Authors: Zhikai Li, Jing Zhang, Qingyi Gu
Abstract: The disparity in healthcare personnel expertise and medical resources across different regions of the world is a pressing social issue. Artificial intelligence technology offers new opportunities to alleviate this issue. Segment Anything Model (SAM), which excels in intelligent image segmentation, has demonstrated exceptional performance in medical monitoring and assisted diagnosis. Unfortunately, the huge computational and storage overhead of SAM poses significant challenges for deployment on resource-limited edge devices. Quantization is an effective solution for model compression; however, traditional methods rely heavily on original data for calibration, which raises widespread concerns about medical data privacy and security. In this paper, we propose a data-free quantization framework for SAM, called DFQ-SAM, which learns and calibrates quantization parameters without any original data, thus effectively preserving data privacy during model compression. Specifically, we propose pseudo-positive label evolution for segmentation, combined with patch similarity, to fully leverage the semantic and distribution priors in pre-trained models, which facilitates high-quality data synthesis as a substitute for real data. Furthermore, we introduce scale reparameterization to ensure the accuracy of low-bit quantization. We perform extensive segmentation experiments on various datasets, and DFQ-SAM consistently provides significant performance on low-bit quantization. DFQ-SAM eliminates the need for data transfer in cloud-edge collaboration, thereby protecting sensitive data from potential attacks. It enables secure, fast, and personalized healthcare services at the edge, which enhances system efficiency and optimizes resource allocation, and thus facilitating the pervasive application of artificial intelligence in worldwide healthcare.
Authors: Awal Ahmed Fime, Saifuddin Mahmud, Arpita Das, Md. Sunzidul Islam, Hong-Hoon Kim
Abstract: Automatic scene generation is an essential area of research with applications in robotics, recreation, visual representation, training and simulation, education, and more. This survey provides a comprehensive review of the current state-of-the-arts in automatic scene generation, focusing on techniques that leverage machine learning, deep learning, embedded systems, and natural language processing (NLP). We categorize the models into four main types: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Transformers, and Diffusion Models. Each category is explored in detail, discussing various sub-models and their contributions to the field. We also review the most commonly used datasets, such as COCO-Stuff, Visual Genome, and MS-COCO, which are critical for training and evaluating these models. Methodologies for scene generation are examined, including image-to-3D conversion, text-to-3D generation, UI/layout design, graph-based methods, and interactive scene generation. Evaluation metrics such as Frechet Inception Distance (FID), Kullback-Leibler (KL) Divergence, Inception Score (IS), Intersection over Union (IoU), and Mean Average Precision (mAP) are discussed in the context of their use in assessing model performance. The survey identifies key challenges and limitations in the field, such as maintaining realism, handling complex scenes with multiple objects, and ensuring consistency in object relationships and spatial arrangements. By summarizing recent advances and pinpointing areas for improvement, this survey aims to provide a valuable resource for researchers and practitioners working on automatic scene generation.
Authors: Tanusree Sharma, Yujin Potter, Zachary Kilhoffer, Yun Huang, Dawn Song, Yang Wang
Abstract: This paper examines the governance of multimodal large language models (MM-LLMs) through individual and collective deliberation, focusing on analyses of politically sensitive videos. We conducted a two-step study: first, interviews with 10 journalists established a baseline understanding of expert video interpretation; second, 114 individuals from the general public engaged in deliberation using Inclusive.AI, a platform that facilitates democratic decision-making through decentralized autonomous organization (DAO) mechanisms. Our findings show that while experts emphasized emotion and narrative, the general public prioritized factual clarity, objectivity of the situation, and emotional neutrality. Additionally, we explored the impact of different governance mechanisms: quadratic vs. weighted ranking voting and equal vs. 20-80 power distributions on users decision-making on how AI should behave. Specifically, quadratic voting enhanced perceptions of liberal democracy and political equality, and participants who were more optimistic about AI perceived the voting process to have a higher level of participatory democracy. Our results suggest the potential of applying DAO mechanisms to help democratize AI governance.
Authors: Fabien Furfaro
Abstract: This report introduces PixelBytes, a novel approach for unified multimodal representation learning. Inspired by existing sequence models such as Image Transformers, PixelCNN, and Mamba-Bytes, our method aims to capture diverse inputs in a cohesive representation, exploring the integration of different data types, particularly text, audio, and pixelated images (sprites). We conducted experiments on a specialized PixelBytes Pok{\'e}mon dataset. Initially, we investigated various model architectures, including Recurrent Neural Networks (RNNs), State Space Models (SSMs), and Attention-based models, focusing on bidirectional processing and our convolutional PxBy embedding technique. Subsequently, we evaluated models based on data reduction strategies and the effectiveness of autoregressive learning. We specifically examined Long Short-Term Memory (LSTM) networks in both predictive and autoregressive modes for our main experiments. Our findings suggest that autoregressive models outperform predictive models in this context. By adopting a flexible approach to multimodal modeling, PixelBytes contributes to the ongoing development of foundation models capable of understanding and generating multimodal data. The complete PixelBytes project, including code, models, and datasets, is available online.
Authors: Biplov Paneru, Bishwash Paneru, Krishna Bikram Shah
Abstract: This study presents a novel method for improving rice disease classification using 8 different convolutional neural network (CNN) algorithms, which will further the field of precision agriculture. Tkinter-based application that offers farmers a feature-rich interface. With the help of this cutting-edge application, farmers will be able to make timely and well-informed decisions by enabling real-time disease prediction and providing personalized recommendations. Together with the user-friendly Tkinter interface, the smooth integration of cutting-edge CNN transfer learning algorithms-based technology that include ResNet-50, InceptionV3, VGG16, and MobileNetv2 with the UCI dataset represents a major advancement toward modernizing agricultural practices and guaranteeing sustainable crop management. Remarkable outcomes include 75% accuracy for ResNet-50, 90% accuracy for DenseNet121, 84% accuracy for VGG16, 95.83% accuracy for MobileNetV2, 91.61% accuracy for DenseNet169, and 86% accuracy for InceptionV3. These results give a concise summary of the models' capabilities, assisting researchers in choosing appropriate strategies for precise and successful rice crop disease identification. A severe overfitting has been seen on VGG19 with 70% accuracy and Nasnet with 80.02% accuracy. On Renset101, only an accuracy of 54% could be achieved, along with only 33% on efficientNetB0. A MobileNetV2-trained model was successfully deployed on a TKinter GUI application to make predictions using image or real-time video capture.
Authors: Jianchun Chen, Jian Wang, Yinda Zhang, Rohit Pandey, Thabo Beeler, Marc Habermann, Christian Theobalt
Abstract: Immersive VR telepresence ideally means being able to interact and communicate with digital avatars that are indistinguishable from and precisely reflect the behaviour of their real counterparts. The core technical challenge is two fold: Creating a digital double that faithfully reflects the real human and tracking the real human solely from egocentric sensing devices that are lightweight and have a low energy consumption, e.g. a single RGB camera. Up to date, no unified solution to this problem exists as recent works solely focus on egocentric motion capture, only model the head, or build avatars from multi-view captures. In this work, we, for the first time in literature, propose a person-specific egocentric telepresence approach, which jointly models the photoreal digital avatar while also driving it from a single egocentric video. We first present a character model that is animatible, i.e. can be solely driven by skeletal motion, while being capable of modeling geometry and appearance. Then, we introduce a personalized egocentric motion capture component, which recovers full-body motion from an egocentric video. Finally, we apply the recovered pose to our character model and perform a test-time mesh refinement such that the geometry faithfully projects onto the egocentric view. To validate our design choices, we propose a new and challenging benchmark, which provides paired egocentric and dense multi-view videos of real humans performing various motions. Our experiments demonstrate a clear step towards egocentric and photoreal telepresence as our method outperforms baselines as well as competing methods. For more details, code, and data, we refer to our project page.
Authors: Soufiane Belharbi, Marco Pedersoli, Alessandro Lameiras Koerich, Simon Bacon, Eric Granger
Abstract: Although state-of-the-art classifiers for facial expression recognition (FER) can achieve a high level of accuracy, they lack interpretability, an important feature for end-users. Experts typically associate spatial action units (AUs) from a codebook to facial regions for the visual interpretation of expressions. In this paper, the same expert steps are followed. A new learning strategy is proposed to explicitly incorporate AU cues into classifier training, allowing to train deep interpretable models. During training, this AU codebook is used, along with the input image expression label, and facial landmarks, to construct a AU heatmap that indicates the most discriminative image regions of interest w.r.t the facial expression. This valuable spatial cue is leveraged to train a deep interpretable classifier for FER. This is achieved by constraining the spatial layer features of a classifier to be correlated with AU heatmaps. Using a composite loss, the classifier is trained to correctly classify an image while yielding interpretable visual layer-wise attention correlated with AU maps, simulating the expert decision process. Our strategy only relies on image class expression for supervision, without additional manual annotations. Our new strategy is generic, and can be applied to any deep CNN- or transformer-based classifier without requiring any architectural change or significant additional training time. Our extensive evaluation on two public benchmarks RAF-DB, and AffectNet datasets shows that our proposed strategy can improve layer-wise interpretability without degrading classification performance. In addition, we explore a common type of interpretable classifiers that rely on class activation mapping (CAM) methods, and show that our approach can also improve CAM interpretability.
Authors: Shuxin Yang, Xinhan Di
Abstract: There is a gap in the understanding of occluded objects in existing large-scale visual language multi-modal models. Current state-of-the-art multi-modal models fail to provide satisfactory results in describing occluded objects through universal visual encoders and supervised learning strategies. Therefore, we introduce a multi-modal large language framework and corresponding self-supervised learning strategy with support of 3D generation. We start our experiments comparing with the state-of-the-art models in the evaluation of a large-scale dataset SOMVideo [18]. The initial results demonstrate the improvement of 16.92% in comparison with the state-of-the-art VLM models.
Authors: Aakash Varma Nadimpalli, Ajita Rattani
Abstract: With the significant advances in deep generative models for image and video synthesis, Deepfakes and manipulated media have raised severe societal concerns. Conventional machine learning classifiers for deepfake detection often fail to cope with evolving deepfake generation technology and are susceptible to adversarial attacks. Alternatively, invisible image watermarking is being researched as a proactive defense technique that allows media authentication by verifying an invisible secret message embedded in the image pixels. A handful of invisible image watermarking techniques introduced for media authentication have proven vulnerable to basic image processing operations and watermark removal attacks. In response, we have proposed a semi-fragile image watermarking technique that embeds an invisible secret message into real images for media authentication. Our proposed watermarking framework is designed to be fragile to facial manipulations or tampering while being robust to benign image-processing operations and watermark removal attacks. This is facilitated through a unique architecture of our proposed technique consisting of critic and adversarial networks that enforce high image quality and resiliency to watermark removal efforts, respectively, along with the backbone encoder-decoder and the discriminator networks. Thorough experimental investigations on SOTA facial Deepfake datasets demonstrate that our proposed model can embed a $64$-bit secret as an imperceptible image watermark that can be recovered with a high-bit recovery accuracy when benign image processing operations are applied while being non-recoverable when unseen Deepfake manipulations are applied. In addition, our proposed watermarking technique demonstrates high resilience to several white-box and black-box watermark removal attacks. Thus, obtaining state-of-the-art performance.
Authors: Liang Chen, Sinan Tan, Zefan Cai, Weichu Xie, Haozhe Zhao, Yichi Zhang, Junyang Lin, Jinze Bai, Tianyu Liu, Baobao Chang
Abstract: This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-Transformer predicts more codes for an image by introducing a new autoregression direction, \textit{model depth}, along with the sequence length direction. Compared to traditional 1D autoregression and previous work utilizing similar 2D image decomposition such as RQ-Transformer, the DnD-Transformer is an end-to-end model that can generate higher quality images with the same backbone model size and sequence length, opening a new optimization perspective for autoregressive image generation. Furthermore, our experiments reveal that the DnD-Transformer's potential extends beyond generating natural images. It can even generate images with rich text and graphical elements in a self-supervised manner, demonstrating an understanding of these combined modalities. This has not been previously demonstrated for popular vision generative models such as diffusion models, showing a spark of vision-language intelligence when trained solely on images. Code, datasets and models are open at https://github.com/chenllliang/DnD-Transformer.
