier Detection task. Specifically, we design two categories of triggers to shift inlier samples to outliers and vice versa. We evaluate BATOD using various real-world datasets and demonstrate its superior ability to degrade the open-set performance of classifiers compared to previous attacks, both before and after applying defenses.
Authors: Tom Bachard, Thomas Maugey
Abstract: Semantic compression, a compression scheme where the distortion metric, typically MSE, is replaced with semantic fidelity metrics, tends to become more and more popular. Most recent semantic compression schemes rely on the foundation model CLIP. In this work, we extend such a scheme to image collection compression, where inter-item redundancy is taken into account during the coding phase. For that purpose, we first show that CLIP's latent space allows for easy semantic additions and subtractions. From this property, we define a dictionary-based multi-item codec that outperforms state-of-the-art generative codec in terms of compression rate, around $10^{-5}$ BPP per image, while not sacrificing semantic fidelity. We also show that the learned dictionary is of a semantic nature and works as a semantic projector for the semantic content of images.
Authors: Kaizhen Sun, Jinghang Li, Kuan Dai, Bangyan Liao, Wei Xiong, Yi Zhou
Abstract: Time-to-Collision (TTC) estimation lies in the core of the forward collision warning (FCW) functionality, which is key to all Automatic Emergency Braking (AEB) systems. Although the success of solutions using frame-based cameras (e.g., Mobileye's solutions) has been witnessed in normal situations, some extreme cases, such as the sudden variation in the relative speed of leading vehicles and the sudden appearance of pedestrians, still pose significant risks that cannot be handled. This is due to the inherent imaging principles of frame-based cameras, where the time interval between adjacent exposures introduces considerable system latency to AEB. Event cameras, as a novel bio-inspired sensor, offer ultra-high temporal resolution and can asynchronously report brightness changes at the microsecond level. To explore the potential of event cameras in the above-mentioned challenging cases, we propose EvTTC, which is, to the best of our knowledge, the first multi-sensor dataset focusing on TTC tasks under high-relative-speed scenarios. EvTTC consists of data collected using standard cameras and event cameras, covering various potential collision scenarios in daily driving and involving multiple collision objects. Additionally, LiDAR and GNSS/INS measurements are provided for the calculation of ground-truth TTC. Considering the high cost of testing TTC algorithms on full-scale mobile platforms, we also provide a small-scale TTC testbed for experimental validation and data augmentation. All the data and the design of the testbed are open sourced, and they can serve as a benchmark that will facilitate the development of vision-based TTC techniques.
Authors: Lara Blomenkamp, Ivanna Kramer, Sabine Bauer, Kevin Weirauch, Dietrich Paulus
Abstract: Patient-specific 3D spine models serve as a foundation for spinal treatment and surgery planning as well as analysis of loading conditions in biomechanical and biomedical research. Despite advancements in imaging technologies, the reconstruction of complete 3D spine models often faces challenges due to limitations in imaging modalities such as planar X-Ray and missing certain spinal structures, such as the spinal or transverse processes, in volumetric medical images and resulting segmentations. In this study, we present a novel accurate and time-efficient method to reconstruct complete 3D lumbar spine models from incomplete 3D vertebral bodies obtained from segmented magnetic resonance images (MRI). In our method, we use an affine transformation to align artificial vertebra models with patient-specific incomplete vertebrae. The transformation matrix is derived from vertebra landmarks, which are automatically detected on the vertebra endplates. The results of our evaluation demonstrate the high accuracy of the performed registration, achieving an average point-to-model distance of 1.95 mm. Additionally, in assessing the morphological properties of the vertebrae and intervertebral characteristics, our method demonstrated a mean absolute error (MAE) of 3.4{\deg} in the angles of functional spine units (FSUs), emphasizing its effectiveness in maintaining important spinal features throughout the transformation process of individual vertebrae. Our method achieves the registration of the entire lumbar spine, spanning segments L1 to L5, in just 0.14 seconds, showcasing its time-efficiency. Clinical relevance: the fast and accurate reconstruction of spinal models from incomplete input data such as segmentations provides a foundation for many applications in spine diagnostics, treatment planning, and the development of spinal healthcare solutions.
Authors: Haotian Zhao, Ruifeng Chen, Jing Yan, Juan Feng, Jun Xiang, Yang Chen, Dong Liang, Yinsheng Li
Abstract: To shorten the door-to-puncture time for better treating patients with acute ischemic stroke, it is highly desired to obtain quantitative cerebral perfusion images using C-arm cone-beam computed tomography (CBCT) equipped in the interventional suite. However, limited by the slow gantry rotation speed, the temporal resolution and temporal sampling density of typical C-arm CBCT are much poorer than those of multi-detector-row CT in the diagnostic imaging suite. The current quantitative perfusion imaging includes two cascaded steps: time-resolved image reconstruction and perfusion parametric estimation. For time-resolved image reconstruction, the technical challenge imposed by poor temporal resolution and poor sampling density causes inaccurate quantification of the temporal variation of cerebral artery and tissue attenuation values. For perfusion parametric estimation, it remains a technical challenge to appropriately design the handcrafted regularization for better solving the associated deconvolution problem. These two challenges together prevent obtaining quantitatively accurate perfusion images using C-arm CBCT. The purpose of this work is to simultaneously address these two challenges by combining the two cascaded steps into a single joint optimization problem and reconstructing quantitative perfusion images directly from the measured sinogram data. In the developed direct cerebral perfusion parametric image reconstruction technique, TRAINER in short, the quantitative perfusion images have been represented as a subject-specific conditional generative model trained under the constraint of the time-resolved CT forward model, perfusion convolutional model, and the subject's own measured sinogram data. Results shown in this paper demonstrated that using TRAINER, quantitative cerebral perfusion images can be accurately obtained using C-arm CBCT in the interventional suite.
Authors: Junyuan Zhang, Songhua Liu, Xinchao Wang
Abstract: One-shot Federated learning (FL) is a powerful technology facilitating collaborative training of machine learning models in a single round of communication. While its superiority lies in communication efficiency and privacy preservation compared to iterative FL, one-shot FL often compromises model performance. Prior research has primarily focused on employing data-free knowledge distillation to optimize data generators and ensemble models for better aggregating local knowledge into the server model. However, these methods typically struggle with data heterogeneity, where inconsistent local data distributions can cause teachers to provide misleading knowledge. Additionally, they may encounter scalability issues with complex datasets due to inherent two-step information loss: first, during local training (from data to model), and second, when transferring knowledge to the server model (from model to inversed data). In this paper, we propose FedSD2C, a novel and practical one-shot FL framework designed to address these challenges. FedSD2C introduces a distiller to synthesize informative distillates directly from local data to reduce information loss and proposes sharing synthetic distillates instead of inconsistent local models to tackle data heterogeneity. Our empirical results demonstrate that FedSD2C consistently outperforms other one-shot FL methods with more complex and real datasets, achieving up to 2.6 the performance of the best baseline. Code: https://github.com/Carkham/FedSD2C
Authors: Jinlin Wu, Xusheng Liang, Xuexue Bai, Zhen Chen
Abstract: Surgical interventions, particularly in neurology, represent complex and high-stakes scenarios that impose substantial cognitive burdens on surgical teams. Although deliberate education and practice can enhance cognitive capabilities, surgical training opportunities remain limited due to patient safety concerns. To address these cognitive challenges in surgical training and operation, we propose SurgBox, an agent-driven sandbox framework to systematically enhance the cognitive capabilities of surgeons in immersive surgical simulations. Specifically, our SurgBox leverages large language models (LLMs) with tailored Retrieval-Augmented Generation (RAG) to authentically replicate various surgical roles, enabling realistic training environments for deliberate practice. In particular, we devise Surgery Copilot, an AI-driven assistant to actively coordinate the surgical information stream and support clinical decision-making, thereby diminishing the cognitive workload of surgical teams during surgery. By incorporating a novel Long-Short Memory mechanism, our Surgery Copilot can effectively balance immediate procedural assistance with comprehensive surgical knowledge. Extensive experiments using real neurosurgical procedure records validate our SurgBox framework in both enhancing surgical cognitive capabilities and supporting clinical decision-making. By providing an integrated solution for training and operational support to address cognitive challenges, our SurgBox framework advances surgical education and practice, potentially transforming surgical outcomes and healthcare quality. The code is available at https://github.com/franciszchen/SurgBox.
Authors: Ayushman Singh, Sharad Prakash, Aniket Das, Nidhi Kushwaha
Abstract: This study presents an integrated deep learning model for automatic detection and classification of Gastrointestinal bleeding in the frames extracted from Wireless Capsule Endoscopy (WCE) videos. The dataset has been released as part of Auto-WCBleedGen Challenge Version V2 hosted by the MISAHUB team. Our model attained the highest performance among 75 teams that took part in this competition. It aims to efficiently utilizes CNN based model i.e. DenseNet and UNet to detect and segment bleeding and non-bleeding areas in the real-world complex dataset. The model achieves an impressive overall accuracy of 80% which would surely help a skilled doctor to carry out further diagnostics.
Authors: Jarvis Guo, Tuney Zheng, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Yizhi Li, Graham Neubig, Wenhu Chen, Xiang Yue
Abstract: Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained by existing instruction-tuning datasets, which were predominately repurposed from academic datasets such as VQA, AI2D, and ChartQA. These datasets target simplistic tasks, and only provide phrase-level answers without any intermediate rationales. To address these challenges, we introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales designed to elicit CoT reasoning. Using only open models, we create a dataset containing 12M instruction-response pairs to cover diverse, reasoning-intensive tasks with detailed and faithful rationales. Experiments demonstrate that training MLLMs on this dataset significantly improves reasoning capabilities, achieving state-of-the-art performance on benchmarks such as MathVerse (+8.1%), MMMU-Pro (+7%), and MuirBench (+13.3%). Additionally, the model demonstrates notable improvements of up to 4% on non-reasoning-based benchmarks. Ablation studies further highlight the importance of key components, such as rewriting and self-filtering, in the dataset construction process.
Authors: Qian Long, Zhi Li, Ran Gong, Ying Nian Wu, Demetri Terzopoulos, Xiaofeng Gao
Abstract: Collaboration is a cornerstone of society. In the real world, human teammates make use of multi-sensory data to tackle challenging tasks in ever-changing environments. It is essential for embodied agents collaborating in visually-rich environments replete with dynamic interactions to understand multi-modal observations and task specifications. To evaluate the performance of generalizable multi-modal collaborative agents, we present TeamCraft, a multi-modal multi-agent benchmark built on top of the open-world video game Minecraft. The benchmark features 55,000 task variants specified by multi-modal prompts, procedurally-generated expert demonstrations for imitation learning, and carefully designed protocols to evaluate model generalization capabilities. We also perform extensive analyses to better understand the limitations and strengths of existing approaches. Our results indicate that existing models continue to face significant challenges in generalizing to novel goals, scenes, and unseen numbers of agents. These findings underscore the need for further research in this area. The TeamCraft platform and dataset are publicly available at https://github.com/teamcraft-bench/teamcraft.
Authors: Junzhe Zhu, Yuanchen Ju, Junyi Zhang, Muhan Wang, Zhecheng Yuan, Kaizhe Hu, Huazhe Xu
Abstract: Dense 3D correspondence can enhance robotic manipulation by enabling the generalization of spatial, functional, and dynamic information from one object to an unseen counterpart. Compared to shape correspondence, semantic correspondence is more effective in generalizing across different object categories. To this end, we present DenseMatcher, a method capable of computing 3D correspondences between in-the-wild objects that share similar structures. DenseMatcher first computes vertex features by projecting multiview 2D features onto meshes and refining them with a 3D network, and subsequently finds dense correspondences with the obtained features using functional map. In addition, we craft the first 3D matching dataset that contains colored object meshes across diverse categories. In our experiments, we show that DenseMatcher significantly outperforms prior 3D matching baselines by 43.5%. We demonstrate the downstream effectiveness of DenseMatcher in (i) robotic manipulation, where it achieves cross-instance and cross-category generalization on long-horizon complex manipulation tasks from observing only one demo; (ii) zero-shot color mapping between digital assets, where appearance can be transferred between different objects with relatable geometry.
Authors: Zhao Zhang, Suiyi Zhao, Xiaojie Jin, Mingliang Xu, Yi Yang, Shuicheng Yan, Meng Wang
Abstract: Deep learning-based low-light image enhancement (LLIE) is a task of leveraging deep neural networks to enhance the image illumination while keeping the image content unchanged. From the perspective of training data, existing methods complete the LLIE task driven by one of the following three data types: paired data, unpaired data and zero-reference data. Each type of these data-driven methods has its own advantages, e.g., zero-reference data-based methods have very low requirements on training data and can meet the human needs in many scenarios. In this paper, we leverage pure Gaussian noise to complete the LLIE task, which further reduces the requirements for training data in LLIE tasks and can be used as another alternative in practical use. Specifically, we propose Noise SElf-Regression (NoiSER) without access to any task-related data, simply learns a convolutional neural network equipped with an instance-normalization layer by taking a random noise image, $\mathcal{N}(0,\sigma^2)$ for each pixel, as both input and output for each training pair, and then the low-light image is fed to the trained network for predicting the normal-light image. Technically, an intuitive explanation for its effectiveness is as follows: 1) the self-regression reconstructs the contrast between adjacent pixels of the input image, 2) the instance-normalization layer may naturally remediate the overall magnitude/lighting of the input image, and 3) the $\mathcal{N}(0,\sigma^2)$ assumption for each pixel enforces the output image to follow the well-known gray-world hypothesis when the image size is big enough. Compared to current state-of-the-art LLIE methods with access to different task-related data, NoiSER is highly competitive in enhancement quality, yet with a much smaller model size, and much lower training and inference cost. Besides, NoiSER also excels in mitigating overexposure and handling joint tasks.