Authors: Ganesh Raghavendran (Department of NanoEngineering-University of California San Diego), Bing Han (Department of NanoEngineering-University of California San Diego), Fortune Adekogbe (Department of Chemical and Petroleum Engineering-University of Lagos), Shuang Bai (Department of NanoEngineering-University of California San Diego), Bingyu Lu (Department of NanoEngineering-University of California San Diego), William Wu (Del Norte High School), Minghao Zhang (Department of NanoEngineering-University of California San Diego), Ying Shirley Meng (Department of NanoEngineering-University of California San Diego, Pritzker School of Molecular Engineering-University of Chicago)
Abstract: In the domain of battery research, the processing of high-resolution microscopy images is a challenging task, as it involves dealing with complex images and requires a prior understanding of the components involved. The utilization of deep learning methodologies for image analysis has attracted considerable interest in recent years, with multiple investigations employing such techniques for image segmentation and analysis within the realm of battery research. However, the automated analysis of high-resolution microscopy images for detecting phases and components in composite materials is still an underexplored area. This work proposes a novel workflow for detecting components and phase segmentation from raw high resolution transmission electron microscopy (TEM) images using a trained U-Net segmentation model. The developed model can expedite the detection of components and phase segmentation, diminishing the temporal and cognitive demands associated with scrutinizing an extensive array of TEM images, thereby mitigating the potential for human errors. This approach presents a novel and efficient image analysis approach with broad applicability beyond the battery field and holds potential for application in other related domains characterized by phase and composition distribution, such as alloy production.
Authors: Hao Li, Jiayang Gu, Jingkuan Song, An Zhang, Lianli Gao
Abstract: Mitigating the detrimental effects of noisy labels on the training process has become increasingly critical, as obtaining entirely clean or human-annotated samples for large-scale pre-training tasks is often impractical. Nonetheless, existing noise mitigation methods often encounter limitations in practical applications due to their task-specific design, model dependency, and significant computational overhead. In this work, we exploit the properties of high-dimensional orthogonality to identify a robust and effective boundary in cone space for separating clean and noisy samples. Building on this, we propose One-step Anti-Noise (OSA), a model-agnostic noisy label mitigation paradigm that employs an estimator model and a scoring function to assess the noise level of input pairs through just one-step inference, a cost-efficient process. We empirically demonstrate the superiority of OSA, highlighting its enhanced training robustness, improved task transferability, ease of deployment, and reduced computational costs across various benchmarks, models, and tasks. Our code is released at https://github.com/leolee99/OSA.
Authors: Mohammad Mahdavian, Mohammad Loni, Mo Chen
Abstract: Detecting human actions is a crucial task for autonomous robots and vehicles, often requiring the integration of various data modalities for improved accuracy. In this study, we introduce a novel approach to Human Action Recognition (HAR) based on skeleton and visual cues. Our method leverages a language model to guide the feature extraction process in the skeleton encoder. Specifically, we employ learnable prompts for the language model conditioned on the skeleton modality to optimize feature representation. Furthermore, we propose a fusion mechanism that combines dual-modality features using a salient fusion module, incorporating attention and transformer mechanisms to address the modalities' high dimensionality. This fusion process prioritizes informative video frames and body joints, enhancing the recognition accuracy of human actions. Additionally, we introduce a new dataset tailored for real-world robotic applications in construction sites, featuring visual, skeleton, and depth data modalities, named VolvoConstAct. This dataset serves to facilitate the training and evaluation of machine learning models to instruct autonomous construction machines for performing necessary tasks in the real world construction zones. To evaluate our approach, we conduct experiments on our dataset as well as three widely used public datasets, NTU-RGB+D, NTU-RGB+D120 and NW-UCLA. Results reveal that our proposed method achieves promising performance across all datasets, demonstrating its robustness and potential for various applications. The codes and dataset are available at: https://mmahdavian.github.io/ls_har/
Authors: Xinlong Hou, Sen Shen, Xueshen Li, Xinran Gao, Ziyi Huang, Steven J. Holiday, Matthew R. Cribbet, Susan W. White, Edward Sazonov, Yu Gan
Abstract: Being able to accurately monitor the screen exposure of young children is important for research on phenomena linked to screen use such as childhood obesity, physical activity, and social interaction. Most existing studies rely upon self-report or manual measures from bulky wearable sensors, thus lacking efficiency and accuracy in capturing quantitative screen exposure data. In this work, we developed a novel sensor informatics framework that utilizes egocentric images from a wearable sensor, termed the screen time tracker (STT), and a vision language model (VLM). In particular, we devised a multi-view VLM that takes multiple views from egocentric image sequences and interprets screen exposure dynamically. We validated our approach by using a dataset of children's free-living activities, demonstrating significant improvement over existing methods in plain vision language models and object detection models. Results supported the promise of this monitoring approach, which could optimize behavioral research on screen exposure in children's naturalistic settings.
Authors: Reza Basiri, Ali Abedi, Chau Nguyen, Milos R. Popovic, Shehroz S. Khan
Abstract: Diabetic foot ulcers (DFUs) are a leading cause of hospitalizations and lower limb amputations, placing a substantial burden on patients and healthcare systems. Early detection and accurate classification of DFUs are critical for preventing serious complications, yet many patients experience delays in receiving care due to limited access to specialized services. Telehealth has emerged as a promising solution, improving access to care and reducing the need for in-person visits. The integration of artificial intelligence and pattern recognition into telemedicine has further enhanced DFU management by enabling automatic detection, classification, and monitoring from images. Despite advancements in artificial intelligence-driven approaches for DFU image analysis, the application of large language models for DFU image transcription has not yet been explored. To address this gap, we introduce UlcerGPT, a novel multimodal approach leveraging large language and vision models for DFU image transcription. This framework combines advanced vision and language models, such as Large Language and Vision Assistant and Chat Generative Pre-trained Transformer, to transcribe DFU images by jointly detecting, classifying, and localizing regions of interest. Through detailed experiments on a public dataset, evaluated by expert clinicians, UlcerGPT demonstrates promising results in the accuracy and efficiency of DFU transcription, offering potential support for clinicians in delivering timely care via telemedicine.
Authors: S. Parisa Dajkhosh, Peter M. Le, Orges Furxhi, Eddie L. Jacobs
Abstract: Capturing real-world aerial images for vision-based navigation (VBN) is challenging due to limited availability and conditions that make it nearly impossible to access all desired images from any location. The complexity increases when multiple locations are involved. The state of the art solutions, such as flying a UAV (Unmanned Aerial Vehicle) to take pictures or using existing research databases, have significant limitations. SkyAI Sim offers a compelling alternative by simulating a UAV to capture bird's-eye view satellite images at zero-yaw with real-world visible-band specifications. This open-source tool allows users to specify the bounding box (top-left and bottom-right) coordinates of any region on a map. Without the need to physically fly a drone, the virtual Python UAV performs a raster search to capture satellite images using the Google Maps Static API. Users can define parameters such as flight altitude, aspect ratio and diagonal field of view of the camera, and the overlap between consecutive images. SkyAI Sim's capabilities range from capturing a few low-altitude images for basic applications to generating extensive datasets of entire cities for complex tasks like deep learning. This versatility makes SkyAI a valuable tool for not only VBN, but also other applications including environmental monitoring, construction, and city management. The open-source nature of the tool also allows for extending the raster search to other missions. A dataset of Memphis, TN has been provided along with this simulator, partially generated using SkyAI and, also includes data from a 3D world generation package for comparison.
Authors: Pranav Jeevan, Neeraj Nixon, Amit Sethi
Abstract: We propose two new evaluation metrics to assess realness of generated images based on normalizing flows: a simpler and efficient flow-based likelihood distance (FLD) and a more exact dual-flow based likelihood distance (D-FLD). Because normalizing flows can be used to compute the exact likelihood, the proposed metrics assess how closely generated images align with the distribution of real images from a given domain. This property gives the proposed metrics a few advantages over the widely used Fr\'echet inception distance (FID) and other recent metrics. Firstly, the proposed metrics need only a few hundred images to stabilize (converge in mean), as opposed to tens of thousands needed for FID, and at least a few thousand for the other metrics. This allows confident evaluation of even small sets of generated images, such as validation batches inside training loops. Secondly, the network used to compute the proposed metric has over an order of magnitude fewer parameters compared to Inception-V3 used to compute FID, making it computationally more efficient. For assessing the realness of generated images in new domains (e.g., x-ray images), ideally these networks should be retrained on real images to model their distinct distributions. Thus, our smaller network will be even more advantageous for new domains. Extensive experiments show that the proposed metrics have the desired monotonic relationships with the extent of image degradation of various kinds.
Authors: Kyle Buettner, Adriana Kovashka
Abstract: There is a scarcity of multilingual vision-language models that properly account for the perceptual differences that are reflected in image captions across languages and cultures. In this work, through a multimodal, multilingual retrieval case study, we quantify the existing lack of model flexibility. We empirically show performance gaps between training on captions that come from native German perception and captions that have been either machine-translated or human-translated from English into German. To address these gaps, we further propose and evaluate caption augmentation strategies. While we achieve mean recall improvements (+1.3), gaps still remain, indicating an open area of future work for the community.
Authors: Kyle Vedder, Neehar Peri, Ishan Khatri, Siyi Li, Eric Eaton, Mehmet Kocamaz, Yue Wang, Zhiding Yu, Deva Ramanan, Joachim Pehserl
Abstract: We reframe scene flow as the problem of estimating a continuous space and time PDE that describes motion for an entire observation sequence, represented with a neural prior. Our resulting unsupervised method, EulerFlow, produces high quality scene flow on real-world data across multiple domains, including large-scale autonomous driving scenes and dynamic tabletop settings. Notably, EulerFlow produces high quality flow on small, fast moving objects like birds and tennis balls, and exhibits emergent 3D point tracking behavior by solving its estimated PDE over long time horizons. On the Argoverse 2 2024 Scene Flow Challenge, EulerFlow outperforms all prior art, beating the next best unsupervised method by over 2.5x and the next best supervised method by over 10%.
Authors: Mahshid Dehghani, Amirahmad Shafiee, Ali Shafiei, Neda Fallah, Farahmand Alizadeh, Mohammad Mehdi Gholinejad, Hamid Behroozi, Jafar Habibi, Ehsaneddin Asgari
Abstract: Existing 3D facial emotion modeling have been constrained by limited emotion classes and insufficient datasets. This paper introduces "Emo3D", an extensive "Text-Image-Expression dataset" spanning a wide spectrum of human emotions, each paired with images and 3D blendshapes. Leveraging Large Language Models (LLMs), we generate a diverse array of textual descriptions, facilitating the capture of a broad spectrum of emotional expressions. Using this unique dataset, we conduct a comprehensive evaluation of language-based models' fine-tuning and vision-language models like Contranstive Language Image Pretraining (CLIP) for 3D facial expression synthesis. We also introduce a new evaluation metric for this task to more directly measure the conveyed emotion. Our new evaluation metric, Emo3D, demonstrates its superiority over Mean Squared Error (MSE) metrics in assessing visual-text alignment and semantic richness in 3D facial expressions associated with human emotions. "Emo3D" has great applications in animation design, virtual reality, and emotional human-computer interaction.
Authors: James Baker
Abstract: Teaching text-to-image models to be creative involves using style ambiguity loss. In this work, we explore using the style ambiguity training objective, used to approximate creativity, on a diffusion model. We then experiment with forms of style ambiguity loss that do not require training a classifier or a labeled dataset, and find that the models trained with style ambiguity loss can generate better images than the baseline diffusion models and GANs. Code is available at https://github.com/jamesBaker361/clipcreate.
Authors: Jing He, Haodong Li, Yongzhe Hu, Guibao Shen, Yingjie Cai, Weichao Qiu, Ying-Cong Chen
Abstract: In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both tuning-based and tuning-free, struggle with interpreting the subject-essential attributes from the visual prompt. This leads to subject-irrelevant attributes infiltrating the generation process, ultimately compromising the personalization quality in both editability and ID preservation. In this paper, we present DisEnvisioner, a novel approach for effectively extracting and enriching the subject-essential features while filtering out -irrelevant information, enabling exceptional customization performance, in a tuning-free manner and using only a single image. Specifically, the feature of the subject and other irrelevant components are effectively separated into distinctive visual tokens, enabling a much more accurate customization. Aiming to further improving the ID consistency, we enrich the disentangled features, sculpting them into more granular representations. Experiments demonstrate the superiority of our approach over existing methods in instruction response (editability), ID consistency, inference speed, and the overall image quality, highlighting the effectiveness and efficiency of DisEnvisioner. Project page: https://disenvisioner.github.io/.
Authors: Mariia Drozdova, Vitaliy Kinakh, Yury Belousov, Erica Lastufka, Slava Voloshynovskiy
Abstract: In this paper, we present a semi-supervised fine-tuning approach designed to improve the performance of foundation models on downstream tasks with limited labeled data. By leveraging content-style decomposition within an information-theoretic framework, our method enhances the latent representations of pre-trained vision foundation models, aligning them more effectively with specific task objectives and addressing the problem of distribution shift. We evaluate our approach on multiple datasets, including MNIST, its augmented variations (with yellow and white stripes), CIFAR-10, SVHN, and GalaxyMNIST. The experiments show improvements over purely supervised baselines, particularly in low-labeled data regimes, across both frozen and trainable backbones for the majority of the tested datasets.
Authors: Alzayat Saleh, Melanie Olsen, Bouchra Senadji, Mostafa Rahimi Azghadi
Abstract: Monocular Depth and Surface Normals Estimation (MDSNE) is crucial for tasks such as 3D reconstruction, autonomous navigation, and underwater exploration. Current methods rely either on discriminative models, which struggle with transparent or reflective surfaces, or generative models, which, while accurate, are computationally expensive. This paper presents a novel deep learning model for MDSNE, specifically tailored for underwater environments, using a hybrid architecture that integrates Convolutional Neural Networks (CNNs) with Transformers, leveraging the strengths of both approaches. Training effective MDSNE models is often hampered by noisy real-world datasets and the limited generalization of synthetic datasets. To address this, we generate pseudo-labeled real data using multiple pre-trained MDSNE models. To ensure the quality of this data, we propose the Depth Normal Evaluation and Selection Algorithm (DNESA), which evaluates and selects the most reliable pseudo-labeled samples using domain-specific metrics. A lightweight student model is then trained on this curated dataset. Our model reduces parameters by 90% and training costs by 80%, allowing real-time 3D perception on resource-constrained devices. Key contributions include: a novel and efficient MDSNE model, the DNESA algorithm, a domain-specific data pipeline, and a focus on real-time performance and scalability. Designed for real-world underwater applications, our model facilitates low-cost deployments in underwater robots and autonomous vehicles, bridging the gap between research and practical implementation.
Authors: Aleksei Bochkovskii, Ama\"el Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R. Richter, Vladlen Koltun
Abstract: We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU. These characteristics are enabled by a number of technical contributions, including an efficient multi-scale vision transformer for dense prediction, a training protocol that combines real and synthetic datasets to achieve high metric accuracy alongside fine boundary tracing, dedicated evaluation metrics for boundary accuracy in estimated depth maps, and state-of-the-art focal length estimation from a single image. Extensive experiments analyze specific design choices and demonstrate that Depth Pro outperforms prior work along multiple dimensions. We release code and weights at https://github.com/apple/ml-depth-pro
Authors: Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
Abstract: Multi-modal Large Language Models (MLLMs) have recently exhibited impressive general-purpose capabilities by leveraging vision foundation models to encode the core concepts of images into representations. These are then combined with instructions and processed by the language model to generate high-quality responses. Despite significant progress in enhancing the language component, challenges persist in optimally fusing visual encodings within the language model for task-specific adaptability. Recent research has focused on improving this fusion through modality adaptation modules but at the cost of significantly increased model complexity and training data needs. In this paper, we propose EMMA (Efficient Multi-Modal Adaptation), a lightweight cross-modality module designed to efficiently fuse visual and textual encodings, generating instruction-aware visual representations for the language model. Our key contributions include: (1) an efficient early fusion mechanism that integrates vision and language representations with minimal added parameters (less than 0.2% increase in model size), (2) an in-depth interpretability analysis that sheds light on the internal mechanisms of the proposed method; (3) comprehensive experiments that demonstrate notable improvements on both specialized and general benchmarks for MLLMs. Empirical results show that EMMA boosts performance across multiple tasks by up to 9.3% while significantly improving robustness against hallucinations. Our code is available at https://github.com/SaraGhazanfari/EMMA
Authors: Haotian Sun, Bowen Zhang, Yanghao Li, Haoshuo Huang, Tao Lei, Ruoming Pang, Bo Dai, Nan Du
Abstract: Diffusion transformers have been widely adopted for text-to-image synthesis. While scaling these models up to billions of parameters shows promise, the effectiveness of scaling beyond current sizes remains underexplored and challenging. By explicitly exploiting the computational heterogeneity of image generations, we develop a new family of Mixture-of-Experts (MoE) models (EC-DIT) for diffusion transformers with expert-choice routing. EC-DIT learns to adaptively optimize the compute allocated to understand the input texts and generate the respective image patches, enabling heterogeneous computation aligned with varying text-image complexities. This heterogeneity provides an efficient way of scaling EC-DIT up to 97 billion parameters and achieving significant improvements in training convergence, text-to-image alignment, and overall generation quality over dense models and conventional MoE models. Through extensive ablations, we show that EC-DIT demonstrates superior scalability and adaptive compute allocation by recognizing varying textual importance through end-to-end training. Notably, in text-to-image alignment evaluation, our largest models achieve a state-of-the-art GenEval score of 71.68% and still maintain competitive inference speed with intuitive interpretability.
Authors: Christopher Scarvelis, David Benhaim, Paul Zhang
Abstract: Orientation estimation is a fundamental task in 3D shape analysis which consists of estimating a shape's orientation axes: its side-, up-, and front-axes. Using this data, one can rotate a shape into canonical orientation, where its orientation axes are aligned with the coordinate axes. Developing an orientation algorithm that reliably estimates complete orientations of general shapes remains an open problem. We introduce a two-stage orientation pipeline that achieves state of the art performance on up-axis estimation and further demonstrate its efficacy on full-orientation estimation, where one seeks all three orientation axes. Unlike previous work, we train and evaluate our method on all of Shapenet rather than a subset of classes. We motivate our engineering contributions by theory describing fundamental obstacles to orientation estimation for rotationally-symmetric shapes, and show how our method avoids these obstacles.
Authors: Xiaobiao Du, Yida Wang, Xin Yu
Abstract: Recent works in volume rendering, \textit{e.g.} NeRF and 3D Gaussian Splatting (3DGS), significantly advance the rendering quality and efficiency with the help of the learned implicit neural radiance field or 3D Gaussians. Rendering on top of an explicit representation, the vanilla 3DGS and its variants deliver real-time efficiency by optimizing the parametric model with single-view supervision per iteration during training which is adopted from NeRF. Consequently, certain views are overfitted, leading to unsatisfying appearance in novel-view synthesis and imprecise 3D geometries. To solve aforementioned problems, we propose a new 3DGS optimization method embodying four key novel contributions: 1) We transform the conventional single-view training paradigm into a multi-view training strategy. With our proposed multi-view regulation, 3D Gaussian attributes are further optimized without overfitting certain training views. As a general solution, we improve the overall accuracy in a variety of scenarios and different Gaussian variants. 2) Inspired by the benefit introduced by additional views, we further propose a cross-intrinsic guidance scheme, leading to a coarse-to-fine training procedure concerning different resolutions. 3) Built on top of our multi-view regulated training, we further propose a cross-ray densification strategy, densifying more Gaussian kernels in the ray-intersect regions from a selection of views. 4) By further investigating the densification strategy, we found that the effect of densification should be enhanced when certain views are distinct dramatically. As a solution, we propose a novel multi-view augmented densification strategy, where 3D Gaussians are encouraged to get densified to a sufficient number accordingly, resulting in improved reconstruction accuracy.
Authors: Arun Reddy, Ketul Shah, Corban Rivera, William Paul, Celso M. De Melo, Rama Chellappa
Abstract: In this work, we explore the possibility of using synthetically generated data for video-based gesture recognition with large pre-trained models. We consider whether these models have sufficiently robust and expressive representation spaces to enable "training-free" classification. Specifically, we utilize various state-of-the-art video encoders to extract features for use in k-nearest neighbors classification, where the training data points are derived from synthetic videos only. We compare these results with another training-free approach -- zero-shot classification using text descriptions of each gesture. In our experiments with the RoCoG-v2 dataset, we find that using synthetic training videos yields significantly lower classification accuracy on real test videos compared to using a relatively small number of real training videos. We also observe that video backbones that were fine-tuned on classification tasks serve as superior feature extractors, and that the choice of fine-tuning data has a substantial impact on k-nearest neighbors performance. Lastly, we find that zero-shot text-based classification performs poorly on the gesture recognition task, as gestures are not easily described through natural language.
Authors: Adrian Chan, Anupam Mijar, Mehreen Saeed, Chau-Wai Wong, Akram Khater
Abstract: Arabic handwritten text recognition (HTR) is challenging, especially for historical texts, due to diverse writing styles and the intrinsic features of Arabic script. Additionally, Arabic handwriting datasets are smaller compared to English ones, making it difficult to train generalizable Arabic HTR models. To address these challenges, we propose HATFormer, a transformer-based encoder-decoder architecture that builds on a state-of-the-art English HTR model. By leveraging the transformer's attention mechanism, HATFormer captures spatial contextual information to address the intrinsic challenges of Arabic script through differentiating cursive characters, decomposing visual representations, and identifying diacritics. Our customization to historical handwritten Arabic includes an image processor for effective ViT information preprocessing, a text tokenizer for compact Arabic text representation, and a training pipeline that accounts for a limited amount of historic Arabic handwriting data. HATFormer achieves a character error rate (CER) of 8.6% on the largest public historical handwritten Arabic dataset, with a 51% improvement over the best baseline in the literature. HATFormer also attains a comparable CER of 4.2% on the largest private non-historical dataset. Our work demonstrates the feasibility of adapting an English HTR method to a low-resource language with complex, language-specific challenges, contributing to advancements in document digitization, information retrieval, and cultural preservation.
Authors: Zheng Zhang, Xu Yuan, Lei Zhu, Jingkuan Song, Liqiang Nie
Abstract: Despite remarkable successes in unimodal learning tasks, backdoor attacks against cross-modal learning are still underexplored due to the limited generalization and inferior stealthiness when involving multiple modalities. Notably, since works in this area mainly inherit ideas from unimodal visual attacks, they struggle with dealing with diverse cross-modal attack circumstances and manipulating imperceptible trigger samples, which hinders their practicability in real-world applications. In this paper, we introduce a novel bilateral backdoor to fill in the missing pieces of the puzzle in the cross-modal backdoor and propose a generalized invisible backdoor framework against cross-modal learning (BadCM). Specifically, a cross-modal mining scheme is developed to capture the modality-invariant components as target poisoning areas, where well-designed trigger patterns injected into these regions can be efficiently recognized by the victim models. This strategy is adapted to different image-text cross-modal models, making our framework available to various attack scenarios. Furthermore, for generating poisoned samples of high stealthiness, we conceive modality-specific generators for visual and linguistic modalities that facilitate hiding explicit trigger patterns in modality-invariant regions. To the best of our knowledge, BadCM is the first invisible backdoor method deliberately designed for diverse cross-modal attacks within one unified framework. Comprehensive experimental evaluations on two typical applications, i.e., cross-modal retrieval and VQA, demonstrate the effectiveness and generalization of our method under multiple kinds of attack scenarios. Moreover, we show that BadCM can robustly evade existing backdoor defenses. Our code is available at https://github.com/xandery-geek/BadCM.