Authors: Ying Shen, Ismini Lourentzou
Abstract: The research community has shown increasing interest in designing intelligent embodied agents that can assist humans in accomplishing tasks. Although there have been significant advancements in related vision-language benchmarks, most prior work has focused on building agents that follow instructions rather than endowing agents the ability to ask questions to actively resolve ambiguities arising naturally in embodied environments. To address this gap, we propose an Embodied Learning-By-Asking (ELBA) model that learns when and what questions to ask to dynamically acquire additional information for completing the task. We evaluate ELBA on the TEACh vision-dialog navigation and task completion dataset. Experimental results show that the proposed method achieves improved task performance compared to baseline models without question-answering capabilities.
Authors: Senmao Li, Joost van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang, Jian Yang, Ming-Ming Cheng
Abstract: A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the image in the latent space of the pretrained model. However, they suffer from two problems: (1) Unsatisfying results for selected regions and unexpected changes in non-selected regions.(2) They require careful text prompt editing where the prompt should include all visual objects in the input image.To address this, we propose two improvements: (1) Only optimizing the input of the value linear network in the cross-attention layers is sufficiently powerful to reconstruct a real image. (2) We propose attention regularization to preserve the object-like attention maps after reconstruction and editing, enabling us to obtain accurate style editing without invoking significant structural changes. We further improve the editing technique that is used for the unconditional branch of classifier-free guidance as used by P2P. Extensive experimental prompt-editing results on a variety of images demonstrate qualitatively and quantitatively that our method has superior editing capabilities compared to existing and concurrent works. See our accompanying code in Stylediffusion: \url{https://github.com/sen-mao/StyleDiffusion}.
Authors: Jing Liu, Donglai Wei, Yang Liu, Sipeng Zhang, Tong Yang, Victor C. M. Leung
Abstract: Text-Based Person Search (TBPS) is a crucial task in the Internet of Things (IoT) domain that enables accurate retrieval of target individuals from large-scale galleries with only given textual caption. For cross-modal TBPS tasks, it is critical to obtain well-distributed representation in the common embedding space to reduce the inter-modal gap. Furthermore, learning detailed image-text correspondences is essential to discriminate similar targets and enable fine-grained search. To address these challenges, we present a simple yet effective method named Sew Calibration and Masked Modeling (SCMM) that calibrates cross-modal representations by learning compact and well-aligned embeddings. SCMM introduces two novel losses for fine-grained cross-modal representations: Sew calibration loss that aligns image and text features based on textual caption quality, and Masked Caption Modeling (MCM) loss that establishes detailed relationships between textual and visual parts. This dual-pronged strategy enhances feature alignment and cross-modal correspondences, enabling accurate distinction of similar individuals while maintaining a streamlined dual-encoder architecture for real-time inference, which is essential for resource-limited sensors and IoT systems. Extensive experiments on three popular TBPS benchmarks demonstrate the superiority of SCMM, achieving 73.81%, 64.25%, and 57.35% Rank-1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReID, respectively.
Authors: Ankit Dhiman, R Srinath, Srinjay Sarkar, Lokesh R Boregowda, R Venkatesh Babu
Abstract: Colorization is a well-explored problem in the domains of image and video processing. However, extending colorization to 3D scenes presents significant challenges. Recent Neural Radiance Field (NeRF) and Gaussian-Splatting(3DGS) methods enable high-quality novel-view synthesis for multi-view images. However, the question arises: How can we colorize these 3D representations? This work presents a method for synthesizing colorized novel views from input grayscale multi-view images. Using image or video colorization methods to colorize novel views from these 3D representations naively will yield output with severe inconsistencies. We introduce a novel method to use powerful image colorization models for colorizing 3D representations. We propose a distillation-based method that transfers color from these networks trained on natural images to the target 3D representation. Notably, this strategy does not add any additional weights or computational overhead to the original representation during inference. Extensive experiments demonstrate that our method produces high-quality colorized views for indoor and outdoor scenes, showcasing significant cross-view consistency advantages over baseline approaches. Our method is agnostic to the underlying 3D representation and easily generalizable to NeRF and 3DGS methods. Further, we validate the efficacy of our approach in several diverse applications: 1.) Infra-Red (IR) multi-view images and 2.) Legacy grayscale multi-view image sequences. Project Webpage: https://val.cds.iisc.ac.in/chroma-distill.github.io/
Authors: Yu Gao, Lutong Su, Hao Liang, Yufeng Yue, Yi Yang, Mengyin Fu
Abstract: Neural Radiance Fields (NeRF) use multi-view images for 3D scene representation, demonstrating remarkable performance. As one of the primary sources of multi-view images, multi-camera systems encounter challenges such as varying intrinsic parameters and frequent pose changes. Most previous NeRF-based methods assume a unique camera and rarely consider multi-camera scenarios. Besides, some NeRF methods that can optimize intrinsic and extrinsic parameters still remain susceptible to suboptimal solutions when these parameters are poor initialized. In this paper, we propose MC-NeRF, a method that enables joint optimization of both intrinsic and extrinsic parameters alongside NeRF. The method also supports each image corresponding to independent camera parameters. First, we tackle coupling issue and the degenerate case that arise from the joint optimization between intrinsic and extrinsic parameters. Second, based on the proposed solutions, we introduce an efficient calibration image acquisition scheme for multi-camera systems, including the design of calibration object. Finally, we present an end-to-end network with training sequence that enables the estimation of intrinsic and extrinsic parameters, along with the rendering network. Furthermore, recognizing that most existing datasets are designed for a unique camera, we construct a real multi-camera image acquisition system and create a corresponding new dataset, which includes both simulated data and real-world captured images. Experiments confirm the effectiveness of our method when each image corresponds to different camera parameters. Specifically, we use multi-cameras, each with different intrinsic and extrinsic parameters in real-world system, to achieve 3D scene representation without providing initial poses.
Authors: Shadab Ahamed, Yixi Xu, Sara Kurkowska, Claire Gowdy, Joo H. O, Ingrid Bloise, Don Wilson, Patrick Martineau, Fran\c{c}ois B\'enard, Fereshteh Yousefirizi, Rahul Dodhia, Juan M. Lavista, William B. Weeks, Carlos F. Uribe, Arman Rahmim
Abstract: This study addresses critical gaps in automated lymphoma segmentation from PET/CT images, focusing on issues often overlooked in existing literature. While deep learning has been applied for lymphoma lesion segmentation, few studies incorporate out-of-distribution testing, raising concerns about model generalizability across diverse imaging conditions and patient populations. We highlight the need to compare model performance with expert human annotators, including intra- and inter-observer variability, to understand task difficulty better. Most approaches focus on overall segmentation accuracy but overlook lesion-specific measures important for precise lesion detection and disease quantification. To address these gaps, we propose a clinically relevant framework for evaluating deep segmentation networks. Using this lesion measure-specific evaluation, we assess the performance of four deep networks (ResUNet, SegResNet, DynUNet, and SwinUNETR) across 611 cases from multi-institutional datasets, covering various lymphoma subtypes and lesion characteristics. Beyond standard metrics like the Dice similarity coefficient, we evaluate clinical lesion measures and their prediction errors. We also introduce detection criteria for lesion localization and propose a new detection Criterion 3 based on metabolic characteristics. We show that networks perform better on large, intense lesions with higher metabolic activity. Finally, we compare network performance to physicians via intra- and inter-observer variability analyses, demonstrating that network errors closely resemble those made by experts, i.e., the small and faint lesions remain challenging for both humans and networks. This study aims to improve automated lesion segmentation's clinical relevance, supporting better treatment decisions for lymphoma patients. The code is available at: https://github.com/microsoft/lymphoma-segmentation-dnn.
URLs: https://github.com/microsoft/lymphoma-segmentation-dnn.
Authors: Juan A. Rodriguez, Abhay Puri, Shubham Agarwal, Issam H. Laradji, Pau Rodriguez, Sai Rajeswar, David Vazquez, Christopher Pal, Marco Pedersoli
Abstract: Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation methods have focused on curve-based vectorization, lacking semantic understanding, often producing artifacts, and struggling with SVG primitives beyond path curves. To address these issues, we introduce StarVector, a multimodal large language model for SVG generation. It performs image vectorization by understanding image semantics and using SVG primitives for compact, precise outputs. Unlike traditional methods, StarVector works directly in the SVG code space, leveraging visual understanding to apply accurate SVG primitives. To train StarVector, we create SVG-Stack, a diverse dataset of 2M samples that enables generalization across vectorization tasks and precise use of primitives like ellipses, polygons, and text. We address challenges in SVG evaluation, showing that pixel-based metrics like MSE fail to capture the unique qualities of vector graphics. We introduce SVG-Bench, a benchmark across 10 datasets, and 3 tasks: Image-to-SVG, Text-to-SVG generation, and diagram generation. Using this setup, StarVector achieves state-of-the-art performance, producing more compact and semantically rich SVGs.
Authors: Cameron Braunstein, Eddy Ilg, Vladislav Golyanik
Abstract: Quantum visual computing is advancing rapidly. This paper presents a new formulation for stereo matching with nonlinear regularizers and spatial pyramids on quantum annealers as a maximum a posteriori inference problem that minimizes the energy of a Markov Random Field. Our approach is hybrid (i.e., quantum-classical) and is compatible with modern D-Wave quantum annealers, i.e., it includes a quadratic unconstrained binary optimization (QUBO) objective. Previous quantum annealing techniques for stereo matching are limited to using linear regularizers, and thus, they do not exploit the fundamental advantages of the quantum computing paradigm in solving combinatorial optimization problems. In contrast, our method utilizes the full potential of quantum annealing for stereo matching, as nonlinear regularizers create optimization problems which are NP-hard. On the Middlebury benchmark, we achieve an improved root mean squared accuracy over the previous state of the art in quantum stereo matching of 2% and 22.5% when using different solvers.
Authors: Renqiu Xia, Bo Zhang, Hancheng Ye, Xiangchao Yan, Qi Liu, Hongbin Zhou, Zijun Chen, Min Dou, Botian Shi, Junchi Yan, Yu Qiao
Abstract: Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously. However, their capacity to query information depicted in visual charts and engage in reasoning based on the queried contents remains under-explored. In this paper, to comprehensively and rigorously benchmark the ability of the off-the-shelf MLLMs in the chart domain, we construct ChartX, a multi-modal evaluation set covering 18 chart types, 7 chart tasks, 22 disciplinary topics, and high-quality chart data. Besides, we develop ChartVLM to offer a new perspective on handling multi-modal tasks that strongly depend on interpretable patterns, such as reasoning tasks in the field of charts or geometric images. We evaluate the chart-related ability of mainstream MLLMs and our ChartVLM on the proposed ChartX evaluation set. Extensive experiments demonstrate that ChartVLM surpasses both versatile and chart-related large models, achieving results comparable to GPT-4V. We believe that our study can pave the way for further exploration in creating a more comprehensive chart evaluation set and developing more interpretable multi-modal models. Both ChartX and ChartVLM are available at: https://github.com/UniModal4Reasoning/ChartVLM
Authors: Ying Shen, Zhiyang Xu, Qifan Wang, Yu Cheng, Wenpeng Yin, Lifu Huang
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in diverse tasks across different domains, with an increasing focus on improving their zero-shot generalization capabilities for unseen multimodal tasks. Multimodal instruction tuning has emerged as a successful strategy for achieving zero-shot generalization by fine-tuning pre-trained models on diverse multimodal tasks through instructions. As MLLMs grow in complexity and size, the need for parameter-efficient fine-tuning methods like Low-Rank Adaption (LoRA), which fine-tunes with a minimal set of parameters, becomes essential. However, applying LoRA in multimodal instruction tuning presents the challenge of task interference, which leads to performance degradation, especially when dealing with a broad array of multimodal tasks. To address this, this paper introduces a novel approach that integrates multimodal instruction tuning with Conditional Mixture-of-LoRA (MixLoRA). It innovates upon LoRA by dynamically constructing low-rank adaptation matrices tailored to the unique demands of each input instance, aiming to mitigate task interference. Experimental results on various multimodal evaluation datasets indicate that MixLoRA not only outperforms the conventional LoRA with the same or even higher ranks, demonstrating its efficacy and adaptability in diverse multimodal tasks.