Authors: Hang Guo, Yuzhen Zhang, Tianci Gao, Junning Su, Pei Lv, Mingliang Xu
Abstract: Trajectory prediction is a pivotal component of autonomous driving systems, enabling the application of accumulated movement experience to current scenarios. Although most existing methods concentrate on learning continuous representations to gain valuable experience, they often suffer from computational inefficiencies and struggle with unfamiliar situations. To address this issue, we propose the Fragmented-Memory-based Trajectory Prediction (FMTP) model, inspired by the remarkable learning capabilities of humans, particularly their ability to leverage accumulated experience and recall relevant memories in unfamiliar situations. The FMTP model employs discrete representations to enhance computational efficiency by reducing information redundancy while maintaining the flexibility to utilize past experiences. Specifically, we design a learnable memory array by consolidating continuous trajectory representations from the training set using defined quantization operations during the training phase. This approach further eliminates redundant information while preserving essential features in discrete form. Additionally, we develop an advanced reasoning engine based on language models to deeply learn the associative rules among these discrete representations. Our method has been evaluated on various public datasets, including ETH-UCY, inD, SDD, nuScenes, Waymo, and VTL-TP. The extensive experimental results demonstrate that our approach achieves significant performance and extracts more valuable experience from past trajectories to inform the current state.
Authors: Qingyuan Liu, Avideh Zakhor
Abstract: Melanoma segmentation in Whole Slide Images (WSIs) is useful for prognosis and the measurement of crucial prognostic factors such as Breslow depth and primary invasive tumor size. In this paper, we present a novel approach that uses the Segment Anything Model (SAM) for automatic melanoma segmentation in microscopy slide images. Our method employs an initial semantic segmentation model to generate preliminary segmentation masks that are then used to prompt SAM. We design a dynamic prompting strategy that uses a combination of centroid and grid prompts to achieve optimal coverage of the super high-resolution slide images while maintaining the quality of generated prompts. To optimize for invasive melanoma segmentation, we further refine the prompt generation process by implementing in-situ melanoma detection and low-confidence region filtering. We select Segformer as the initial segmentation model and EfficientSAM as the segment anything model for parameter-efficient fine-tuning. Our experimental results demonstrate that this approach not only surpasses other state-of-the-art melanoma segmentation methods but also significantly outperforms the baseline Segformer by 9.1% in terms of IoU.
Authors: Wentao Huang, Xiaoling Hu, Shahira Abousamra, Prateek Prasanna, Chao Chen
Abstract: Weakly supervised whole slide image (WSI) classification is challenging due to the lack of patch-level labels and high computational costs. State-of-the-art methods use self-supervised patch-wise feature representations for multiple instance learning (MIL). Recently, methods have been proposed to fine-tune the feature representation on the downstream task using pseudo labeling, but mostly focusing on selecting high-quality positive patches. In this paper, we propose to mine hard negative samples during fine-tuning. This allows us to obtain better feature representations and reduce the training cost. Furthermore, we propose a novel patch-wise ranking loss in MIL to better exploit these hard negative samples. Experiments on two public datasets demonstrate the efficacy of these proposed ideas. Our codes are available at https://github.com/winston52/HNM-WSI
Authors: Yangyang Qiu, Guoan Xu, Guangwei Gao, Zhenhua Guo, Yi Yu, Chia-Wen Lin
Abstract: Recently, the integration of the local modeling capabilities of Convolutional Neural Networks (CNNs) with the global dependency strengths of Transformers has created a sensation in the semantic segmentation community. However, substantial computational workloads and high hardware memory demands remain major obstacles to their further application in real-time scenarios. In this work, we propose a lightweight multiple-information interaction network for real-time semantic segmentation, called LMIINet, which effectively combines CNNs and Transformers while reducing redundant computations and memory footprint. It features Lightweight Feature Interaction Bottleneck (LFIB) modules comprising efficient convolutions that enhance context integration. Additionally, improvements are made to the Flatten Transformer by enhancing local and global feature interaction to capture detailed semantic information. The incorporation of a combination coefficient learning scheme in both LFIB and Transformer blocks facilitates improved feature interaction. Extensive experiments demonstrate that LMIINet excels in balancing accuracy and efficiency. With only 0.72M parameters and 11.74G FLOPs, LMIINet achieves 72.0% mIoU at 100 FPS on the Cityscapes test set and 69.94% mIoU at 160 FPS on the CamVid test dataset using a single RTX2080Ti GPU.
Authors: Chengkai Hou, Zhengrong Xue, Bingyang Zhou, Jinghan Ke, Lin Shao, Huazhe Xu
Abstract: Detecting 3D keypoints with semantic consistency is widely used in many scenarios such as pose estimation, shape registration and robotics. Currently, most unsupervised 3D keypoint detection methods focus on the rigid-body objects. However, when faced with deformable objects, the keypoints they identify do not preserve semantic consistency well. In this paper, we introduce an innovative unsupervised keypoint detector Key-Grid for both the rigid-body and deformable objects, which is an autoencoder framework. The encoder predicts keypoints and the decoder utilizes the generated keypoints to reconstruct the objects. Unlike previous work, we leverage the identified keypoint in formation to form a 3D grid feature heatmap called grid heatmap, which is used in the decoder section. Grid heatmap is a novel concept that represents the latent variables for grid points sampled uniformly in the 3D cubic space, where these variables are the shortest distance between the grid points and the skeleton connected by keypoint pairs. Meanwhile, we incorporate the information from each layer of the encoder into the decoder section. We conduct an extensive evaluation of Key-Grid on a list of benchmark datasets. Key-Grid achieves the state-of-the-art performance on the semantic consistency and position accuracy of keypoints. Moreover, we demonstrate the robustness of Key-Grid to noise and downsampling. In addition, we achieve SE-(3) invariance of keypoints though generalizing Key-Grid to a SE(3)-invariant backbone.
Authors: Zihao Pan, Weibin Wu, Yuhang Cao, Zibin Zheng
Abstract: Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic. Recent works have utilized the diffusion inversion process to map images into a latent space, where high-level semantics are manipulated by introducing perturbations. However, they often results in substantial semantic distortions in the denoised output and suffers from low efficiency. In this study, we propose a novel framework called Semantic-Consistent Unrestricted Adversarial Attacks (SCA), which employs an inversion method to extract edit-friendly noise maps and utilizes Multimodal Large Language Model (MLLM) to provide semantic guidance throughout the process. Under the condition of rich semantic information provided by MLLM, we perform the DDPM denoising process of each step using a series of edit-friendly noise maps, and leverage DPM Solver++ to accelerate this process, enabling efficient sampling with semantic consistency. Compared to existing methods, our framework enables the efficient generation of adversarial examples that exhibit minimal discernible semantic changes. Consequently, we for the first time introduce Semantic-Consistent Adversarial Examples (SCAE). Extensive experiments and visualizations have demonstrated the high efficiency of SCA, particularly in being on average 12 times faster than the state-of-the-art attacks. Our code can be found at https://github.com/Pan-Zihao/SCA}{https://github.com/Pan-Zihao/SCA.
URLs: https://github.com/Pan-Zihao/SCA, https://github.com/Pan-Zihao/SCA.
Authors: Qixuan Zhang, Zhifeng Wang, Dylan Zhang, Wenjia Niu, Sabrina Caldwell, Tom Gedeon, Yang Liu, Zhenyue Qin
Abstract: Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing. Nonetheless, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatial localization and often discard valuable global context. To address this problem, we propose a Set-of-Vision prompting (SoV) approach that enhances zero-shot emotion recognition by using spatial information, such as bounding boxes and facial landmarks, to mark targets precisely. SoV improves accuracy in face count and emotion categorization while preserving the enriched image context. Through a battery of experimentation and analysis of recent commercial or open-source VLLMs, we evaluate the SoV model's ability to comprehend facial expressions in natural environments. Our findings demonstrate the effectiveness of integrating spatial visual prompts into VLLMs for improving emotion recognition performance.
Authors: Jiahang Cao, Mingyuan Sun, Ziqing Wang, Hao Cheng, Qiang Zhang, Shibo Zhou, Renjing Xu
Abstract: Event-based cameras are attracting significant interest as they provide rich edge information, high dynamic range, and high temporal resolution. Many state-of-the-art event-based algorithms rely on splitting the events into fixed groups, resulting in the omission of crucial temporal information, particularly when dealing with diverse motion scenarios (e.g., high/low speed). In this work, we propose SpikeSlicer, a novel-designed plug-and-play event processing method capable of splitting events stream adaptively. SpikeSlicer utilizes a lightweight (0.41M) and low-energy spiking neural network (SNN) to trigger event slicing. To guide the SNN to fire spikes at optimal time steps, we propose the Spiking Position-aware Loss (SPA-Loss) to modulate the neuron's state. Additionally, we develop a Feedback-Update training strategy that refines the slicing decisions using feedback from the downstream artificial neural network (ANN). Extensive experiments demonstrate that our method yields significant performance improvements in event-based object tracking and recognition. Notably, SpikeSlicer provides a brand-new SNN-ANN cooperation paradigm, where the SNN acts as an efficient, low-energy data processor to assist the ANN in improving downstream performance, injecting new perspectives and potential avenues of exploration.
Authors: Dominik J. M\"uhlematter, Sebastian Schweizer, Chenjing Jiao, Xue Xia, Magnus Heitzler, Lorenz Hurni
Abstract: Historical maps are invaluable for analyzing long-term changes in transportation and spatial development, offering a rich source of data for evolutionary studies. However, digitizing and classifying road networks from these maps is often expensive and time-consuming, limiting their widespread use. Recent advancements in deep learning have made automatic road extraction from historical maps feasible, yet these methods typically require large amounts of labeled training data. To address this challenge, we introduce a novel framework that integrates deep learning with geoinformation, computer-based painting, and image processing methodologies. This framework enables the extraction and classification of roads from historical maps using only road geometries without needing road class labels for training. The process begins with training of a binary segmentation model to extract road geometries, followed by morphological operations, skeletonization, vectorization, and filtering algorithms. Synthetic training data is then generated by a painting function that artificially re-paints road segments using predefined symbology for road classes. Using this synthetic data, a deep ensemble is trained to generate pixel-wise probabilities for road classes to mitigate distribution shift. These predictions are then discretized along the extracted road geometries. Subsequently, further processing is employed to classify entire roads, enabling the identification of potential changes in road classes and resulting in a labeled road class dataset. Our method achieved completeness and correctness scores of over 94% and 92%, respectively, for road class 2, the most prevalent class in the two Siegfried Map sheets from Switzerland used for testing. This research offers a powerful tool for urban planning and transportation decision-making by efficiently extracting and classifying roads from historical maps.
Authors: Yu Cao, Xin Duan, Xiangqiao Meng, P. Y. Mok, Ping Li, Tong-Yee Lee
Abstract: This paper reviews published research in the field of computer-aided colorization technology. We argue that the colorization task originates from computer graphics, prospers by introducing computer vision, and tends to the fusion of vision and graphics, so we put forward our taxonomy and organize the whole paper chronologically. We extend the existing reconstruction-based colorization evaluation techniques, considering that aesthetic assessment of colored images should be introduced to ensure that colorization satisfies human visual-related requirements and emotions more closely. We perform the colorization aesthetic assessment on seven representative unconditional colorization models and discuss the difference between our assessment and the existing reconstruction-based metrics. Finally, this paper identifies unresolved issues and proposes fruitful areas for future research and development. Access to the project associated with this survey can be obtained at https://github.com/DanielCho-HK/Colorization.
Authors: Shayan Rokhva, Babak Teimourpour
Abstract: Integrating artificial intelligence into modern society is profoundly transformative, significantly enhancing productivity by streamlining various daily tasks. AI-driven recognition systems provide notable advantages in the food sector, including improved nutrient tracking, tackling food waste, and boosting food production and consumption efficiency. Accurate food classification is a crucial initial step in utilizing advanced AI models, as the effectiveness of this process directly influences the success of subsequent operations; therefore, achieving high accuracy at a reasonable speed is essential. Despite existing research efforts, a gap persists in improving performance while ensuring rapid processing times, prompting researchers to pursue cost-effective and precise models. This study addresses this gap by employing the state-of-the-art EfficientNetB7 architecture, enhanced through transfer learning, data augmentation, and the CBAM attention module. This methodology results in a robust model that surpasses previous studies in accuracy while maintaining rapid processing suitable for real-world applications. The Food11 dataset from Kaggle was utilized, comprising 16643 imbalanced images across 11 diverse classes with significant intra-category diversities and inter-category similarities. Furthermore, the proposed methodology, bolstered by various deep learning techniques, consistently achieves an impressive average accuracy of 96.40%. Notably, it can classify over 60 images within one second during inference on unseen data, demonstrating its ability to deliver high accuracy promptly. This underscores its potential for practical applications in accurate food classification and enhancing efficiency in subsequent processes.