Authors: Srinitish Srinivasan, Varenya Pathak, Abirami S
Abstract: Abstract Art is an immensely popular, discussed form of art that often has the ability to depict the emotions of an artist. Many researchers have made attempts to study abstract art in the form of edge detection, brush stroke and emotion recognition algorithms using machine and deep learning. This papers describes the study of a wide distribution of abstract paintings using Generative Adversarial Neural Networks(GAN). GANs have the ability to learn and reproduce a distribution enabling researchers and scientists to effectively explore and study the generated image space. However, the challenge lies in developing an efficient GAN architecture that overcomes common training pitfalls. This paper addresses this challenge by introducing a modified-DCGAN (mDCGAN) specifically designed for high-quality artwork generation. The approach involves a thorough exploration of the modifications made, delving into the intricate workings of DCGANs, optimisation techniques, and regularisation methods aimed at improving stability and realism in art generation enabling effective study of generated patterns. The proposed mDCGAN incorporates meticulous adjustments in layer configurations and architectural choices, offering tailored solutions to the unique demands of art generation while effectively combating issues like mode collapse and gradient vanishing. Further this paper explores the generated latent space by performing random walks to understand vector relationships between brush strokes and colours in the abstract art space and a statistical analysis of unstable outputs after a certain period of GAN training and compare its significant difference. These findings validate the effectiveness of the proposed approach, emphasising its potential to revolutionise the field of digital art generation and digital art ecosystem.
Authors: Ruiming Cao, Dekel Galor, Amit Kohli, Jacob L Yates, Laura Waller
Abstract: Event cameras, also known as dynamic vision sensors, are an emerging modality for measuring fast dynamics asynchronously. Event cameras capture changes of log-intensity over time as a stream of 'events' and generally cannot measure intensity itself; hence, they are only used for imaging dynamic scenes. However, fluctuations due to random photon arrival inevitably trigger noise events, even for static scenes. While previous efforts have been focused on filtering out these undesirable noise events to improve signal quality, we find that, in the photon-noise regime, these noise events are correlated with the static scene intensity. We analyze the noise event generation and model its relationship to illuminance. Based on this understanding, we propose a method, called Noise2Image, to leverage the illuminance-dependent noise characteristics to recover the static parts of a scene, which are otherwise invisible to event cameras. We experimentally collect a dataset of noise events on static scenes to train and validate Noise2Image. Our results provide a novel approach for capturing static scenes in event cameras, solely from noise events, without additional hardware.
Authors: Kai Chen, Yanze Li, Wenhua Zhang, Yanxin Liu, Pengxiang Li, Ruiyuan Gao, Lanqing Hong, Meng Tian, Xinhai Zhao, Zhenguo Li, Dit-Yan Yeung, Huchuan Lu, Xu Jia
Abstract: Large Vision-Language Models (LVLMs) have received widespread attention for advancing the interpretable self-driving. Existing evaluations of LVLMs primarily focus on multi-faceted capabilities in natural circumstances, lacking automated and quantifiable assessment for self-driving, let alone the severe road corner cases. In this work, we propose CODA-LM, the very first benchmark for the automatic evaluation of LVLMs for self-driving corner cases. We adopt a hierarchical data structure and prompt powerful LVLMs to analyze complex driving scenes and generate high-quality pre-annotations for the human annotators, while for LVLM evaluation, we show that using the text-only large language models (LLMs) as judges reveals even better alignment with human preferences than the LVLM judges. Moreover, with our CODA-LM, we build CODA-VLM, a new driving LVLM surpassing all open-sourced counterparts on CODA-LM. Our CODA-VLM performs comparably with GPT-4V, even surpassing GPT-4V by +21.42% on the regional perception task. We hope CODA-LM can become the catalyst to promote interpretable self-driving empowered by LVLMs.
Authors: Junghyup Lee, Jeimin Jeon, Dohyung Kim, Bumsub Ham
Abstract: Quantization-aware training (QAT) simulates a quantization process during training to lower bit-precision of weights/activations. It learns quantized weights indirectly by updating latent weights, i.e., full-precision inputs to a quantizer, using gradient-based optimizers. We claim that coupling a user-defined learning rate (LR) with these optimizers is sub-optimal for QAT. Quantized weights transit discrete levels of a quantizer, only if corresponding latent weights pass transition points, where the quantizer changes discrete states. This suggests that the changes of quantized weights are affected by both the LR for latent weights and their distributions. It is thus difficult to control the degree of changes for quantized weights by scheduling the LR manually. We conjecture that the degree of parameter changes in QAT is related to the number of quantized weights transiting discrete levels. Based on this, we introduce a transition rate (TR) scheduling technique that controls the number of transitions of quantized weights explicitly. Instead of scheduling a LR for latent weights, we schedule a target TR of quantized weights, and update the latent weights with a novel transition-adaptive LR (TALR), enabling considering the degree of changes for the quantized weights during QAT. Experimental results demonstrate the effectiveness of our approach on standard benchmarks.
Authors: Fangneng Zhan, Hanxue Liang, Yifan Wang, Michael Niemeyer, Michael Oechsle, Adam Kortylewski, Cengiz Oztireli, Gordon Wetzstein, Christian Theobalt
Abstract: The landscape of computer graphics has undergone significant transformations with the recent advances of differentiable rendering models. These rendering models often rely on heuristic designs that may not fully align with the final rendering objectives. We address this gap by pioneering \textit{evolutive rendering models}, a methodology where rendering models possess the ability to evolve and adapt dynamically throughout the rendering process. In particular, we present a comprehensive learning framework that enables the optimization of three principal rendering elements, including the gauge transformations, the ray sampling mechanisms, and the primitive organization. Central to this framework is the development of differentiable versions of these rendering elements, allowing for effective gradient backpropagation from the final rendering objectives. A detailed analysis of gradient characteristics is performed to facilitate a stable and goal-oriented elements evolution. Our extensive experiments demonstrate the large potential of evolutive rendering models for enhancing the rendering performance across various domains, including static and dynamic scene representations, generative modeling, and texture mapping.
Authors: Divyam Madaan, Taro Makino, Sumit Chopra, Kyunghyun Cho
Abstract: Supervised multi-modal learning involves mapping multiple modalities to a target label. Previous studies in this field have concentrated on capturing in isolation either the inter-modality dependencies (the relationships between different modalities and the label) or the intra-modality dependencies (the relationships within a single modality and the label). We argue that these conventional approaches that rely solely on either inter- or intra-modality dependencies may not be optimal in general. We view the multi-modal learning problem from the lens of generative models where we consider the target as a source of multiple modalities and the interaction between them. Towards that end, we propose inter- & intra-modality modeling (I2M2) framework, which captures and integrates both the inter- and intra-modality dependencies, leading to more accurate predictions. We evaluate our approach using real-world healthcare and vision-and-language datasets with state-of-the-art models, demonstrating superior performance over traditional methods focusing only on one type of modality dependency.
Authors: Wangbo Yu, Chaoran Feng, Jiye Tang, Jiashu Yang, Zhenyu Tang, Xu Jia, Yuchao Yang, Li Yuan, Yonghong Tian
Abstract: 3D Gaussian Splatting (3D-GS) has demonstrated exceptional capabilities in 3D scene reconstruction and novel view synthesis. However, its training heavily depends on high-quality, sharp images and accurate camera poses. Fulfilling these requirements can be challenging in non-ideal real-world scenarios, where motion-blurred images are commonly encountered in high-speed moving cameras or low-light environments that require long exposure times. To address these challenges, we introduce Event Stream Assisted Gaussian Splatting (EvaGaussians), a novel approach that integrates event streams captured by an event camera to assist in reconstructing high-quality 3D-GS from blurry images. Capitalizing on the high temporal resolution and dynamic range offered by the event camera, we leverage the event streams to explicitly model the formation process of motion-blurred images and guide the deblurring reconstruction of 3D-GS. By jointly optimizing the 3D-GS parameters and recovering camera motion trajectories during the exposure time, our method can robustly facilitate the acquisition of high-fidelity novel views with intricate texture details. We comprehensively evaluated our method and compared it with previous state-of-the-art deblurring rendering methods. Both qualitative and quantitative comparisons demonstrate that our method surpasses existing techniques in restoring fine details from blurry images and producing high-fidelity novel views.
Authors: Yanmin Wu, Jiarui Meng, Haijie Li, Chenming Wu, Yahao Shi, Xinhua Cheng, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Jian Zhang
Abstract: This paper introduces OpenGaussian, a method based on 3D Gaussian Splatting (3DGS) capable of 3D point-level open vocabulary understanding. Our primary motivation stems from observing that existing 3DGS-based open vocabulary methods mainly focus on 2D pixel-level parsing. These methods struggle with 3D point-level tasks due to weak feature expressiveness and inaccurate 2D-3D feature associations. To ensure robust feature presentation and 3D point-level understanding, we first employ SAM masks without cross-frame associations to train instance features with 3D consistency. These features exhibit both intra-object consistency and inter-object distinction. Then, we propose a two-stage codebook to discretize these features from coarse to fine levels. At the coarse level, we consider the positional information of 3D points to achieve location-based clustering, which is then refined at the fine level. Finally, we introduce an instance-level 3D-2D feature association method that links 3D points to 2D masks, which are further associated with 2D CLIP features. Extensive experiments, including open vocabulary-based 3D object selection, 3D point cloud understanding, click-based 3D object selection, and ablation studies, demonstrate the effectiveness of our proposed method. The source code is available at our project page: https://3d-aigc.github.io/OpenGaussian
Authors: Zhanhao Liang, Yuhui Yuan, Shuyang Gu, Bohan Chen, Tiankai Hang, Mingxi Cheng, Ji Li, Liang Zheng
Abstract: Generating visually appealing images is fundamental to modern text-to-image generation models. A potential solution to better aesthetics is direct preference optimization (DPO), which has been applied to diffusion models to improve general image quality including prompt alignment and aesthetics. Popular DPO methods propagate preference labels from clean image pairs to all the intermediate steps along the two generation trajectories. However, preference labels provided in existing datasets are blended with layout and aesthetic opinions, which would disagree with aesthetic preference. Even if aesthetic labels were provided (at substantial cost), it would be hard for the two-trajectory methods to capture nuanced visual differences at different steps. To improve aesthetics economically, this paper uses existing generic preference data and introduces step-by-step preference optimization (SPO) that discards the propagation strategy and allows fine-grained image details to be assessed. Specifically, at each denoising step, we 1) sample a pool of candidates by denoising from a shared noise latent, 2) use a step-aware preference model to find a suitable win-lose pair to supervise the diffusion model, and 3) randomly select one from the pool to initialize the next denoising step. This strategy ensures that the diffusion models to focus on the subtle, fine-grained visual differences instead of layout aspect. We find that aesthetic can be significantly enhanced by accumulating these improved minor differences. When fine-tuning Stable Diffusion v1.5 and SDXL, SPO yields significant improvements in aesthetics compared with existing DPO methods while not sacrificing image-text alignment compared with vanilla models. Moreover, SPO converges much faster than DPO methods due to the step-by-step alignment of fine-grained visual details. Code and models are available at https://github.com/RockeyCoss/SPO.
Authors: Jiho Choi, Seonho Lee, Seungho Lee, Minhyun Lee, Hyunjung Shim
Abstract: Open-vocabulary part segmentation (OVPS) is an emerging research area focused on segmenting fine-grained entities using diverse and previously unseen vocabularies. Our study highlights the inherent complexities of part segmentation due to intricate boundaries and diverse granularity, reflecting the knowledge-based nature of part identification. To address these challenges, we propose PartCLIPSeg, a novel framework utilizing generalized parts and object-level contexts to mitigate the lack of generalization in fine-grained parts. PartCLIPSeg integrates competitive part relationships and attention control, alleviating ambiguous boundaries and underrepresented parts. Experimental results demonstrate that PartCLIPSeg outperforms existing state-of-the-art OVPS methods, offering refined segmentation and an advanced understanding of part relationships within images. Through extensive experiments, our model demonstrated a significant improvement over the state-of-the-art models on the Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets.
Authors: Fengxiang Wang, Hongzhen Wang, Di Wang, Zonghao Guo, Zhenyu Zhong, Long Lan, Jing Zhang, Zhiyuan Liu, Maosong Sun
Abstract: Masked Image Modeling (MIM) has become an essential method for building foundational visual models in remote sensing (RS). However, the limitations in size and diversity of existing RS datasets restrict the ability of MIM methods to learn generalizable representations. Additionally, conventional MIM techniques, which require reconstructing all tokens, introduce unnecessary computational overhead. To address these issues, we present a new pre-training pipeline for RS models, featuring the creation of a large-scale RS dataset and an efficient MIM approach. We curated a high-quality dataset named OpticalRS-13M by collecting publicly available RS datasets and processing them through exclusion, slicing, and deduplication. OpticalRS-13M comprises 13 million optical images covering various RS tasks, such as object detection and pixel segmentation. To enhance efficiency, we propose SelectiveMAE, a pre-training method that dynamically encodes and reconstructs semantically rich patch tokens, thereby reducing the inefficiencies of traditional MIM models caused by redundant background pixels in RS images. Extensive experiments demonstrate that OpticalRS-13M significantly improves classification, detection, and segmentation performance, while SelectiveMAE increases training efficiency over 2 times. This highlights the effectiveness and scalability of our pipeline in developing RS foundational models.