Authors: Mingxuan Li, Kai Zhou
Abstract: Facial recognition using deep learning has been widely used in social life for applications such as authentication, smart door locks, and photo grouping, etc. More and more networks have been developed to facilitate computer vision tasks, such as ResNet, DenseNet, EfficientNet, ConvNeXt, and Siamese networks. However, few studies have systematically compared the advantages and disadvantages of such neural networks in identifying individuals from images, especially for pet animals like cats. In the present study, by systematically comparing the efficacy of different neural networks in cat recognition, we found traditional CNNs trained with transfer learning have better performance than models trained with the fine-tuning method or Siamese networks in individual cat recognition. In addition, ConvNeXt and DenseNet yield significant results which could be further optimized for individual cat recognition in pet stores and in the wild. These results provide a method to improve cat management in pet stores and monitoring of cats in the wild.
Authors: Ren-Min Si, Yan-Ming Zhang, Yi Chen
Abstract: Text plays a crucial role in the transmission of human civilization, and teaching machines to generate online handwritten text in various styles presents an interesting and significant challenge. However, most prior work has concentrated on generating individual Chinese fonts, leaving {complete text line generation largely unexplored}. In this paper, we identify that text lines can naturally be divided into two components: layout and glyphs. Based on this division, we designed a text line layout generator coupled with a diffusion-based stylized font synthesizer to address this challenge hierarchically. More concretely, the layout generator performs in-context-like learning based on the text content and the provided style references to generate positions for each glyph autoregressively. Meanwhile, the font synthesizer which consists of a character embedding dictionary, a multi-scale calligraphy style encoder, and a 1D U-Net based diffusion denoiser will generate each font on its position while imitating the calligraphy style extracted from the given style references. Qualitative and quantitative experiments on the CASIA-OLHWDB demonstrate that our method is capable of generating structurally correct and indistinguishable imitation samples.
Authors: Thomas Buddenkotte, Roland Opfer, Julia Kr\"uger, Alessa Hering, Mireia Crispin-Ortuzar
Abstract: Medical image analysis tasks often focus on regions or structures located in a particular location within the patient's body. Often large parts of the image may not be of interest for the image analysis task. When using deep-learning based approaches, this causes an unnecessary increases the computational burden during inference and raises the chance of errors. In this paper, we introduce CTARR, a novel generic method for CT Anatomical Region Recognition. The method serves as a pre-processing step for any deep learning-based CT image analysis pipeline by automatically identifying the pre-defined anatomical region that is relevant for the follow-up task and removing the rest. It can be used in (i) image segmentation to prevent false positives in anatomically implausible regions and speeding up the inference, (ii) image classification to produce image crops that are consistent in their anatomical context, and (iii) image registration by serving as a fast pre-registration step. Our proposed method is based on atlas registration and provides a fast and robust way to crop any anatomical region encoded as one or multiple bounding box(es) from any unlabeled CT scan of the brain, chest, abdomen and/or pelvis. We demonstrate the utility and robustness of the proposed method in the context of medical image segmentation by evaluating it on six datasets of public segmentation challenges. The foreground voxels in the regions of interest are preserved in the vast majority of cases and tasks (97.45-100%) while taking only fractions of a seconds to compute (0.1-0.21s) on a deep learning workstation and greatly reducing the segmentation runtime (2.0-12.7x). Our code is available at https://github.com/ThomasBudd/ctarr.
Authors: Remco Royen, Kostas Pataridis, Ward van der Tempel, Adrian Munteanu
Abstract: 3D scene understanding is crucial for facilitating seamless interaction between digital devices and the physical world. Real-time capturing and processing of the 3D scene are essential for achieving this seamless integration. While existing approaches typically separate acquisition and processing for each frame, the advent of resolution-scalable 3D sensors offers an opportunity to overcome this paradigm and fully leverage the otherwise wasted acquisition time to initiate processing. In this study, we introduce VX-S3DIS, a novel point cloud dataset accurately simulating the behavior of a resolution-scalable 3D sensor. Additionally, we present RESSCAL3D++, an important improvement over our prior work, RESSCAL3D, by incorporating an update module and processing strategy. By applying our method to the new dataset, we practically demonstrate the potential of joint acquisition and semantic segmentation of 3D point clouds. Our resolution-scalable approach significantly reduces scalability costs from 2% to just 0.2% in mIoU while achieving impressive speed-ups of 15.6 to 63.9% compared to the non-scalable baseline. Furthermore, our scalable approach enables early predictions, with the first one occurring after only 7% of the total inference time of the baseline. The new VX-S3DIS dataset is available at https://github.com/remcoroyen/vx-s3dis.
Authors: Junlin Hou, Sicen Liu, Yequan Bie, Hongmei Wang, Andong Tan, Luyang Luo, Hao Chen
Abstract: The increasing demand for transparent and reliable models, particularly in high-stakes decision-making areas such as medical image analysis, has led to the emergence of eXplainable Artificial Intelligence (XAI). Post-hoc XAI techniques, which aim to explain black-box models after training, have been controversial in recent works concerning their fidelity to the models' predictions. In contrast, Self-eXplainable AI (S-XAI) offers a compelling alternative by incorporating explainability directly into the training process of deep learning models. This approach allows models to generate inherent explanations that are closely aligned with their internal decision-making processes. Such enhanced transparency significantly supports the trustworthiness, robustness, and accountability of AI systems in real-world medical applications. To facilitate the development of S-XAI methods for medical image analysis, this survey presents an comprehensive review across various image modalities and clinical applications. It covers more than 200 papers from three key perspectives: 1) input explainability through the integration of explainable feature engineering and knowledge graph, 2) model explainability via attention-based learning, concept-based learning, and prototype-based learning, and 3) output explainability by providing counterfactual explanation and textual explanation. Additionally, this paper outlines the desired characteristics of explainability and existing evaluation methods for assessing explanation quality. Finally, it discusses the major challenges and future research directions in developing S-XAI for medical image analysis.
Authors: Remco Royen, Leon Denis, Adrian Munteanu
Abstract: 3D instance segmentation is crucial for obtaining an understanding of a point cloud scene. This paper presents a novel neural network architecture for performing instance segmentation on 3D point clouds. We propose to jointly learn coefficients and prototypes in parallel which can be combined to obtain the instance predictions. The coefficients are computed using an overcomplete set of sampled points with a novel multi-scale module, dubbed dilated point inception. As the set of obtained instance mask predictions is overcomplete, we employ a non-maximum suppression algorithm to retrieve the final predictions. This approach allows to omit the time-expensive clustering step and leads to a more stable inference time. The proposed method is not only 28% faster than the state-of-the-art, it also exhibits the lowest standard deviation. Our experiments have shown that the standard deviation of the inference time is only 1.0% of the total time while it ranges between 10.8 and 53.1% for the state-of-the-art methods. Lastly, our method outperforms the state-of-the-art both on S3DIS-blocks (4.9% in mRec on Fold-5) and PartNet (2.0% on average in mAP).
Authors: Shubhi Bansal, Sreeharish A, Madhava Prasath J, Manikandan S, Sreekanth Madisetty, Mohammad Zia Ur Rehman, Chandravardhan Singh Raghaw, Gaurav Duggal, Nagendra Kumar
Abstract: Mamba, a special case of the State Space Model, is gaining popularity as an alternative to template-based deep learning approaches in medical image analysis. While transformers are powerful architectures, they have drawbacks, including quadratic computational complexity and an inability to address long-range dependencies efficiently. This limitation affects the analysis of large and complex datasets in medical imaging, where there are many spatial and temporal relationships. In contrast, Mamba offers benefits that make it well-suited for medical image analysis. It has linear time complexity, which is a significant improvement over transformers. Mamba processes longer sequences without attention mechanisms, enabling faster inference and requiring less memory. Mamba also demonstrates strong performance in merging multimodal data, improving diagnosis accuracy and patient outcomes. The organization of this paper allows readers to appreciate the capabilities of Mamba in medical imaging step by step. We begin by defining core concepts of SSMs and models, including S4, S5, and S6, followed by an exploration of Mamba architectures such as pure Mamba, U-Net variants, and hybrid models with convolutional neural networks, transformers, and Graph Neural Networks. We also cover Mamba optimizations, techniques and adaptations, scanning, datasets, applications, experimental results, and conclude with its challenges and future directions in medical imaging. This review aims to demonstrate the transformative potential of Mamba in overcoming existing barriers within medical imaging while paving the way for innovative advancements in the field. A comprehensive list of Mamba architectures applied in the medical field, reviewed in this work, is available at Github.
Authors: Muzhi Zhu, Yang Liu, Zekai Luo, Chenchen Jing, Hao Chen, Guangkai Xu, Xinlong Wang, Chunhua Shen
Abstract: The Diffusion Model has not only garnered noteworthy achievements in the realm of image generation but has also demonstrated its potential as an effective pretraining method utilizing unlabeled data. Drawing from the extensive potential unveiled by the Diffusion Model in both semantic correspondence and open vocabulary segmentation, our work initiates an investigation into employing the Latent Diffusion Model for Few-shot Semantic Segmentation. Recently, inspired by the in-context learning ability of large language models, Few-shot Semantic Segmentation has evolved into In-context Segmentation tasks, morphing into a crucial element in assessing generalist segmentation models. In this context, we concentrate on Few-shot Semantic Segmentation, establishing a solid foundation for the future development of a Diffusion-based generalist model for segmentation. Our initial focus lies in understanding how to facilitate interaction between the query image and the support image, resulting in the proposal of a KV fusion method within the self-attention framework. Subsequently, we delve deeper into optimizing the infusion of information from the support mask and simultaneously re-evaluating how to provide reasonable supervision from the query mask. Based on our analysis, we establish a simple and effective framework named DiffewS, maximally retaining the original Latent Diffusion Model's generative framework and effectively utilizing the pre-training prior. Experimental results demonstrate that our method significantly outperforms the previous SOTA models in multiple settings.
Authors: Guodong Du, Junlin Lee, Jing Li, Runhua Jiang, Yifei Guo, Shuyang Yu, Hanting Liu, Sim Kuan Goh, Ho-Kin Tang, Daojing He, Min Zhang
Abstract: While fine-tuning pretrained models has become common practice, these models often underperform outside their specific domains. Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned for distinct tasks, into a single model. This strategy promotes multitasking capabilities without requiring retraining on the original datasets. However, existing methods fall short in addressing potential conflicts and complex correlations between tasks, especially in parameter-level adjustments, posing a challenge in effectively balancing parameter competition across various tasks. This paper introduces an innovative technique named PCB-Merging (Parameter Competition Balancing), a lightweight and training-free technique that adjusts the coefficients of each parameter for effective model merging. PCB-Merging employs intra-balancing to gauge parameter significance within individual tasks and inter-balancing to assess parameter similarities across different tasks. Parameters with low importance scores are dropped, and the remaining ones are rescaled to form the final merged model. We assessed our approach in diverse merging scenarios, including cross-task, cross-domain, and cross-training configurations, as well as out-of-domain generalization. The experimental results reveal that our approach achieves substantial performance enhancements across multiple modalities, domains, model sizes, number of tasks, fine-tuning forms, and large language models, outperforming existing model merging methods. The code is publicly available at: \url{https://github.com/duguodong7/pcb-merging}.