Authors: Ruinan Jin, Zikang Xu, Yuan Zhong, Qiongsong Yao, Qi Dou, S. Kevin Zhou, Xiaoxiao Li
Abstract: The advent of foundation models (FMs) in healthcare offers unprecedented opportunities to enhance medical diagnostics through automated classification and segmentation tasks. However, these models also raise significant concerns about their fairness, especially when applied to diverse and underrepresented populations in healthcare applications. Currently, there is a lack of comprehensive benchmarks, standardized pipelines, and easily adaptable libraries to evaluate and understand the fairness performance of FMs in medical imaging, leading to considerable challenges in formulating and implementing solutions that ensure equitable outcomes across diverse patient populations. To fill this gap, we introduce FairMedFM, a fairness benchmark for FM research in medical imaging.FairMedFM integrates with 17 popular medical imaging datasets, encompassing different modalities, dimensionalities, and sensitive attributes. It explores 20 widely used FMs, with various usages such as zero-shot learning, linear probing, parameter-efficient fine-tuning, and prompting in various downstream tasks -- classification and segmentation. Our exhaustive analysis evaluates the fairness performance over different evaluation metrics from multiple perspectives, revealing the existence of bias, varied utility-fairness trade-offs on different FMs, consistent disparities on the same datasets regardless FMs, and limited effectiveness of existing unfairness mitigation methods. Checkout FairMedFM's project page and open-sourced codebase, which supports extendible functionalities and applications as well as inclusive for studies on FMs in medical imaging over the long term.
Authors: Roy Y. He, Hao Liu
Abstract: We propose a novel model for decomposing grayscale images into three distinct components: the structural part, representing sharp boundaries and regions with strong light-to-dark transitions; the smooth part, capturing soft shadows and shades; and the oscillatory part, characterizing textures and noise. To capture the homogeneous structures, we introduce a combination of $L^0$-gradient and curvature regularization on level lines. This new regularization term enforces strong sparsity on the image gradient while reducing the undesirable staircase effects as well as preserving the geometry of contours. For the smoothly varying component, we utilize the $L^2$-norm of the Laplacian that favors isotropic smoothness. To capture the oscillation, we use the inverse Sobolev seminorm. To solve the associated minimization problem, we design an efficient operator-splitting algorithm. Our algorithm effectively addresses the challenging non-convex non-smooth problem by separating it into sub-problems. Each sub-problem can be solved either directly using closed-form solutions or efficiently using the Fast Fourier Transform (FFT). We provide systematic experiments, including ablation and comparison studies, to analyze our model's behaviors and demonstrate its effectiveness as well as efficiency.
Authors: Songqin Nong, Jiali Zhu, Rui Wu, Jiongchao Jin, Shuo Shan, Xiutian Huang, Wenhao Xu
Abstract: Currently, the integration of mobile Graphical User Interfaces (GUIs) is ubiquitous in most people's daily lives. And the ongoing evolution of multimodal large-scale models, such as GPT-4v, Qwen-VL-Max, has significantly bolstered the capabilities of GUI comprehension and user action analysis, showcasing the potentiality of intelligent GUI assistants. However, current GUI Agents often need to access page layout information through calling system APIs, which may pose privacy risks. Fixing GUI (such as mobile interfaces) to a certain low resolution might result in the loss of fine-grained image details. At the same time, the multimodal large models built for GUI Agents currently have poor understanding and decision-making abilities for Chinese GUI interfaces, making them difficult to apply to a large number of Chinese apps. This paper introduces MobileFlow, a multimodal large language model meticulously crafted for mobile GUI agents. Transforming from the open-source model Qwen-VL-Chat into GUI domain, MobileFlow contains approximately 21 billion parameters and is equipped with novel hybrid visual encoders, making it possible for variable resolutions of image inputs and good support for multilingual GUI. By incorporating Mixture of Experts (MoE) expansions and pioneering alignment training strategies, MobileFlow has the capacity to fully interpret image data and comprehend user instructions for GUI interaction tasks. Finally, MobileFlow outperforms Qwen-VL-Max and GPT-4v in terms of task execution by GUI agents on both public and our proposed evaluation metrics, and has been successfully deployed in real-world business contexts, proving its effectiveness for practical applications.
Authors: Matthias Freiberger, Peter Kun, Anders Sundnes L{\o}vlie, Sebastian Risi
Abstract: Due to their architecture and how they are trained, artificial neural networks are typically not robust toward pruning or shuffling layers at test time. However, such properties would be desirable for different applications, such as distributed neural network architectures where the order of execution cannot be guaranteed or parts of the network can fail during inference. In this work, we address these issues through a number of training approaches for vision transformers whose most important component is randomizing the execution order of attention modules at training time. With our proposed approaches, vision transformers are capable to adapt to arbitrary layer execution orders at test time assuming one tolerates a reduction (about 20\%) in accuracy at the same model size. We analyse the feature representations of our trained models as well as how each layer contributes to the models prediction based on its position during inference. Our analysis shows that layers learn to contribute differently based on their position in the network. Finally, we layer-prune our models at test time and find that their performance declines gracefully. Code available at https://github.com/matfrei/layershuffle.
Authors: Kun Wu, Zhiguo Jiang, Kunming Tang, Jun Shi, Fengying Xie, Wei Wang, Haibo Wu, Yushan Zheng
Abstract: Large-scale pre-training models have promoted the development of histopathology image analysis. However, existing self-supervised methods for histopathology images primarily focus on learning patch features, while there is a notable gap in the availability of pre-training models specifically designed for WSI-level feature learning. In this paper, we propose a novel self-supervised learning framework for pan-cancer WSI-level representation pre-training with the designed position-aware masked autoencoder (PAMA). Meanwhile, we propose the position-aware cross-attention (PACA) module with a kernel reorientation (KRO) strategy and an anchor dropout (AD) mechanism. The KRO strategy can capture the complete semantic structure and eliminate ambiguity in WSIs, and the AD contributes to enhancing the robustness and generalization of the model. We evaluated our method on 7 large-scale datasets from multiple organs for pan-cancer classification tasks. The results have demonstrated the effectiveness and generalization of PAMA in discriminative WSI representation learning and pan-cancer WSI pre-training. The proposed method was also compared with 8 WSI analysis methods. The experimental results have indicated that our proposed PAMA is superior to the state-of-the-art methods. The code and checkpoints are available at https://github.com/WkEEn/PAMA.
Authors: Fajwel Fogel, Yohann Perron, Nikola Besic, Laurent Saint-Andr\'e, Agn\`es Pellissier-Tanon, Martin Schwartz, Thomas Boudras, Ibrahim Fayad, Alexandre d'Aspremont, Loic Landrieu, Philippe Ciais
Abstract: Estimating canopy height and its changes at meter resolution from satellite imagery is a significant challenge in computer vision with critical environmental applications. However, the lack of open-access datasets at this resolution hinders the reproducibility and evaluation of models. We introduce Open-Canopy, the first open-access, country-scale benchmark for very high-resolution (1.5 m) canopy height estimation, covering over 87,000 km$^2$ across France with 1.5 m resolution satellite imagery and aerial LiDAR data. Additionally, we present Open-Canopy-$\Delta$, a benchmark for canopy height change detection between images from different years at tree level-a challenging task for current computer vision models. We evaluate state-of-the-art architectures on these benchmarks, highlighting significant challenges and opportunities for improvement. Our datasets and code are publicly available at https://github.com/fajwel/Open-Canopy.
Authors: Jiawei Lian, Jianhong Pan, Lefan Wang, Yi Wang, Lap-Pui Chau, Shaohui Mei
Abstract: Physical attacks against object detection have gained increasing attention due to their significant practical implications. However, conducting physical experiments is extremely time-consuming and labor-intensive. Moreover, physical dynamics and cross-domain transformation are challenging to strictly regulate in the real world, leading to unaligned evaluation and comparison, severely hindering the development of physically robust models. To accommodate these challenges, we explore utilizing realistic simulation to thoroughly and rigorously benchmark physical attacks with fairness under controlled physical dynamics and cross-domain transformation. This resolves the problem of capturing identical adversarial images that cannot be achieved in the real world. Our benchmark includes 20 physical attack methods, 48 object detectors, comprehensive physical dynamics, and evaluation metrics. We also provide end-to-end pipelines for dataset generation, detection, evaluation, and further analysis. In addition, we perform 8064 groups of evaluation based on our benchmark, which includes both overall evaluation and further detailed ablation studies for controlled physical dynamics. Through these experiments, we provide in-depth analyses of physical attack performance and physical adversarial robustness, draw valuable observations, and discuss potential directions for future research. Codebase: https://github.com/JiaweiLian/Benchmarking_Physical_Attack
URLs: https://github.com/JiaweiLian/Benchmarking_Physical_Attack
Authors: Victoria Clerico (George Mason Unviersity), Shay Snyder (George Mason Unviersity), Arya Lohia (George Mason Unviersity), Md Abdullah-Al Kaiser (University of Southern, California), Gregory Schwartz (Northwestern University), Akhilesh Jaiswal (University of Southern, California), Maryam Parsa (George Mason Unviersity)
Abstract: Event-cameras have emerged as a revolutionary technology with a high temporal resolution that far surpasses standard active pixel cameras. This technology draws biological inspiration from photoreceptors and the initial retinal synapse. This research showcases the potential of additional retinal functionalities to extract visual features. We provide a domain-agnostic and efficient algorithm for ego-motion compensation based on Object Motion Sensitivity (OMS), one of the multiple features computed within the mammalian retina. We develop a method based on experimental neuroscience that translates OMS' biological circuitry to a low-overhead algorithm to suppress camera motion bypassing the need for deep networks and learning. Our system processes event data from dynamic scenes to perform pixel-wise object motion segmentation using a real and synthetic dataset. This paper introduces a bio-inspired computer vision method that dramatically reduces the number of parameters by $\text{10}^\text{3}$ to $\text{10}^\text{6}$ orders of magnitude compared to previous approaches. Our work paves the way for robust, high-speed, and low-bandwidth decision-making for in-sensor computations.
Authors: Karsten Roth, Vishaal Udandarao, Sebastian Dziadzio, Ameya Prabhu, Mehdi Cherti, Oriol Vinyals, Olivier H\'enaff, Samuel Albanie, Matthias Bethge, Zeynep Akata
Abstract: Multimodal foundation models serve numerous applications at the intersection of vision and language. Still, despite being pretrained on extensive data, they become outdated over time. To keep models updated, research into continual pretraining mainly explores scenarios with either (1) infrequent, indiscriminate updates on large-scale new data, or (2) frequent, sample-level updates. However, practical model deployment often operates in the gap between these two limit cases, as real-world applications often demand adaptation to specific subdomains, tasks or concepts -- spread over the entire, varying life cycle of a model. In this work, we complement current perspectives on continual pretraining through a research test bed as well as provide comprehensive guidance for effective continual model updates in such scenarios. We first introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements, constructed over 63 datasets with diverse visual and semantic coverage. Using FoMo-in-Flux, we explore the complex landscape of practical continual pretraining through multiple perspectives: (1) A data-centric investigation of data mixtures and stream orderings that emulate real-world deployment situations, (2) a method-centric investigation ranging from simple fine-tuning and traditional continual learning strategies to parameter-efficient updates and model merging, (3) meta learning rate schedules and mechanistic design choices, and (4) the influence of model and compute scaling. Together, our insights provide a practitioner's guide to continual multimodal pretraining for real-world deployment. Our benchmark and code is here: https://github.com/ExplainableML/fomo_in_flux.
Authors: Lintao Xu, Chaohui Wang
Abstract: Occlusion boundaries (OBs) geometrically localize the occlusion events in a 2D image, and contain useful information for addressing various scene understanding problems. To advance their study, we have led the investigation in the following three aspects. Firstly, we have studied interactive estimation of OBs, which is the first in the literature, and proposed an efficient deep-network-based method using multiple-scribble intervention, named DNMMSI, which significantly improves the performance over the state-of-the-art fully-automatic methods. Secondly, we propose to exploit the synthetic benchmark for the training, thanks to the particularity that OBs are determined geometrically and unambiguously from the 3D scene. To this end, we have developed an efficient tool, named Mesh2OB, for the automatic generation of 2D images together with their ground-truth OBs, using which we have constructed a synthetic benchmark, named OB-FUTURE. Abundant experimental results demonstrate that leveraging such a synthetic benchmark for training achieves promising performance, even without the use of domain adaptation techniques. Finally, to achieve a more compelling and robust evaluation in OB-related research, we have created a real-world benchmark OB-LabName, consisting of 120 high-resolution images together with their ground-truth OBs, with precision surpassing that of previous benchmarks. We will release DNMMSI with pre-trained parameters, Mesh2OB, OB-FUTURE, and OB-LabName to support further research.
Authors: Raja Kumar, Raghav Singhal, Pranamya Kulkarni, Deval Mehta, Kshitij Jadhav
Abstract: Deep multimodal learning has shown remarkable success by leveraging contrastive learning to capture explicit one-to-one relations across modalities. However, real-world data often exhibits shared relations beyond simple pairwise associations. We propose M3CoL, a Multimodal Mixup Contrastive Learning approach to capture nuanced shared relations inherent in multimodal data. Our key contribution is a Mixup-based contrastive loss that learns robust representations by aligning mixed samples from one modality with their corresponding samples from other modalities thereby capturing shared relations between them. For multimodal classification tasks, we introduce a framework that integrates a fusion module with unimodal prediction modules for auxiliary supervision during training, complemented by our proposed Mixup-based contrastive loss. Through extensive experiments on diverse datasets (N24News, ROSMAP, BRCA, and Food-101), we demonstrate that M3CoL effectively captures shared multimodal relations and generalizes across domains. It outperforms state-of-the-art methods on N24News, ROSMAP, and BRCA, while achieving comparable performance on Food-101. Our work highlights the significance of learning shared relations for robust multimodal learning, opening up promising avenues for future research. Our code is publicly available at https://github.com/RaghavSinghal10/M3CoL.
Authors: Jacopo Dapueto, Nicoletta Noceti, Francesca Odone
Abstract: Developing meaningful and efficient representations that separate the fundamental structure of the data generation mechanism is crucial in representation learning. However, Disentangled Representation Learning has not fully shown its potential on real images, because of correlated generative factors, their resolution and limited access to ground truth labels. Specifically on the latter, we investigate the possibility of leveraging synthetic data to learn general-purpose disentangled representations applicable to real data, discussing the effect of fine-tuning and what properties of disentanglement are preserved after the transfer. We provide an extensive empirical study to address these issues. In addition, we propose a new interpretable intervention-based metric, to measure the quality of factors encoding in the representation. Our results indicate that some level of disentanglement, transferring a representation from synthetic to real data, is possible and effective.
Authors: Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick P\'erez, Raoul de Charette
Abstract: We consider the problem of adapting a contrastively pretrained vision-language model like CLIP (Radford et al., 2021) for few-shot classification. The literature addresses this problem by learning a linear classifier of the frozen visual features, optimizing word embeddings, or learning external feature adapters. This paper introduces an alternative way for CLIP adaptation without adding 'external' parameters to optimize. We find that simply fine-tuning the last projection matrix of the vision encoder leads to performance better than all baselines. Furthermore, we show that regularizing training with the distance between the fine-tuned and pretrained matrices adds reliability for adapting CLIP. This simple approach, coined ProLIP, yields state-of-the-art performance on 11 few-shot classification benchmarks, few-shot domain generalization, cross-dataset transfer, base-to-new class generalization, and test-time adaptation. Code will be made available at: https://github.com/astra-vision/ProLIP .
Authors: Yize Chen, Zhiyuan Yan, Siwei Lyu, Baoyuan Wu
Abstract: Detecting deepfakes has become an important task. Most existing detection methods provide only real/fake predictions without offering human-comprehensible explanations. Recent studies leveraging MLLMs for deepfake detection have shown improvements in explainability. However, the performance of pre-trained MLLMs (e.g., LLaVA) remains limited due to a lack of understanding of their capabilities for this task and strategies to enhance them. In this work, we empirically assess the strengths and weaknesses of MLLMs specifically in deepfake detection via forgery features analysis. Building on these assessments, we propose a novel framework called ${X}^2$-DFD, consisting of three core modules. The first module, Model Feature Assessment (MFA), measures the detection capabilities of forgery features intrinsic to MLLMs, and gives a descending ranking of these features. The second module, Strong Feature Strengthening (SFS), enhances the detection and explanation capabilities by fine-tuning the MLLM on a dataset constructed based on the top-ranked features. The third module, Weak Feature Supplementing (WFS), improves the fine-tuned MLLM's capabilities on lower-ranked features by integrating external dedicated deepfake detectors. To verify the effectiveness of this framework, we further present a practical implementation, where an automated forgery features generation, evaluation, and ranking procedure is designed for MFA module; an automated generation procedure of the fine-tuning dataset containing real and fake images with explanations based on top-ranked features is developed for SFS model; an external conventional deepfake detector focusing on blending artifact, which corresponds to a low detection capability in the pre-trained MLLM, is integrated for WFS module. Experiments show that our approach enhances both detection and explanation performance.
Authors: Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong, Lei Zhu, Shuicheng Yan
Abstract: We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations, advanced positional encoding strategies, and optimized sampling conditions, Meissonic substantially improves MIM's performance and efficiency. Additionally, we leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images. Extensive experiments validate Meissonic's capabilities, demonstrating its potential as a new standard in text-to-image synthesis. We release a model checkpoint capable of producing $1024 \times 1024$ resolution images.
Authors: Zhi-Song Liu, Li-Wen Wang, Jun Xiao, Vicky Kalogeiton
Abstract: Image style transfer has attracted widespread attention in the past few years. Despite its remarkable results, it requires additional style images available as references, making it less flexible and inconvenient. Using text is the most natural way to describe the style. More importantly, text can describe implicit abstract styles, like styles of specific artists or art movements. In this paper, we propose a Contrastive Learning for Artistic Style Transfer (CLAST) that leverages advanced image-text encoders to control arbitrary style transfer. We introduce a supervised contrastive training strategy to effectively extract style descriptions from the image-text model (i.e., CLIP), which aligns stylization with the text description. To this end, we also propose a novel and efficient adaLN based state space models that explore style-content fusion. Finally, we achieve a text-driven image style transfer. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods in artistic style transfer. More importantly, it does not require online fine-tuning and can render a 512x512 image in 0.03s.
Authors: Donghao Zhou, Jiancheng Huang, Jinbin Bai, Jiaze Wang, Hao Chen, Guangyong Chen, Xiaowei Hu, Pheng-Ann Heng
Abstract: Recent text-to-image models generate high-quality images from text prompts but lack precise control over specific components within visual concepts. Therefore, we introduce component-controllable personalization, a new task that allows users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesirable elements distort the concept, and semantic imbalance, which leads to disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adaptively perturb unwanted visual semantics and Dual-Stream Balancing for more balanced learning of desired visual semantics. The experimental results show that MagicTailor outperforms existing methods in this task and enables more personalized, nuanced, and creative image generation.
Authors: Juliette Marrie, Romain Menegaux, Michael Arbel, Diane Larlus, Julien Mairal
Abstract: We address the problem of extending the capabilities of vision foundation models such as DINO, SAM, and CLIP, to 3D tasks. Specifically, we introduce a novel method to uplift 2D image features into 3D Gaussian Splatting scenes. Unlike traditional approaches that rely on minimizing a reconstruction loss, our method employs a simpler and more efficient feature aggregation technique, augmented by a graph diffusion mechanism. Graph diffusion enriches features from a given model, such as CLIP, by leveraging 3D geometry and pairwise similarities induced by another strong model such as DINOv2. Our approach achieves performance comparable to the state of the art on multiple downstream tasks while delivering significant speed-ups. Notably, we obtain competitive segmentation results using generic DINOv2 features, despite DINOv2 not being trained on millions of annotated segmentation masks like SAM. When applied to CLIP features, our method demonstrates strong performance in open-vocabulary object detection tasks, highlighting the versatility of our approach.
Authors: Sanghyuk Chun, Wonjae Kim, Song Park, Sangdoo Yun
Abstract: Vision-language models (VLMs) embed aligned image-text pairs into a joint space but often rely on deterministic embeddings, assuming a one-to-one correspondence between images and texts. This oversimplifies real-world relationships, which are inherently many-to-many, with multiple captions describing a single image and vice versa. We introduce Probabilistic Language-Image Pre-training (ProLIP), the first probabilistic VLM pre-trained on a billion-scale image-text dataset using only probabilistic objectives, achieving a strong zero-shot capability (e.g., 74.6% ImageNet zero-shot accuracy with ViT-B/16). ProLIP efficiently estimates uncertainty by an "uncertainty token" without extra parameters. We also introduce a novel inclusion loss that enforces distributional inclusion relationships between image-text pairs and between original and masked inputs. Experiments demonstrate that, by leveraging uncertainty estimates, ProLIP benefits downstream tasks and aligns with intuitive notions of uncertainty, e.g., shorter texts being more uncertain and more general inputs including specific ones. Utilizing text uncertainties, we further improve ImageNet accuracy from 74.6% to 75.8% (under a few-shot setting), supporting the practical advantages of our probabilistic approach. The code is available at https://github.com/naver-ai/prolip
Authors: Hairuo Hu, Haiyong Cong, Zhuyu Shao, Yubo Bi, Jinghao Liu
Abstract: In the context of firefighting and rescue operations, a cross-modal semantic segmentation model based on a single-chip millimeter-wave (mmWave) radar for indoor environmental perception is proposed and discussed. To efficiently obtain high-quality labels, an automatic label generation method utilizing LiDAR point clouds and occupancy grid maps is introduced. The proposed segmentation model is based on U-Net. A spatial attention module is incorporated, which enhanced the performance of the mode. The results demonstrate that cross-modal semantic segmentation provides a more intuitive and accurate representation of indoor environments. Unlike traditional methods, the model's segmentation performance is minimally affected by azimuth. Although performance declines with increasing distance, this can be mitigated by a well-designed model. Additionally, it was found that using raw ADC data as input is ineffective; compared to RA tensors, RD tensors are more suitable for the proposed model.
Authors: Haoxuan Che, Xuanhua He, Quande Liu, Cheng Jin, Hao Chen
Abstract: We introduce GameGen-X, the first diffusion transformer model specifically designed for both generating and interactively controlling open-world game videos. This model facilitates high-quality, open-domain generation by simulating an extensive array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, predicting and altering future content based on the current clip, thus allowing for gameplay simulation. To realize this vision, we first collected and built an Open-World Video Game Dataset from scratch. It is the first and largest dataset for open-world game video generation and control, which comprises over a million diverse gameplay video clips sampling from over 150 games with informative captions from GPT-4o. GameGen-X undergoes a two-stage training process, consisting of foundation model pre-training and instruction tuning. Firstly, the model was pre-trained via text-to-video generation and video continuation, endowing it with the capability for long-sequence, high-quality open-domain game video generation. Further, to achieve interactive controllability, we designed InstructNet to incorporate game-related multi-modal control signal experts. This allows the model to adjust latent representations based on user inputs, unifying character interaction and scene content control for the first time in video generation. During instruction tuning, only the InstructNet is updated while the pre-trained foundation model is frozen, enabling the integration of interactive controllability without loss of diversity and quality of generated video content.
Authors: Xianghui Yang, Huiwen Shi, Bowen Zhang, Fan Yang, Jiacheng Wang, Hongxu Zhao, Xinhai Liu, Xinzhou Wang, Qingxiang Lin, Jiaao Yu, Lifu Wang, Zhuo Chen, Sicong Liu, Yuhong Liu, Yong Yang, Di Wang, Jie Jiang, Chunchao Guo
Abstract: While 3D generative models have greatly improved artists' workflows, the existing diffusion models for 3D generation suffer from slow generation and poor generalization. To address this issue, we propose a two-stage approach named Hunyuan3D-1.0 including a lite version and a standard version, that both support text- and image-conditioned generation. In the first stage, we employ a multi-view diffusion model that efficiently generates multi-view RGB in approximately 4 seconds. These multi-view images capture rich details of the 3D asset from different viewpoints, relaxing the tasks from single-view to multi-view reconstruction. In the second stage, we introduce a feed-forward reconstruction model that rapidly and faithfully reconstructs the 3D asset given the generated multi-view images in approximately 7 seconds. The reconstruction network learns to handle noises and in-consistency introduced by the multi-view diffusion and leverages the available information from the condition image to efficiently recover the 3D structure. Our framework involves the text-to-image model, i.e., Hunyuan-DiT, making it a unified framework to support both text- and image-conditioned 3D generation. Our standard version has 3x more parameters than our lite and other existing model. Our Hunyuan3D-1.0 achieves an impressive balance between speed and quality, significantly reducing generation time while maintaining the quality and diversity of the produced assets.
Authors: Xiayang Xiao, Zhuoxuan Li, Ruyi Zhang, Jiacheng Chen, Haipeng Wang
Abstract: The limitations of existing Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) methods lie in their confinement by the closed-environment assumption, hindering their effective and robust handling of unknown target categories in open environments. Open Set Recognition (OSR), a pivotal facet for algorithmic practicality, intends to categorize known classes while denoting unknown ones as "unknown." The chief challenge in OSR involves concurrently mitigating risks associated with generalizing features from a restricted set of known classes to numerous unknown samples and the open space exposure to potential unknown data. To enhance open-set SAR classification, a method called scattering kernel with reciprocal learning network is proposed. Initially, a feature learning framework is constructed based on reciprocal point learning (RPL), establishing a bounded space for potential unknown classes. This approach indirectly introduces unknown information into a learner confined to known classes, thereby acquiring more concise and discriminative representations. Subsequently, considering the variability in the imaging of targets at different angles and the discreteness of components in SAR images, a proposal is made to design convolutional kernels based on large-sized attribute scattering center models. This enhances the ability to extract intrinsic non-linear features and specific scattering characteristics in SAR images, thereby improving the discriminative features of the model and mitigating the impact of imaging variations on classification performance. Experiments on the MSTAR datasets substantiate the superior performance of the proposed approach called ASC-RPL over mainstream methods.
Authors: Tianhe Ren, Yihao Chen, Qing Jiang, Zhaoyang Zeng, Yuda Xiong, Wenlong Liu, Zhengyu Ma, Junyi Shen, Yuan Gao, Xiaoke Jiang, Xingyu Chen, Zhuheng Song, Yuhong Zhang, Hongjie Huang, Han Gao, Shilong Liu, Hao Zhang, Feng Li, Kent Yu, Lei Zhang
Abstract: In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.5 to pursue an object-level representation for open-world object understanding. To make long-tailed object detection easy, DINO-X extends its input options to support text prompt, visual prompt, and customized prompt. With such flexible prompt options, we develop a universal object prompt to support prompt-free open-world detection, making it possible to detect anything in an image without requiring users to provide any prompt. To enhance the model's core grounding capability, we have constructed a large-scale dataset with over 100 million high-quality grounding samples, referred to as Grounding-100M, for advancing the model's open-vocabulary detection performance. Pre-training on such a large-scale grounding dataset leads to a foundational object-level representation, which enables DINO-X to integrate multiple perception heads to simultaneously support multiple object perception and understanding tasks, including detection, segmentation, pose estimation, object captioning, object-based QA, etc. Experimental results demonstrate the superior performance of DINO-X. Specifically, the DINO-X Pro model achieves 56.0 AP, 59.8 AP, and 52.4 AP on the COCO, LVIS-minival, and LVIS-val zero-shot object detection benchmarks, respectively. Notably, it scores 63.3 AP and 56.5 AP on the rare classes of LVIS-minival and LVIS-val benchmarks, improving the previous SOTA performance by 5.8 AP and 5.0 AP. Such a result underscores its significantly improved capacity for recognizing long-tailed objects.