Authors: Nikolaos Giakoumoglou, Tania Stathaki
Abstract: Contrastive learning has become a dominant approach in self-supervised visual representation learning, with hard negatives-samples that closely resemble the anchor-being key to enhancing the discriminative power of learned representations. However, efficiently leveraging hard negatives remains a challenge due to the difficulty in identifying and incorporating them without significantly increasing computational costs. To address this, we introduce SynCo (Synthetic Negatives in Contrastive learning), a novel contrastive learning approach that improves model performance by generating synthetic hard negatives. Built on the MoCo framework, SynCo introduces six novel strategies for creating diverse synthetic hard negatives that can be generated on-the-fly with minimal computational overhead. SynCo achieves faster training and better representation learning, achieving a top-1 accuracy of 68.1% in ImageNet linear evaluation after only 200 epochs on pretraining, surpassing MoCo's 67.5% with the same ResNet-50 encoder. Additionally, it transfers more effectively to detection tasks: on the PASCAL VOC, it outperforms both the supervised baseline and MoCo, achieving an AP of 82.5%; on the COCO dataset, it sets a new benchmark with 40.4% AP for bounding box detection and 35.4% AP for instance segmentation. Our synthetic hard negative generation procedure significantly enhances the quality of visual representations learned through self-supervised contrastive learning. Code is available at https://github.com/giakoumoglou/synco.
Authors: Karim Slimani, Brahim Tamadazte, Catherine Achard
Abstract: This paper introduces a new hybrid descriptor for 3D point matching and point cloud registration, combining local geometrical properties and learning-based feature propagation for each point's neighborhood structure description. The proposed architecture first extracts prior geometrical information by computing each point's planarity, anisotropy, and omnivariance using a Principal Components Analysis (PCA). This prior information is completed by a descriptor based on the normal vectors estimated thanks to constructing a neighborhood based on triangles. The final geometrical descriptor is propagated between the points using local graph convolutions and attention mechanisms. The new feature extractor is evaluated on ModelNet40, Bunny Stanford dataset, KITTI and MVP (Multi-View Partial)-RG for point cloud registration and shows interesting results, particularly on noisy and low overlapping point clouds.
Authors: S\'egol\`ene Martin, Anne Gagneux, Paul Hagemann, Gabriele Steidl
Abstract: In this paper, we introduce Plug-and-Play (PnP) Flow Matching, an algorithm for solving imaging inverse problems. PnP methods leverage the strength of pre-trained denoisers, often deep neural networks, by integrating them in optimization schemes. While they achieve state-of-the-art performance on various inverse problems in imaging, PnP approaches face inherent limitations on more generative tasks like inpainting. On the other hand, generative models such as Flow Matching pushed the boundary in image sampling yet lack a clear method for efficient use in image restoration. We propose to combine the PnP framework with Flow Matching (FM) by defining a time-dependent denoiser using a pre-trained FM model. Our algorithm alternates between gradient descent steps on the data-fidelity term, reprojections onto the learned FM path, and denoising. Notably, our method is computationally efficient and memory-friendly, as it avoids backpropagation through ODEs and trace computations. We evaluate its performance on denoising, super-resolution, deblurring, and inpainting tasks, demonstrating superior results compared to existing PnP algorithms and Flow Matching based state-of-the-art methods.
Authors: Julia Alekseenko, Bram Stieltjes, Michael Bach, Melanie Boerries, Oliver Opitz, Alexandros Karargyris, Nicolas Padoy
Abstract: Clinnova, a collaborative initiative involving France, Germany, Switzerland, and Luxembourg, is dedicated to unlocking the power of precision medicine through data federation, standardization, and interoperability. This European Greater Region initiative seeks to create an interoperable European standard using artificial intelligence (AI) and data science to enhance healthcare outcomes and efficiency. Key components include multidisciplinary research centers, a federated biobanking strategy, a digital health innovation platform, and a federated AI strategy. It targets inflammatory bowel disease, rheumatoid diseases, and multiple sclerosis (MS), emphasizing data quality to develop AI algorithms for personalized treatment and translational research. The IHU Strasbourg (Institute of Minimal-invasive Surgery) has the lead in this initiative to develop the federated learning (FL) proof of concept (POC) that will serve as a foundation for advancing AI in healthcare. At its core, Clinnova-MS aims to enhance MS patient care by using FL to develop more accurate models that detect disease progression, guide interventions, and validate digital biomarkers across multiple sites. This technical report presents insights and key takeaways from the first cross-border federated POC on MS segmentation of MRI images within the Clinnova framework. While our work marks a significant milestone in advancing MS segmentation through cross-border collaboration, it also underscores the importance of addressing technical, logistical, and ethical considerations to realize the full potential of FL in healthcare settings.
Authors: Maxime Talarmain, Carlos Boned, Sanket Biswas, Oriol Ramos
Abstract: General-purpose ID, or travel, document image- and video-based verification systems have yet to achieve good enough performance to be considered a solved problem. There are several factors that negatively impact their performance, including low-resolution images and videos and a lack of sufficient data to train the models. This task is particularly challenging when dealing with unseen class of ID, or travel, documents. In this paper we address this task by proposing a recurrent-based model able to detect forged documents in a few-shot scenario. The recurrent architecture makes the model robust to document resolution variability. Moreover, the few-shot approach allow the model to perform well even for unseen class of documents. Preliminary results on the SIDTD and Findit datasets show good performance of this model for this task.
Authors: Zhen Wang, Yilei Jiang, Dong Zheng, Jun Xiao, Long Chen
Abstract: Customized Image Generation, generating customized images with user-specified concepts, has raised significant attention due to its creativity and novelty. With impressive progress achieved in subject customization, some pioneer works further explored the customization of action and interaction beyond entity (i.e., human, animal, and object) appearance. However, these approaches only focus on basic actions and interactions between two entities, and their effects are limited by insufficient ''exactly same'' reference images. To extend customized image generation to more complex scenes for general real-world applications, we propose a new task: event-customized image generation. Given a single reference image, we define the ''event'' as all specific actions, poses, relations, or interactions between different entities in the scene. This task aims at accurately capturing the complex event and generating customized images with various target entities. To solve this task, we proposed a novel training-free event customization method: FreeEvent. Specifically, FreeEvent introduces two extra paths alongside the general diffusion denoising process: 1) Entity switching path: it applies cross-attention guidance and regulation for target entity generation. 2) Event transferring path: it injects the spatial feature and self-attention maps from the reference image to the target image for event generation. To further facilitate this new task, we collected two evaluation benchmarks: SWiG-Event and Real-Event. Extensive experiments and ablations have demonstrated the effectiveness of FreeEvent.
Authors: Xuchen Li, Shiyu Hu, Xiaokun Feng, Dailing Zhang, Meiqi Wu, Jing Zhang, Kaiqi Huang
Abstract: Visual language tracking (VLT) has emerged as a cutting-edge research area, harnessing linguistic data to enhance algorithms with multi-modal inputs and broadening the scope of traditional single object tracking (SOT) to encompass video understanding applications. Despite this, most VLT benchmarks still depend on succinct, human-annotated text descriptions for each video. These descriptions often fall short in capturing the nuances of video content dynamics and lack stylistic variety in language, constrained by their uniform level of detail and a fixed annotation frequency. As a result, algorithms tend to default to a "memorize the answer" strategy, diverging from the core objective of achieving a deeper understanding of video content. Fortunately, the emergence of large language models (LLMs) has enabled the generation of diverse text. This work utilizes LLMs to generate varied semantic annotations (in terms of text lengths and granularities) for representative SOT benchmarks, thereby establishing a novel multi-modal benchmark. Specifically, we (1) propose a new visual language tracking benchmark with diverse texts, named DTVLT, based on five prominent VLT and SOT benchmarks, including three sub-tasks: short-term tracking, long-term tracking, and global instance tracking. (2) We offer four granularity texts in our benchmark, considering the extent and density of semantic information. We expect this multi-granular generation strategy to foster a favorable environment for VLT and video understanding research. (3) We conduct comprehensive experimental analyses on DTVLT, evaluating the impact of diverse text on tracking performance and hope the identified performance bottlenecks of existing algorithms can support further research in VLT and video understanding. The proposed benchmark, experimental results and toolkit will be released gradually on http://videocube.aitestunion.com/.
Authors: Kai Liu, Ziqing Zhang, Wenbo Li, Renjing Pei, Fenglong Song, Xiaohong Liu, Linghe Kong, Yulun Zhang
Abstract: Image quality assessment (IQA) serves as the golden standard for all models' performance in nearly all computer vision fields. However, it still suffers from poor out-of-distribution generalization ability and expensive training costs. To address these problems, we propose Dog-IQA, a standard-guided zero-shot mix-grained IQA method, which is training-free and utilizes the exceptional prior knowledge of multimodal large language models (MLLMs). To obtain accurate IQA scores, namely scores consistent with humans, we design an MLLM-based inference pipeline that imitates human experts. In detail, Dog-IQA applies two techniques. First, Dog-IQA objectively scores with specific standards that utilize MLLM's behavior pattern and minimize the influence of subjective factors. Second, Dog-IQA comprehensively takes local semantic objects and the whole image as input and aggregates their scores, leveraging local and global information. Our proposed Dog-IQA achieves state-of-the-art (SOTA) performance compared with training-free methods, and competitive performance compared with training-based methods in cross-dataset scenarios. Our code and models will be available at https://github.com/Kai-Liu001/Dog-IQA.
Authors: Emir Konuk, Christos Matsoukas, Moein Sorkhei, Phitchapha Lertsiravaramet, Kevin Smith
Abstract: We introduce Learning from Offline Foundation Features with Tensor Augmentations (LOFF-TA), an efficient training scheme designed to harness the capabilities of foundation models in limited resource settings where their direct development is not feasible. LOFF-TA involves training a compact classifier on cached feature embeddings from a frozen foundation model, resulting in up to $37\times$ faster training and up to $26\times$ reduced GPU memory usage. Because the embeddings of augmented images would be too numerous to store, yet the augmentation process is essential for training, we propose to apply tensor augmentations to the cached embeddings of the original non-augmented images. LOFF-TA makes it possible to leverage the power of foundation models, regardless of their size, in settings with limited computational capacity. Moreover, LOFF-TA can be used to apply foundation models to high-resolution images without increasing compute. In certain scenarios, we find that training with LOFF-TA yields better results than directly fine-tuning the foundation model.
Authors: Jingjing Ren, Xiaoyong Zhang, Lina Zhang
Abstract: Numerous studies have demonstrated the strong performance of Vision Transformer (ViT)-based methods across various computer vision tasks. However, ViT models often struggle to effectively capture high-frequency components in images, which are crucial for detecting small targets and preserving edge details, especially in complex scenarios. This limitation is particularly challenging in colon polyp segmentation, where polyps exhibit significant variability in structure, texture, and shape. High-frequency information, such as boundary details, is essential for achieving precise semantic segmentation in this context. To address these challenges, we propose HiFiSeg, a novel network for colon polyp segmentation that enhances high-frequency information processing through a global-local vision transformer framework. HiFiSeg leverages the pyramid vision transformer (PVT) as its encoder and introduces two key modules: the global-local interaction module (GLIM) and the selective aggregation module (SAM). GLIM employs a parallel structure to fuse global and local information at multiple scales, effectively capturing fine-grained features. SAM selectively integrates boundary details from low-level features with semantic information from high-level features, significantly improving the model's ability to accurately detect and segment polyps. Extensive experiments on five widely recognized benchmark datasets demonstrate the effectiveness of HiFiSeg for polyp segmentation. Notably, the mDice scores on the challenging CVC-ColonDB and ETIS datasets reached 0.826 and 0.822, respectively, underscoring the superior performance of HiFiSeg in handling the specific complexities of this task.
Authors: Ruizhi Yang, Xingqiang Li, Jiajun Bai, Jinsong Du
Abstract: Self-supervised stereo matching holds great promise for application and research due to its independence from expensive labeled data. However, direct self-supervised stereo matching paradigms based on photometric loss functions have consistently struggled with performance issues due to the occlusion challenge. The crux of the occlusion challenge lies in the fact that the positions of occluded pixels consistently align with the epipolar search direction defined by the input stereo images, leading to persistent information loss and erroneous feedback at fixed locations during self-supervised training. In this work, we propose a simple yet highly effective pseudo-stereo inputs strategy to address the core occlusion challenge. This strategy decouples the input and feedback images, compelling the network to probabilistically sample information from both sides of the occluding objects. As a result, the persistent lack of information in the aforementioned fixed occlusion areas is mitigated. Building upon this, we further address feedback conflicts and overfitting issues arising from the strategy. By integrating these components, our method achieves stable and significant performance improvements compared to existing methods. Quantitative experiments are conducted to evaluate the performance. Qualitative experiments further demonstrate accurate disparity inference even at occluded regions. These results demonstrate a significant advancement over previous methods in the field of direct self-supervised stereo matching based on photometric loss. The proposed pseudo-stereo inputs strategy, due to its simplicity and effectiveness, has the potential to serve as a new paradigm for direct self-supervised stereo matching. Code is available at https://github.com/qrzyang/Pseudo-Stereo.