Authors: Wang Yu, Wei Wei
Abstract: Recognition of low-quality face images remains a challenge due to invisible or deformation in partial facial regions. For low-quality images dominated by missing partial facial regions, local region similarity contributes more to face recognition (FR). Conversely, in cases dominated by local face deformation, excessive attention to local regions may lead to misjudgments, while global features exhibit better robustness. However, most of the existing FR methods neglect the bias in feature quality of low-quality images introduced by different factors. To address this issue, we propose a Local and Global Feature Attention Fusion (LGAF) network based on feature quality. The network adaptively allocates attention between local and global features according to feature quality and obtains more discriminative and high-quality face features through local and global information complementarity. In addition, to effectively obtain fine-grained information at various scales and increase the separability of facial features in high-dimensional space, we introduce a Multi-Head Multi-Scale Local Feature Extraction (MHMS) module. Experimental results demonstrate that the LGAF achieves the best average performance on $4$ validation sets (CFP-FP, CPLFW, AgeDB, and CALFW), and the performance on TinyFace and SCFace outperforms the state-of-the-art methods (SoTA).
Authors: Jun Chen, Dannong Xu, Junjie Fei, Chun-Mei Feng, Mohamed Elhoseiny
Abstract: Large multimodal models (LMMs) have achieved impressive progress in vision-language understanding, yet they face limitations in real-world applications requiring complex reasoning over a large number of images. Existing benchmarks for multi-image question-answering are limited in scope, each question is paired with only up to 30 images, which does not fully capture the demands of large-scale retrieval tasks encountered in the real-world usages. To reduce these gaps, we introduce two document haystack benchmarks, dubbed DocHaystack and InfoHaystack, designed to evaluate LMM performance on large-scale visual document retrieval and understanding. Additionally, we propose V-RAG, a novel, vision-centric retrieval-augmented generation (RAG) framework that leverages a suite of multimodal vision encoders, each optimized for specific strengths, and a dedicated question-document relevance module. V-RAG sets a new standard, with a 9% and 11% improvement in Recall@1 on the challenging DocHaystack-1000 and InfoHaystack-1000 benchmarks, respectively, compared to the previous best baseline models. Additionally, integrating V-RAG with LMMs enables them to efficiently operate across thousands of images, yielding significant improvements on our DocHaystack and InfoHaystack benchmarks. Our code and datasets are available at https://github.com/Vision-CAIR/dochaystacks
Authors: Nicola Fanelli, Gennaro Vessio, Giovanna Castellano
Abstract: Inpainting focuses on filling missing or corrupted regions of an image to blend seamlessly with its surrounding content and style. While conditional diffusion models have proven effective for text-guided inpainting, we introduce the novel task of multi-mask inpainting, where multiple regions are simultaneously inpainted using distinct prompts. Furthermore, we design a fine-tuning procedure for multimodal LLMs, such as LLaVA, to generate multi-mask prompts automatically using corrupted images as inputs. These models can generate helpful and detailed prompt suggestions for filling the masked regions. The generated prompts are then fed to Stable Diffusion, which is fine-tuned for the multi-mask inpainting problem using rectified cross-attention, enforcing prompts onto their designated regions for filling. Experiments on digitized paintings from WikiArt and the Densely Captioned Images dataset demonstrate that our pipeline delivers creative and accurate inpainting results. Our code, data, and trained models are available at https://cilabuniba.github.io/i-dream-my-painting.
Authors: Tiantian Geng, Jinrui Zhang, Qingni Wang, Teng Wang, Jinming Duan, Feng Zheng
Abstract: Despite impressive advancements in video understanding, most efforts remain limited to coarse-grained or visual-only video tasks. However, real-world videos encompass omni-modal information (vision, audio, and speech) with a series of events forming a cohesive storyline. The lack of multi-modal video data with fine-grained event annotations and the high cost of manual labeling are major obstacles to comprehensive omni-modality video perception. To address this gap, we propose an automatic pipeline consisting of high-quality multi-modal video filtering, semantically coherent omni-modal event boundary detection, and cross-modal correlation-aware event captioning. In this way, we present LongVALE, the first-ever Vision-Audio-Language Event understanding benchmark comprising 105K omni-modal events with precise temporal boundaries and detailed relation-aware captions within 8.4K high-quality long videos. Further, we build a baseline that leverages LongVALE to enable video large language models (LLMs) for omni-modality fine-grained temporal video understanding for the first time. Extensive experiments demonstrate the effectiveness and great potential of LongVALE in advancing comprehensive multi-modal video understanding.
Authors: Libin Liu, Shen Chen, Sen Jia, Jingzhe Shi, Zhongyu Jiang, Can Jin, Wu Zongkai, Jenq-Neng Hwang, Lei Li
Abstract: Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on predefined datasets, and struggle to adapt dynamically to changing spatial relationships. In this paper, we introduce GraphCanvas3D, a programmable, extensible, and adaptable framework for controllable 3D scene generation. Leveraging in-context learning, GraphCanvas3D enables dynamic adaptability without the need for retraining, supporting flexible and customizable scene creation. Our framework employs hierarchical, graph-driven scene descriptions, representing spatial elements as graph nodes and establishing coherent relationships among objects in 3D environments. Unlike conventional approaches, which are constrained in adaptability and often require predefined input masks or retraining for modifications, GraphCanvas3D allows for seamless object manipulation and scene adjustments on the fly. Additionally, GraphCanvas3D supports 4D scene generation, incorporating temporal dynamics to model changes over time. Experimental results and user studies demonstrate that GraphCanvas3D enhances usability, flexibility, and adaptability for scene generation. Our code and models are available on the project website: https://github.com/ILGLJ/Graph-Canvas.
Authors: Haoze Sun, Wenbo Li, Jiayue Liu, Kaiwen Zhou, Yongqiang Chen, Yong Guo, Yanwei Li, Renjing Pei, Long Peng, Yujiu Yang
Abstract: Generalization has long been a central challenge in real-world image restoration. While recent diffusion-based restoration methods, which leverage generative priors from text-to-image models, have made progress in recovering more realistic details, they still encounter "generative capability deactivation" when applied to out-of-distribution real-world data. To address this, we propose using text as an auxiliary invariant representation to reactivate the generative capabilities of these models. We begin by identifying two key properties of text input: richness and relevance, and examine their respective influence on model performance. Building on these insights, we introduce Res-Captioner, a module that generates enhanced textual descriptions tailored to image content and degradation levels, effectively mitigating response failures. Additionally, we present RealIR, a new benchmark designed to capture diverse real-world scenarios. Extensive experiments demonstrate that Res-Captioner significantly enhances the generalization abilities of diffusion-based restoration models, while remaining fully plug-and-play.
Authors: Wooseok Jang, Youngjun Hong, Geonho Cha, Seungryong Kim
Abstract: Manipulation of facial images to meet specific controls such as pose, expression, and lighting, also known as face rigging, is a complex task in computer vision. Existing methods are limited by their reliance on image datasets, which necessitates individual-specific fine-tuning and limits their ability to retain fine-grained identity and semantic details, reducing practical usability. To overcome these limitations, we introduce ControlFace, a novel face rigging method conditioned on 3DMM renderings that enables flexible, high-fidelity control. We employ a dual-branch U-Nets: one, referred to as FaceNet, captures identity and fine details, while the other focuses on generation. To enhance control precision, the control mixer module encodes the correlated features between the target-aligned control and reference-aligned control, and a novel guidance method, reference control guidance, steers the generation process for better control adherence. By training on a facial video dataset, we fully utilize FaceNet's rich representations while ensuring control adherence. Extensive experiments demonstrate ControlFace's superior performance in identity preservation and control precision, highlighting its practicality. Please see the project website: https://cvlab-kaist.github.io/ControlFace/.
Authors: Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou, Yi-Zhe Song
Abstract: We introduce NitroFusion, a fundamentally different approach to single-step diffusion that achieves high-quality generation through a dynamic adversarial framework. While one-step methods offer dramatic speed advantages, they typically suffer from quality degradation compared to their multi-step counterparts. Just as a panel of art critics provides comprehensive feedback by specializing in different aspects like composition, color, and technique, our approach maintains a large pool of specialized discriminator heads that collectively guide the generation process. Each discriminator group develops expertise in specific quality aspects at different noise levels, providing diverse feedback that enables high-fidelity one-step generation. Our framework combines: (i) a dynamic discriminator pool with specialized discriminator groups to improve generation quality, (ii) strategic refresh mechanisms to prevent discriminator overfitting, and (iii) global-local discriminator heads for multi-scale quality assessment, and unconditional/conditional training for balanced generation. Additionally, our framework uniquely supports flexible deployment through bottom-up refinement, allowing users to dynamically choose between 1-4 denoising steps with the same model for direct quality-speed trade-offs. Through comprehensive experiments, we demonstrate that NitroFusion significantly outperforms existing single-step methods across multiple evaluation metrics, particularly excelling in preserving fine details and global consistency.
Authors: Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood, Karthik Nandakumar, Naveed Akhtar
Abstract: Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps. This paper introduces GenMix, a generalizable prompt-guided generative data augmentation approach that enhances both in-domain and cross-domain image classification. Our technique leverages image editing to generate augmented images based on custom conditional prompts, designed specifically for each problem type. By blending portions of the input image with its edited generative counterpart and incorporating fractal patterns, our approach mitigates unrealistic images and label ambiguity, improving the performance and adversarial robustness of the resulting models. Efficacy of our method is established with extensive experiments on eight public datasets for general and fine-grained classification, in both in-domain and cross-domain settings. Additionally, we demonstrate performance improvements for self-supervised learning, learning with data scarcity, and adversarial robustness. As compared to the existing state-of-the-art methods, our technique achieves stronger performance across the board.
Authors: Jin Hu, Mingjia Li, Xiaojie Guo
Abstract: Shadows introduce challenges such as reduced brightness, texture deterioration, and color distortion in images, complicating a holistic solution. This study presents ShadowHack, a divide-and-conquer strategy that tackles these complexities by decomposing the original task into luminance recovery and color remedy. To brighten shadow regions and repair the corrupted textures in the luminance space, we customize LRNet, a U-shaped network with a rectified outreach attention module, to enhance information interaction and recalibrate contaminated attention maps. With luminance recovered, CRNet then leverages cross-attention mechanisms to revive vibrant colors, producing visually compelling results. Extensive experiments on multiple datasets are conducted to demonstrate the superiority of ShadowHack over existing state-of-the-art solutions both quantitatively and qualitatively, highlighting the effectiveness of our design. Our code will be made publicly available at https://github.com/lime-j/ShadowHack
Authors: Joongwon Chae, Zhenyu Wang, Peiwu Qin
Abstract: Despite significant advances in vision-language understanding, implementing image segmentation within multimodal architectures remains a fundamental challenge in modern artificial intelligence systems. Existing vision-language models, which primarily rely on backbone architectures or CLIP-based embedding learning, demonstrate inherent limitations in fine-grained spatial localization and operational capabilities. This paper introduces SJTU: Spatial Judgments in Multimodal Models - Towards Unified Segmentation through Coordinate Detection, a framework that leverages spatial coordinate understanding to bridge vision-language interaction and precise segmentation, enabling accurate target identification through natural language instructions. The framework presents an approach for integrating segmentation techniques with vision-language models through spatial inference in multimodal space. By utilizing normalized coordinate detection for bounding boxes and transforming them into actionable segmentation outputs, we establish a connection between spatial and language representations in multimodal architectures. Experimental results demonstrate superior performance across benchmark datasets, achieving IoU scores of 0.5958 on COCO 2017 and 0.6758 on Pascal VOC. Testing on a single NVIDIA RTX 3090 GPU with 512x512 resolution images yields an average inference time of 7 seconds per image, demonstrating the framework's effectiveness in both accuracy and practical deployability. The project code is available at https://github.com/jw-chae/SJTU
Authors: Trung-Anh Dang, Vincent Nguyen, Ngoc-Son Vu, Christel Vrain
Abstract: Contrastive learning has significantly improved representation quality, enhancing knowledge transfer across tasks in continual learning (CL). However, catastrophic forgetting remains a key challenge, as contrastive based methods primarily focus on "soft relationships" or "softness" between samples, which shift with changing data distributions and lead to representation overlap across tasks. Recently, the newly identified Neural Collapse phenomenon has shown promise in CL by focusing on "hard relationships" or "hardness" between samples and fixed prototypes. However, this approach overlooks "softness", crucial for capturing intra-class variability, and this rigid focus can also pull old class representations toward current ones, increasing forgetting. Building on these insights, we propose Focal Neural Collapse Contrastive (FNC^2), a novel representation learning loss that effectively balances both soft and hard relationships. Additionally, we introduce the Hardness-Softness Distillation (HSD) loss to progressively preserve the knowledge gained from these relationships across tasks. Our method outperforms state-of-the-art approaches, particularly in minimizing memory reliance. Remarkably, even without the use of memory, our approach rivals rehearsal-based methods, offering a compelling solution for data privacy concerns.
Authors: Alin Dondera, Anuj Singh, Hadi Jamali-Rad
Abstract: Masked Autoencoders (MAEs) are an important divide in self-supervised learning (SSL) due to their independence from augmentation techniques for generating positive (and/or negative) pairs as in contrastive frameworks. Their masking and reconstruction strategy also nicely aligns with SSL approaches in natural language processing. Most MAEs are built upon Transformer-based architectures where visual features are not regularized as opposed to their convolutional neural network (CNN) based counterparts, which can potentially hinder their performance. To address this, we introduce MAGMA, a novel batch-wide layer-wise regularization loss applied to representations of different Transformer layers. We demonstrate that by plugging in the proposed regularization loss, one can significantly improve the performance of MAE-based models. We further demonstrate the impact of the proposed loss on optimizing other generic SSL approaches (such as VICReg and SimCLR), broadening the impact of the proposed approach. Our code base can be found at https://github.com/adondera/magma.
Authors: Xiaohe Ma, Valentin Deschaintre, Milo\v{s} Ha\v{s}an, Fujun Luan, Kun Zhou, Hongzhi Wu, Yiwei Hu
Abstract: High-quality material generation is key for virtual environment authoring and inverse rendering. We propose MaterialPicker, a multi-modal material generator leveraging a Diffusion Transformer (DiT) architecture, improving and simplifying the creation of high-quality materials from text prompts and/or photographs. Our method can generate a material based on an image crop of a material sample, even if the captured surface is distorted, viewed at an angle or partially occluded, as is often the case in photographs of natural scenes. We further allow the user to specify a text prompt to provide additional guidance for the generation. We finetune a pre-trained DiT-based video generator into a material generator, where each material map is treated as a frame in a video sequence. We evaluate our approach both quantitatively and qualitatively and show that it enables more diverse material generation and better distortion correction than previous work.
Authors: Lingen Li, Zhaoyang Zhang, Yaowei Li, Jiale Xu, Wenbo Hu, Xiaoyu Li, Weihao Cheng, Jinwei Gu, Tianfan Xue, Ying Shan
Abstract: Recent advancements in generative models have significantly improved novel view synthesis (NVS) from multi-view data. However, existing methods depend on external multi-view alignment processes, such as explicit pose estimation or pre-reconstruction, which limits their flexibility and accessibility, especially when alignment is unstable due to insufficient overlap or occlusions between views. In this paper, we propose NVComposer, a novel approach that eliminates the need for explicit external alignment. NVComposer enables the generative model to implicitly infer spatial and geometric relationships between multiple conditional views by introducing two key components: 1) an image-pose dual-stream diffusion model that simultaneously generates target novel views and condition camera poses, and 2) a geometry-aware feature alignment module that distills geometric priors from dense stereo models during training. Extensive experiments demonstrate that NVComposer achieves state-of-the-art performance in generative multi-view NVS tasks, removing the reliance on external alignment and thus improving model accessibility. Our approach shows substantial improvements in synthesis quality as the number of unposed input views increases, highlighting its potential for more flexible and accessible generative NVS systems. Our project page is available at https://lg-li.github.io/project/nvcomposer
Authors: Weijie Kong (refer to the report for detailed contributions), Qi Tian (refer to the report for detailed contributions), Zijian Zhang (refer to the report for detailed contributions), Rox Min (refer to the report for detailed contributions), Zuozhuo Dai (refer to the report for detailed contributions), Jin Zhou (refer to the report for detailed contributions), Jiangfeng Xiong (refer to the report for detailed contributions), Xin Li (refer to the report for detailed contributions), Bo Wu (refer to the report for detailed contributions), Jianwei Zhang (refer to the report for detailed contributions), Kathrina Wu (refer to the report for detailed contributions), Qin Lin (refer to the report for detailed contributions), Junkun Yuan (refer to the report for detailed contributions), Yanxin Long (refer to the report for detailed contributions), Aladdin Wang (refer to the report for detailed contributions), Andong Wang (refer to the report for detailed contributions), Changlin Li (refer to the report for detailed contributions), Duojun Huang (refer to the report for detailed contributions), Fang Yang (refer to the report for detailed contributions), Hao Tan (refer to the report for detailed contributions), Hongmei Wang (refer to the report for detailed contributions), Jacob Song (refer to the report for detailed contributions), Jiawang Bai (refer to the report for detailed contributions), Jianbing Wu (refer to the report for detailed contributions), Jinbao Xue (refer to the report for detailed contributions), Joey Wang (refer to the report for detailed contributions), Kai Wang (refer to the report for detailed contributions), Mengyang Liu (refer to the report for detailed contributions), Pengyu Li (refer to the report for detailed contributions), Shuai Li (refer to the report for detailed contributions), Weiyan Wang (refer to the report for detailed contributions), Wenqing Yu (refer to the report for detailed contributions), Xinchi Deng (refer to the report for detailed contributions), Yang Li (refer to the report for detailed contributions), Yi Chen (refer to the report for detailed contributions), Yutao Cui (refer to the report for detailed contributions), Yuanbo Peng (refer to the report for detailed contributions), Zhentao Yu (refer to the report for detailed contributions), Zhiyu He (refer to the report for detailed contributions), Zhiyong Xu (refer to the report for detailed contributions), Zixiang Zhou (refer to the report for detailed contributions), Zunnan Xu (refer to the report for detailed contributions), Yangyu Tao (refer to the report for detailed contributions), Qinglin Lu (refer to the report for detailed contributions), Songtao Liu (refer to the report for detailed contributions), Daquan Zhou (refer to the report for detailed contributions), Hongfa Wang (refer to the report for detailed contributions), Yong Yang (refer to the report for detailed contributions), Di Wang (refer to the report for detailed contributions), Yuhong Liu (refer to the report for detailed contributions), Jie Jiang (refer to the report for detailed contributions), Caesar Zhong (refer to the report for detailed contributions)
Abstract: Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at https://github.com/Tencent/HunyuanVideo.
Authors: Xiyao Wang, Zhengyuan Yang, Linjie Li, Hongjin Lu, Yuancheng Xu, Chung-Ching Lin, Kevin Lin, Furong Huang, Lijuan Wang
Abstract: Despite significant advancements in vision-language models (VLMs), there lacks effective approaches to enhance response quality by scaling inference-time computation. This capability is known to be a core step towards the self-improving models in recent large language model studies. In this paper, we present Vision Value Model (VisVM) that can guide VLM inference-time search to generate responses with better visual comprehension. Specifically, VisVM not only evaluates the generated sentence quality in the current search step, but also anticipates the quality of subsequent sentences that may result from the current step, thus providing a long-term value. In this way, VisVM steers VLMs away from generating sentences prone to hallucinations or insufficient detail, thereby producing higher quality responses. Experimental results demonstrate that VisVM-guided search significantly enhances VLMs' ability to generate descriptive captions with richer visual details and fewer hallucinations, compared with greedy decoding and search methods with other visual reward signals. Furthermore, we find that self-training the model with the VisVM-guided captions improve VLM's performance across a wide range of multimodal benchmarks, indicating the potential for developing self-improving VLMs. Our value model and code are available at https://github.com/si0wang/VisVM.
Authors: Nefeli Andreou, Varsha Vivek, Ying Wang, Alex Vorobiov, Tiffany Deng, Raja Bala, Larry Davis, Betty Mohler Tesch
Abstract: Accurately generating images of human bodies from text remains a challenging problem for state of the art text-to-image models. Commonly observed body-related artifacts include extra or missing limbs, unrealistic poses, blurred body parts, etc. Currently, evaluation of such artifacts relies heavily on time-consuming human judgments, limiting the ability to benchmark models at scale. We address this by proposing BodyMetric, a learnable metric that predicts body realism in images. BodyMetric is trained on realism labels and multi-modal signals including 3D body representations inferred from the input image, and textual descriptions. In order to facilitate this approach, we design an annotation pipeline to collect expert ratings on human body realism leading to a new dataset for this task, namely, BodyRealism. Ablation studies support our architectural choices for BodyMetric and the importance of leveraging a 3D human body prior in capturing body-related artifacts in 2D images. In comparison to concurrent metrics which evaluate general user preference in images, BodyMetric specifically reflects body-related artifacts. We demonstrate the utility of BodyMetric through applications that were previously infeasible at scale. In particular, we use BodyMetric to benchmark the generation ability of text-to-image models to produce realistic human bodies. We also demonstrate the effectiveness of BodyMetric in ranking generated images based on the predicted realism scores.
Authors: Jiahao Zhang, Ryota Yoshihashi, Shunsuke Kitada, Atsuki Osanai, Yuta Nakashima
Abstract: Large language models (LLMs) have proven effective for layout generation due to their ability to produce structure-description languages, such as HTML or JSON, even without access to visual information. Recently, LLM providers have evolved these models into large vision-language models (LVLM), which shows prominent multi-modal understanding capabilities. Then, how can we leverage this multi-modal power for layout generation? To answer this, we propose Visual-Aware Self-Correction LAyout GeneRation (VASCAR) for LVLM-based content-aware layout generation. In our method, LVLMs iteratively refine their outputs with reference to rendered layout images, which are visualized as colored bounding boxes on poster backgrounds. In experiments, we demonstrate that our method combined with the Gemini. Without any additional training, VASCAR achieves state-of-the-art (SOTA) layout generation quality outperforming both existing layout-specific generative models and other LLM-based methods.
Authors: Yuqi Wu, Wenzhao Zheng, Sicheng Zuo, Yuanhui Huang, Jie Zhou, Jiwen Lu
Abstract: 3D occupancy prediction provides a comprehensive description of the surrounding scenes and has become an essential task for 3D perception. Most existing methods focus on offline perception from one or a few views and cannot be applied to embodied agents which demands to gradually perceive the scene through progressive embodied exploration. In this paper, we formulate an embodied 3D occupancy prediction task to target this practical scenario and propose a Gaussian-based EmbodiedOcc framework to accomplish it. We initialize the global scene with uniform 3D semantic Gaussians and progressively update local regions observed by the embodied agent. For each update, we extract semantic and structural features from the observed image and efficiently incorporate them via deformable cross-attention to refine the regional Gaussians. Finally, we employ Gaussian-to-voxel splatting to obtain the global 3D occupancy from the updated 3D Gaussians. Our EmbodiedOcc assumes an unknown (i.e., uniformly distributed) environment and maintains an explicit global memory of it with 3D Gaussians. It gradually gains knowledge through the local refinement of regional Gaussians, which is consistent with how humans understand new scenes through embodied exploration. We reorganize an EmbodiedOcc-ScanNet benchmark based on local annotations to facilitate the evaluation of the embodied 3D occupancy prediction task. Experiments demonstrate that our EmbodiedOcc outperforms existing local prediction methods and accomplishes the embodied occupancy prediction with high accuracy and strong expandability. Code: https://github.com/YkiWu/EmbodiedOcc.
Authors: Yuanhui Huang, Amonnut Thammatadatrakoon, Wenzhao Zheng, Yunpeng Zhang, Dalong Du, Jiwen Lu
Abstract: 3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving, which predicts fine-grained geometry and semantics of the surrounding scene. Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes. Although 3D semantic Gaussian serves as an object-centric sparse alternative, most of the Gaussians still describe the empty region with low efficiency. To address this, we propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its neighborhood being occupied and conforms to probabilistic multiplication to derive the overall geometry. Furthermore, we adopt the exact Gaussian mixture model for semantics calculation to avoid unnecessary overlapping of Gaussians. To effectively initialize Gaussians in non-empty region, we design a distribution-based initialization module which learns the pixel-aligned occupancy distribution instead of the depth of surfaces. We conduct extensive experiments on nuScenes and KITTI-360 datasets and our GaussianFormer-2 achieves state-of-the-art performance with high efficiency. Code: https://github.com/huang-yh/GaussianFormer.
Authors: Ryan Feng, Neal Mangaokar, Jihye Choi, Somesh Jha, Atul Prakash
Abstract: Patch attacks against object detectors have been of recent interest due to their being physically realizable and more closely aligned with practical systems. In response to this threat, many new defenses have been proposed that train a patch segmenter model to detect and remove the patch before the image is passed to the downstream model. We unify these approaches with a flexible framework, OODSmoother, which characterizes the properties of approaches that aim to remove adversarial patches. This framework naturally guides us to design 1) a novel adaptive attack that breaks existing patch attack defenses on object detectors, and 2) a novel defense approach SemPrior that takes advantage of semantic priors. Our key insight behind SemPrior is that the existing machine learning-based patch detectors struggle to learn semantic priors and that explicitly incorporating them can improve performance. We find that SemPrior alone provides up to a 40% gain, or up to a 60% gain when combined with existing defenses.