Authors: Shiyun Xie, Zhiru Wang, Yinghao Zhu, Chengwei Pan
Abstract: Recently, 3D Gaussian Splatting (3DGS) has exceled in novel view synthesis with its real-time rendering capabilities and superior quality. However, it faces challenges for high-resolution novel view synthesis (HRNVS) due to the coarse nature of primitives derived from low-resolution input views. To address this issue, we propose Super-Resolution 3DGS (SuperGS), which is an expansion of 3DGS designed with a two-stage coarse-to-fine training framework, utilizing pretrained low-resolution scene representation as an initialization for super-resolution optimization. Moreover, we introduce Multi-resolution Feature Gaussian Splatting (MFGS) to incorporates a latent feature field for flexible feature sampling and Gradient-guided Selective Splitting (GSS) for effective Gaussian upsampling. By integrating these strategies within the coarse-to-fine framework ensure both high fidelity and memory efficiency. Extensive experiments demonstrate that SuperGS surpasses state-of-the-art HRNVS methods on challenging real-world datasets using only low-resolution inputs.
Authors: Jing-En Huang, Jia-Wei Liao, Ku-Te Lin, Yu-Ju Tsai, Mei-Heng Yueh
Abstract: The total variation (TV) method is an image denoising technique that aims to reduce noise by minimizing the total variation of the image, which measures the variation in pixel intensities. The TV method has been widely applied in image processing and computer vision for its ability to preserve edges and enhance image quality. In this paper, we propose an improved TV model for image denoising and the associated numerical algorithm to carry out the procedure, which is particularly effective in removing several types of noises and their combinations. Our improved model admits a unique solution and the associated numerical algorithm guarantees the convergence. Numerical experiments are demonstrated to show improved effectiveness and denoising quality compared to other TV models. Such encouraging results further enhance the utility of the TV method in image processing.
Authors: Zihan Fang, Zheng Lin, Senkang Hu, Hangcheng Cao, Yiqin Deng, Xianhao Chen, Yuguang Fang
Abstract: Recently, in-car monitoring has emerged as a promising technology for detecting early-stage abnormal status of the driver and providing timely alerts to prevent traffic accidents. Although training models with multimodal data enhances the reliability of abnormal status detection, the scarcity of labeled data and the imbalance of class distribution impede the extraction of critical abnormal state features, significantly deteriorating training performance. Furthermore, missing modalities due to environment and hardware limitations further exacerbate the challenge of abnormal status identification. More importantly, monitoring abnormal health conditions of passengers, particularly in elderly care, is of paramount importance but remains underexplored. To address these challenges, we introduce our IC3M, an efficient camera-rotation-based multimodal framework for monitoring both driver and passengers in a car. Our IC3M comprises two key modules: an adaptive threshold pseudo-labeling strategy and a missing modality reconstruction. The former customizes pseudo-labeling thresholds for different classes based on the class distribution, generating class-balanced pseudo labels to guide model training effectively, while the latter leverages crossmodality relationships learned from limited labels to accurately recover missing modalities by distribution transferring from available modalities. Extensive experimental results demonstrate that IC3M outperforms state-of-the-art benchmarks in accuracy, precision, and recall while exhibiting superior robustness under limited labeled data and severe missing modality.
Authors: Mor Ventura, Michael Toker, Nitay Calderon, Zorik Gekhman, Yonatan Bitton, Roi Reichart
Abstract: Will a Visual Language Model (VLM)-based bot warn us about slipping if it detects a wet floor? Recent VLMs have demonstrated impressive capabilities, yet their ability to infer outcomes and causes remains underexplored. To address this, we introduce NL-Eye, a benchmark designed to assess VLMs' visual abductive reasoning skills. NL-Eye adapts the abductive Natural Language Inference (NLI) task to the visual domain, requiring models to evaluate the plausibility of hypothesis images based on a premise image and explain their decisions. NL-Eye consists of 350 carefully curated triplet examples (1,050 images) spanning diverse reasoning categories: physical, functional, logical, emotional, cultural, and social. The data curation process involved two steps - writing textual descriptions and generating images using text-to-image models, both requiring substantial human involvement to ensure high-quality and challenging scenes. Our experiments show that VLMs struggle significantly on NL-Eye, often performing at random baseline levels, while humans excel in both plausibility prediction and explanation quality. This demonstrates a deficiency in the abductive reasoning capabilities of modern VLMs. NL-Eye represents a crucial step toward developing VLMs capable of robust multimodal reasoning for real-world applications, including accident-prevention bots and generated video verification.
Authors: Hongze Chen, Zehong Lin, Jun Zhang
Abstract: We present GI-GS, a novel inverse rendering framework that leverages 3D Gaussian Splatting (3DGS) and deferred shading to achieve photo-realistic novel view synthesis and relighting. In inverse rendering, accurately modeling the shading processes of objects is essential for achieving high-fidelity results. Therefore, it is critical to incorporate global illumination to account for indirect lighting that reaches an object after multiple bounces across the scene. Previous 3DGS-based methods have attempted to model indirect lighting by characterizing indirect illumination as learnable lighting volumes or additional attributes of each Gaussian, while using baked occlusion to represent shadow effects. These methods, however, fail to accurately model the complex physical interactions between light and objects, making it impossible to construct realistic indirect illumination during relighting. To address this limitation, we propose to calculate indirect lighting using efficient path tracing with deferred shading. In our framework, we first render a G-buffer to capture the detailed geometry and material properties of the scene. Then, we perform physically-based rendering (PBR) only for direct lighting. With the G-buffer and previous rendering results, the indirect lighting can be calculated through a lightweight path tracing. Our method effectively models indirect lighting under any given lighting conditions, thereby achieving better novel view synthesis and relighting. Quantitative and qualitative results show that our GI-GS outperforms existing baselines in both rendering quality and efficiency.
Authors: Ga\v{s}per Podobnik, Toma\v{z} Vrtovec
Abstract: The evaluation of segmentation performance is a common task in biomedical image analysis, with its importance emphasized in the recently released metrics selection guidelines and computing frameworks. To quantitatively evaluate the alignment of two segmentations, researchers commonly resort to counting metrics, such as the Dice similarity coefficient, or distance-based metrics, such as the Hausdorff distance, which are usually computed by publicly available open-source tools with an inherent assumption that these tools provide consistent results. In this study we questioned this assumption, and performed a systematic implementation analysis along with quantitative experiments on real-world clinical data to compare 11 open-source tools for distance-based metrics computation against our highly accurate mesh-based reference implementation. The results revealed that statistically significant differences among all open-source tools are both surprising and concerning, since they question the validity of existing studies. Besides identifying the main sources of variation, we also provide recommendations for distance-based metrics computation.
Authors: Fabian Herzog, Johannes Gilg, Philipp Wolters, Torben Teepe, Gerhard Rigoll
Abstract: Accurate online multiple-camera vehicle tracking is essential for intelligent transportation systems, autonomous driving, and smart city applications. Like single-camera multiple-object tracking, it is commonly formulated as a graph problem of tracking-by-detection. Within this framework, existing online methods usually consist of two-stage procedures that cluster temporally first, then spatially, or vice versa. This is computationally expensive and prone to error accumulation. We introduce a graph representation that allows spatial-temporal clustering in a single, combined step: New detections are spatially and temporally connected with existing clusters. By keeping sparse appearance and positional cues of all detections in a cluster, our method can compare clusters based on the strongest available evidence. The final tracks are obtained online using a simple multicut assignment procedure. Our method does not require any training on the target scene, pre-extraction of single-camera tracks, or additional annotations. Notably, we outperform the online state-of-the-art on the CityFlow dataset in terms of IDF1 by more than 14%, and on the Synthehicle dataset by more than 25%, respectively. The code is publicly available.
Authors: Jinsu Yoo, Zhenyang Feng, Tai-Yu Pan, Yihong Sun, Cheng Perng Phoo, Xiangyu Chen, Mark Campbell, Kilian Q. Weinberger, Bharath Hariharan, Wei-Lun Chao
Abstract: Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data is tedious and expensive, and often needs repeated effort when a new sensor is adopted or when the detector is deployed in a new environment. We investigate a new scenario to construct 3D object detectors: learning from the predictions of a nearby unit that is equipped with an accurate detector. For example, when a self-driving car enters a new area, it may learn from other traffic participants whose detectors have been optimized for that area. This setting is label-efficient, sensor-agnostic, and communication-efficient: nearby units only need to share the predictions with the ego agent (e.g., car). Naively using the received predictions as ground-truths to train the detector for the ego car, however, leads to inferior performance. We systematically study the problem and identify viewpoint mismatches and mislocalization (due to synchronization and GPS errors) as the main causes, which unavoidably result in false positives, false negatives, and inaccurate pseudo labels. We propose a distance-based curriculum, first learning from closer units with similar viewpoints and subsequently improving the quality of other units' predictions via self-training. We further demonstrate that an effective pseudo label refinement module can be trained with a handful of annotated data, largely reducing the data quantity necessary to train an object detector. We validate our approach on the recently released real-world collaborative driving dataset, using reference cars' predictions as pseudo labels for the ego car. Extensive experiments including several scenarios (e.g., different sensors, detectors, and domains) demonstrate the effectiveness of our approach toward label-efficient learning of 3D perception from other units' predictions.
Authors: Taekyung Lee, Jaemoo Choi, Jaewoong Choi
Abstract: Unpaired point cloud completion explores methods for learning a completion map from unpaired incomplete and complete point cloud data. In this paper, we propose a novel approach for unpaired point cloud completion using the unbalanced optimal transport map, called Unbalanced Optimal Transport Map for Unpaired Point Cloud Completion (UOT-UPC). We demonstrate that the unpaired point cloud completion can be naturally interpreted as the Optimal Transport (OT) problem and introduce the Unbalanced Optimal Transport (UOT) approach to address the class imbalance problem, which is prevalent in unpaired point cloud completion datasets. Moreover, we analyze the appropriate cost function for unpaired completion tasks. This analysis shows that the InfoCD cost function is particularly well-suited for this task. Our model is the first attempt to leverage UOT for unpaired point cloud completion, achieving competitive or superior results on both single-category and multi-category datasets. In particular, our model is especially effective in scenarios with class imbalance, where the proportions of categories are different between the incomplete and complete point cloud datasets.
Authors: Zongming Li, Tianheng Cheng, Shoufa Chen, Peize Sun, Haocheng Shen, Longjin Ran, Xiaoxin Chen, Wenyu Liu, Xinggang Wang
Abstract: Autoregressive (AR) models have reformulated image generation as next-token prediction, demonstrating remarkable potential and emerging as strong competitors to diffusion models. However, control-to-image generation, akin to ControlNet, remains largely unexplored within AR models. Although a natural approach, inspired by advancements in Large Language Models, is to tokenize control images into tokens and prefill them into the autoregressive model before decoding image tokens, it still falls short in generation quality compared to ControlNet and suffers from inefficiency. To this end, we introduce ControlAR, an efficient and effective framework for integrating spatial controls into autoregressive image generation models. Firstly, we explore control encoding for AR models and propose a lightweight control encoder to transform spatial inputs (e.g., canny edges or depth maps) into control tokens. Then ControlAR exploits the conditional decoding method to generate the next image token conditioned on the per-token fusion between control and image tokens, similar to positional encodings. Compared to prefilling tokens, using conditional decoding significantly strengthens the control capability of AR models but also maintains the model's efficiency. Furthermore, the proposed ControlAR surprisingly empowers AR models with arbitrary-resolution image generation via conditional decoding and specific controls. Extensive experiments can demonstrate the controllability of the proposed ControlAR for the autoregressive control-to-image generation across diverse inputs, including edges, depths, and segmentation masks. Furthermore, both quantitative and qualitative results indicate that ControlAR surpasses previous state-of-the-art controllable diffusion models, e.g., ControlNet++. Code, models, and demo will soon be available at https://github.com/hustvl/ControlAR.