Authors: Ruihan Yang, Yejin Kim, Rose Hendrix, Aniruddha Kembhavi, Xiaolong Wang, Kiana Ehsani
Abstract: Recent advancements in robotics have enabled robots to navigate complex scenes or manipulate diverse objects independently. However, robots are still impotent in many household tasks requiring coordinated behaviors such as opening doors. The factorization of navigation and manipulation, while effective for some tasks, fails in scenarios requiring coordinated actions. To address this challenge, we introduce, HarmonicMM, an end-to-end learning method that optimizes both navigation and manipulation, showing notable improvement over existing techniques in everyday tasks. This approach is validated in simulated and real-world environments and adapts to novel unseen settings without additional tuning. Our contributions include a new benchmark for mobile manipulation and the successful deployment with only RGB visual observation in a real unseen apartment, demonstrating the potential for practical indoor robot deployment in daily life. More results are on our project site: https://rchalyang.github.io/HarmonicMM/
Authors: Hiroki Waida, Kimihiro Yamazaki, Atsushi Tokuhisa, Mutsuyo Wada, Yuichiro Wada
Abstract: Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data is lacking. To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments. Through the theoretical analysis, we discuss that the algorithm finds desired solutions to the optimization problem with the population risk, while the guarantee for the empirical risk depends on the hardness of the denoising task in terms of denaturation levels. We also conduct several experiments to investigate the performance of an extended algorithm in practice. The results indicate that the algorithm training with denatured images works, and the empirical performance aligns with the theoretical results. These results suggest several insights for further improvement of self-supervised image denoising that uses denatured data in future directions.
Authors: Kleanthis Marios Papadopoulos, Tania Stathaki
Abstract: The abundance of information present in Whole Slide Images (WSIs) renders them an essential tool for survival analysis. Several Multiple Instance Learning frameworks proposed for this task utilize a ResNet50 backbone pre-trained on natural images. By leveraging recenetly released histopathological foundation models such as UNI and Hibou, the predictive prowess of existing MIL networks can be enhanced. Furthermore, deploying an ensemble of digital pathology foundation models yields higher baseline accuracy, although the benefits appear to diminish with more complex MIL architectures. Our code will be made publicly available upon acceptance.
Authors: Jordan Madden, Moxanki Bhavsar, Lhamo Dorje, Xiaohua Li
Abstract: Perceptual hashing algorithms (PHAs) are widely used for identifying illegal online content and are thus integral to various sensitive applications. However, due to their hasty deployment in real-world scenarios, their adversarial security has not been thoroughly evaluated. This paper assesses the security of three widely utilized PHAs - PhotoDNA, PDQ, and NeuralHash - against hash-evasion and hash-inversion attacks. Contrary to existing literature, our findings indicate that these PHAs demonstrate significant robustness against such attacks. We provide an explanation for these differing results, highlighting that the inherent robustness is partially due to the random hash variations characteristic of PHAs. Additionally, we propose a defense method that enhances security by intentionally introducing perturbations into the hashes.
Authors: Pablo Arratia, Matthias Ehrhardt, Lisa Kreusser
Abstract: In this paper, we investigate image reconstruction for dynamic Computed Tomography. The motion of the target with respect to the measurement acquisition rate leads to highly resolved in time but highly undersampled in space measurements. Such problems pose a major challenge: not accounting for the dynamics of the process leads to a poor reconstruction with non-realistic motion. Variational approaches that penalize time evolution have been proposed to relate subsequent frames and improve image quality based on classical grid-based discretizations. Neural fields have emerged as a novel way to parameterize the quantity of interest using a neural network with a low-dimensional input, benefiting from being lightweight, continuous, and biased towards smooth representations. The latter property has been exploited when solving dynamic inverse problems with neural fields by minimizing a data-fidelity term only. We investigate and show the benefits of introducing explicit motion regularizers for dynamic inverse problems based on partial differential equations, namely, the optical flow equation, for the optimization of neural fields. We compare it against its unregularized counterpart and show the improvements in the reconstruction. We also compare neural fields against a grid-based solver and show that the former outperforms the latter in terms of PSNR in this task.
Authors: Yichi Zhang, Yao Huang, Yitong Sun, Chang Liu, Zhe Zhao, Zhengwei Fang, Yifan Wang, Huanran Chen, Xiao Yang, Xingxing Wei, Hang Su, Yinpeng Dong, Jun Zhu
Abstract: Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited, lacking a holistic evaluation to offer thorough insights into future improvements. In this work, we establish MultiTrust, the first comprehensive and unified benchmark on the trustworthiness of MLLMs across five primary aspects: truthfulness, safety, robustness, fairness, and privacy. Our benchmark employs a rigorous evaluation strategy that addresses both multimodal risks and cross-modal impacts, encompassing 32 diverse tasks with self-curated datasets. Extensive experiments with 21 modern MLLMs reveal some previously unexplored trustworthiness issues and risks, highlighting the complexities introduced by the multimodality and underscoring the necessity for advanced methodologies to enhance their reliability. For instance, typical proprietary models still struggle with the perception of visually confusing images and are vulnerable to multimodal jailbreaking and adversarial attacks; MLLMs are more inclined to disclose privacy in text and reveal ideological and cultural biases even when paired with irrelevant images in inference, indicating that the multimodality amplifies the internal risks from base LLMs. Additionally, we release a scalable toolbox for standardized trustworthiness research, aiming to facilitate future advancements in this important field. Code and resources are publicly available at: https://multi-trust.github.io/.
Authors: Ivana Kaji\'c, Olivia Wiles, Isabela Albuquerque, Matthias Bauer, Su Wang, Jordi Pont-Tuset, Aida Nematzadeh
Abstract: Text-to-image generative models are capable of producing high-quality images that often faithfully depict concepts described using natural language. In this work, we comprehensively evaluate a range of text-to-image models on numerical reasoning tasks of varying difficulty, and show that even the most advanced models have only rudimentary numerical skills. Specifically, their ability to correctly generate an exact number of objects in an image is limited to small numbers, it is highly dependent on the context the number term appears in, and it deteriorates quickly with each successive number. We also demonstrate that models have poor understanding of linguistic quantifiers (such as "a few" or "as many as"), the concept of zero, and struggle with more advanced concepts such as partial quantities and fractional representations. We bundle prompts, generated images and human annotations into GeckoNum, a novel benchmark for evaluation of numerical reasoning.
Authors: Anoop Cherian, Kuan-Chuan Peng, Suhas Lohit, Joanna Matthiesen, Kevin Smith, Joshua B. Tenenbaum
Abstract: Recent years have seen a significant progress in the general-purpose problem solving abilities of large vision and language models (LVLMs), such as ChatGPT, Gemini, etc.; some of these breakthroughs even seem to enable AI models to outperform human abilities in varied tasks that demand higher-order cognitive skills. Are the current large AI models indeed capable of generalized problem solving as humans do? A systematic analysis of AI capabilities for joint vision and text reasoning, however, is missing in the current scientific literature. In this paper, we make an effort towards filling this gap, by evaluating state-of-the-art LVLMs on their mathematical and algorithmic reasoning abilities using visuo-linguistic problems from children's Olympiads. Specifically, we consider problems from the Mathematical Kangaroo (MK) Olympiad, which is a popular international competition targeted at children from grades 1-12, that tests children's deeper mathematical abilities using puzzles that are appropriately gauged to their age and skills. Using the puzzles from MK, we created a dataset, dubbed SMART-840, consisting of 840 problems from years 2020-2024. With our dataset, we analyze LVLMs power on mathematical reasoning; their responses on our puzzles offer a direct way to compare against that of children. Our results show that modern LVLMs do demonstrate increasingly powerful reasoning skills in solving problems for higher grades, but lack the foundations to correctly answer problems designed for younger children. Further analysis shows that there is no significant correlation between the reasoning capabilities of AI models and that of young children, and their capabilities appear to be based on a different type of reasoning than the cumulative knowledge that underlies children's mathematics and logic skills.
Authors: Pandiyaraju V, Shravan Venkatraman, Abeshek A, Pavan Kumar S, Aravintakshan S A
Abstract: Alzheimer's disease (AD) is the most common neurodegeneration, annually diagnosed in millions of patients. The present medicine scenario still finds challenges in the exact diagnosis and classification of AD through neuroimaging data. Traditional CNNs can extract a good amount of low-level information in an image but fail to extract high-level minuscule particles, which is a significant challenge in detecting AD from MRI scans. To overcome this, we propose a novel Granular Feature Integration method to combine information extraction at different scales combined with an efficient information flow, enabling the model to capture both broad and fine-grained features simultaneously. We also propose a Bi-Focal Perspective mechanism to highlight the subtle neurofibrillary tangles and amyloid plaques in the MRI scans, ensuring that critical pathological markers are accurately identified. Our model achieved an F1-Score of 99.31%, precision of 99.24%, and recall of 99.51%. These scores prove that our model is significantly better than the state-of-the-art (SOTA) CNNs in existence.
Authors: Nikolaos Livathinos, Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Kasper Dinkla, Yusik Kim, Shubham Gupta, Rafael Teixeira de Lima, Valery Weber, Lucas Morin, Ingmar Meijer, Viktor Kuropiatnyk, Peter W. J. Staar
Abstract: We introduce Docling, an easy-to-use, self-contained, MIT-licensed, open-source toolkit for document conversion, that can parse several types of popular document formats into a unified, richly structured representation. It is powered by state-of-the-art specialized AI models for layout analysis (DocLayNet) and table structure recognition (TableFormer), and runs efficiently on commodity hardware in a small resource budget. Docling is released as a Python package and can be used as a Python API or as a CLI tool. Docling's modular architecture and efficient document representation %, known as DoclingDocument, make it easy to implement extensions, new features, models, and customizations. Docling has been already integrated in other popular open-source frameworks (e.g., LlamaIndex, LangChain, spaCy), making it a natural fit for the processing of documents and the development of high-end applications. The open-source community has fully engaged in using, promoting, and developing for Docling, which gathered 10k stars on GitHub in less than a month and was reported as the No. 1 trending repository in GitHub worldwide in November 2024.
Authors: Rong Zhou, Zhengqing Yuan, Zhiling Yan, Weixiang Sun, Kai Zhang, Yiwei Li, Yanfang Ye, Xiang Li, Lifang He, Lichao Sun
Abstract: Biomedical image segmentation is crucial for accurately diagnosing and analyzing various diseases. However, Convolutional Neural Networks (CNNs) and Transformers, the most commonly used architectures for this task, struggle to effectively capture long-range dependencies due to the inherent locality of CNNs and the computational complexity of Transformers. To address this limitation, we introduce TTT-Unet, a novel framework that integrates Test-Time Training (TTT) layers into the traditional U-Net architecture for biomedical image segmentation. TTT-Unet dynamically adjusts model parameters during the testing time, enhancing the model's ability to capture both local and long-range features. We evaluate TTT-Unet on multiple medical imaging datasets, including 3D abdominal organ segmentation in CT and MR images, instrument segmentation in endoscopy images, and cell segmentation in microscopy images. The results demonstrate that TTT-Unet consistently outperforms state-of-the-art CNN-based and Transformer-based segmentation models across all tasks. The code is available at https://github.com/rongzhou7/TTT-Unet.
Authors: Houze Liu, Tong Zhou, Yanlin Xiang, Aoran Shen, Jiacheng Hu, Junliang Du
Abstract: Medical image segmentation is crucial for accurate clinical diagnoses, yet it faces challenges such as low contrast between lesions and normal tissues, unclear boundaries, and high variability across patients. Deep learning has improved segmentation accuracy and efficiency, but it still relies heavily on expert annotations and struggles with the complexities of medical images. The small size of medical image datasets and the high cost of data acquisition further limit the performance of segmentation networks. Diffusion models, with their iterative denoising process, offer a promising alternative for better detail capture in segmentation. However, they face difficulties in accurately segmenting small targets and maintaining the precision of boundary details. This article discusses the importance of medical image segmentation, the limitations of current deep learning approaches, and the potential of diffusion models to address these challenges.
Authors: Ching-Yi Wang
Abstract: Multi-modal large language models (MLLMs), such as GPT-4o, excel at integrating text and visual data but face systematic challenges when interpreting ambiguous or incomplete visual stimuli. This study leverages statistical modeling to analyze the factors driving these errors, using a dataset of geometric stimuli characterized by features like 3D, rotation, and missing face/side. We applied parametric methods, non-parametric methods, and ensemble techniques to predict classification errors, with the non-linear gradient boosting model achieving the highest performance (AUC=0.85) during cross-validation. Feature importance analysis highlighted difficulties in depth perception and reconstructing incomplete structures as key contributors to misclassification. These findings demonstrate the effectiveness of statistical approaches for uncovering limitations in MLLMs and offer actionable insights for enhancing model architectures by integrating contextual reasoning mechanisms.
Authors: Genki Osada, Makoto Shing, Takashi Nishide
Abstract: The training of score-based diffusion models (SDMs) is based on score matching. The challenge of score matching is that it includes a computationally expensive Jacobian trace. While several methods have been proposed to avoid this computation, each has drawbacks, such as instability during training and approximating the learning as learning a denoising vector field rather than a true score. We propose a novel score matching variant, local curvature smoothing with Stein's identity (LCSS). The LCSS bypasses the Jacobian trace by applying Stein's identity, enabling regularization effectiveness and efficient computation. We show that LCSS surpasses existing methods in sample generation performance and matches the performance of denoising score matching, widely adopted by most SDMs, in evaluations such as FID, Inception score, and bits per dimension. Furthermore, we show that LCSS enables realistic image generation even at a high resolution of $1024 \times 1024$.