Authors: Hongxiang Zhang, Yifeng He, Hao Chen
Abstract: Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused to produce inappropriate content. Existing safety measures, which typically rely on text classifiers or ControlNet-like approaches, are often insufficient. Traditional text classifiers rely on large-scale labeled datasets and can be easily bypassed by rephrasing. As diffusion models continue to scale, fine-tuning these safeguards becomes increasingly challenging and lacks flexibility. Recent red-teaming attack researches further underscore the need for a new paradigm to prevent the generation of inappropriate content. In this paper, we introduce SteerDiff, a lightweight adaptor module designed to act as an intermediary between user input and the diffusion model, ensuring that generated images adhere to ethical and safety standards with little to no impact on usability. SteerDiff identifies and manipulates inappropriate concepts within the text embedding space to guide the model away from harmful outputs. We conduct extensive experiments across various concept unlearning tasks to evaluate the effectiveness of our approach. Furthermore, we benchmark SteerDiff against multiple red-teaming strategies to assess its robustness. Finally, we explore the potential of SteerDiff for concept forgetting tasks, demonstrating its versatility in text-conditioned image generation.
Authors: Tianyi Xiong, Xiyao Wang, Dong Guo, Qinghao Ye, Haoqi Fan, Quanquan Gu, Heng Huang, Chunyuan Li
Abstract: We introduce LLaVA-Critic, the first open-source large multimodal model (LMM) designed as a generalist evaluator to assess performance across a wide range of multimodal tasks. LLaVA-Critic is trained using a high-quality critic instruction-following dataset that incorporates diverse evaluation criteria and scenarios. Our experiments demonstrate the model's effectiveness in two key areas: (1) LMM-as-a-Judge, where LLaVA-Critic provides reliable evaluation scores, performing on par with or surpassing GPT models on multiple evaluation benchmarks; and (2) Preference Learning, where it generates reward signals for preference learning, enhancing model alignment capabilities. This work underscores the potential of open-source LMMs in self-critique and evaluation, setting the stage for future research into scalable, superhuman alignment feedback mechanisms for LMMs.
Authors: Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun Ma, Ziwei Liu, Chunyuan Li
Abstract: The development of video large multimodal models (LMMs) has been hindered by the difficulty of curating large amounts of high-quality raw data from the web. To address this, we propose an alternative approach by creating a high-quality synthetic dataset specifically for video instruction-following, namely LLaVA-Video-178K. This dataset includes key tasks such as detailed captioning, open-ended question-answering (QA), and multiple-choice QA. By training on this dataset, in combination with existing visual instruction tuning data, we introduce LLaVA-Video, a new video LMM. Our experiments demonstrate that LLaVA-Video achieves strong performance across various video benchmarks, highlighting the effectiveness of our dataset. We plan to release the dataset, its generation pipeline, and the model checkpoints.
Authors: Mengxi Wu, Hao Huang, Yi Fang, Mohammad Rostami
Abstract: Unsupervised Domain Adaptation (UDA) is crucial for reducing the need for extensive manual data annotation when training deep networks on point cloud data. A significant challenge of UDA lies in effectively bridging the domain gap. To tackle this challenge, we propose \textbf{C}urvature \textbf{D}iversity-Driven \textbf{N}uclear-Norm Wasserstein \textbf{D}omain Alignment (CDND). Our approach first introduces a \textit{\textbf{Curv}ature Diversity-driven Deformation \textbf{Rec}onstruction (CurvRec)} task, which effectively mitigates the gap between the source and target domains by enabling the model to extract salient features from semantically rich regions of a given point cloud. We then propose \textit{\textbf{D}eformation-based \textbf{N}uclear-norm \textbf{W}asserstein \textbf{D}iscrepancy (D-NWD)}, which applies the Nuclear-norm Wasserstein Discrepancy to both \textit{deformed and original} data samples to align the source and target domains. Furthermore, we contribute a theoretical justification for the effectiveness of D-NWD in distribution alignment and demonstrate that it is \textit{generic} enough to be applied to \textbf{any} deformations. To validate our method, we conduct extensive experiments on two public domain adaptation datasets for point cloud classification and segmentation tasks. Empirical experiment results show that our CDND achieves state-of-the-art performance by a noticeable margin over existing approaches.
Authors: Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu
Abstract: Object navigation in unknown environments is crucial for deploying embodied agents in real-world applications. While we have witnessed huge progress due to large-scale scene datasets, faster simulators, and stronger models, previous studies mainly focus on limited scene types and target objects. In this paper, we study a new task of navigating to diverse target objects in a large number of scene types. To benchmark the problem, we present a large-scale scene dataset, DivScene, which contains 4,614 scenes across 81 different types. With the dataset, we build an end-to-end embodied agent, NatVLM, by fine-tuning a Large Vision Language Model (LVLM) through imitation learning. The LVLM is trained to take previous observations from the environment and generate the next actions. We also introduce CoT explanation traces of the action prediction for better performance when tuning LVLMs. Our extensive experiments find that we can build a performant LVLM-based agent through imitation learning on the shortest paths constructed by a BFS planner without any human supervision. Our agent achieves a success rate that surpasses GPT-4o by over 20%. Meanwhile, we carry out various analyses showing the generalization ability of our agent.
Authors: Zhengfeng Lai, Vasileios Saveris, Chen Chen, Hong-You Chen, Haotian Zhang, Bowen Zhang, Juan Lao Tebar, Wenze Hu, Zhe Gan, Peter Grasch, Meng Cao, Yinfei Yang
Abstract: Recent advancements in multimodal models highlight the value of rewritten captions for improving performance, yet key challenges remain. For example, while synthetic captions often provide superior quality and image-text alignment, it is not clear whether they can fully replace AltTexts: the role of synthetic captions and their interaction with original web-crawled AltTexts in pre-training is still not well understood. Moreover, different multimodal foundation models may have unique preferences for specific caption formats, but efforts to identify the optimal captions for each model remain limited. In this work, we propose a novel, controllable, and scalable captioning pipeline designed to generate diverse caption formats tailored to various multimodal models. By examining Short Synthetic Captions (SSC) towards Dense Synthetic Captions (DSC+) as case studies, we systematically explore their effects and interactions with AltTexts across models such as CLIP, multimodal LLMs, and diffusion models. Our findings reveal that a hybrid approach that keeps both synthetic captions and AltTexts can outperform the use of synthetic captions alone, improving both alignment and performance, with each model demonstrating preferences for particular caption formats. This comprehensive analysis provides valuable insights into optimizing captioning strategies, thereby advancing the pre-training of multimodal foundation models.
Authors: Zhibin Lan, Liqiang Niu, Fandong Meng, Wenbo Li, Jie Zhou, Jinsong Su
Abstract: Recently, when dealing with high-resolution images, dominant LMMs usually divide them into multiple local images and one global image, which will lead to a large number of visual tokens. In this work, we introduce AVG-LLaVA, an LMM that can adaptively select the appropriate visual granularity based on the input image and instruction. This approach not only reduces the number of visual tokens and speeds up inference, but also improves the overall model performance. Specifically, we introduce the following modules based on LLaVA-NeXT: (a) a visual granularity scaler that includes multiple pooling layers to obtain visual tokens with different granularities; (b) a visual granularity router, which includes a Transformer layer, an MLP layer, and a voter layer, used to select the appropriate visual granularity based on the image and instruction. Furthermore, we propose RGLF, a novel training paradigm that aims at aligning the granularity predicted by the router with the preferences of the LMM, without the need for additional manually annotated data. Extensive experiments and analysis show that AVG-LLaVA achieves superior performance across 11 benchmarks, as well as significantly reduces the number of visual tokens and speeds up inference (e.g., an 85.3% reduction in visual tokens and a 2.53$\times$ increase in inference speed on the AI2D benchmark).
Authors: Hong-You Chen, Zhengfeng Lai, Haotian Zhang, Xinze Wang, Marcin Eichner, Keen You, Meng Cao, Bowen Zhang, Yinfei Yang, Zhe Gan
Abstract: Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone of multimodal large language models (MLLMs) to connect image inputs for language interactions. The success of CLIP as a vision-language foundation model relies on aligning web-crawled noisy text annotations at image levels. Nevertheless, such criteria may become insufficient for downstream tasks in need of fine-grained vision representations, especially when region-level understanding is demanding for MLLMs. In this paper, we improve the localization capability of CLIP with several advances. We propose a pre-training method called Contrastive Localized Language-Image Pre-training (CLOC) by complementing CLIP with region-text contrastive loss and modules. We formulate a new concept, promptable embeddings, of which the encoder produces image embeddings easy to transform into region representations given spatial hints. To support large-scale pre-training, we design a visually-enriched and spatially-localized captioning framework to effectively generate region-text pseudo-labels at scale. By scaling up to billions of annotated images, CLOC enables high-quality regional embeddings for image region recognition and retrieval tasks, and can be a drop-in replacement of CLIP to enhance MLLMs, especially on referring and grounding tasks.
Authors: Yuqing Wang, Tianwei Xiong, Daquan Zhou, Zhijie Lin, Yang Zhao, Bingyi Kang, Jiashi Feng, Xihui Liu
Abstract: It is desirable but challenging to generate content-rich long videos in the scale of minutes. Autoregressive large language models (LLMs) have achieved great success in generating coherent and long sequences of tokens in the domain of natural language processing, while the exploration of autoregressive LLMs for video generation is limited to generating short videos of several seconds. In this work, we conduct a deep analysis of the challenges that prevent autoregressive LLM-based video generators from generating long videos. Based on the observations and analysis, we propose Loong, a new autoregressive LLM-based video generator that can generate minute-long videos. Specifically, we model the text tokens and video tokens as a unified sequence for autoregressive LLMs and train the model from scratch. We propose progressive short-to-long training with a loss re-weighting scheme to mitigate the loss imbalance problem for long video training. We further investigate inference strategies, including video token re-encoding and sampling strategies, to diminish error accumulation during inference. Our proposed Loong can be trained on 10-second videos and be extended to generate minute-level long videos conditioned on text prompts, as demonstrated by the results. More samples are available at: https://epiphqny.github.io/Loong-video.
Authors: Zhipei Xu, Xuanyu Zhang, Runyi Li, Zecheng Tang, Qing Huang, Jian Zhang
Abstract: The rapid development of generative AI is a double-edged sword, which not only facilitates content creation but also makes image manipulation easier and more difficult to detect. Although current image forgery detection and localization (IFDL) methods are generally effective, they tend to face two challenges: \textbf{1)} black-box nature with unknown detection principle, \textbf{2)} limited generalization across diverse tampering methods (e.g., Photoshop, DeepFake, AIGC-Editing). To address these issues, we propose the explainable IFDL task and design FakeShield, a multi-modal framework capable of evaluating image authenticity, generating tampered region masks, and providing a judgment basis based on pixel-level and image-level tampering clues. Additionally, we leverage GPT-4o to enhance existing IFDL datasets, creating the Multi-Modal Tamper Description dataSet (MMTD-Set) for training FakeShield's tampering analysis capabilities. Meanwhile, we incorporate a Domain Tag-guided Explainable Forgery Detection Module (DTE-FDM) and a Multi-modal Forgery Localization Module (MFLM) to address various types of tamper detection interpretation and achieve forgery localization guided by detailed textual descriptions. Extensive experiments demonstrate that FakeShield effectively detects and localizes various tampering techniques, offering an explainable and superior solution compared to previous IFDL methods.
Authors: Nick Jiang, Anish Kachinthaya, Suzie Petryk, Yossi Gandelsman
Abstract: We investigate the internal representations of vision-language models (VLMs) to address hallucinations, a persistent challenge despite advances in model size and training. We project VLMs' internal image representations to their language vocabulary and observe more confident output probabilities on real objects than hallucinated objects. We additionally use these output probabilities to spatially localize real objects. Building on this approach, we introduce a knowledge erasure algorithm that removes hallucinations by linearly orthogonalizing image features with respect to hallucinated object features. We show that targeted edits to a model's latent representations can reduce hallucinations by up to 25.7% on the COCO2014 dataset while preserving performance. Our findings demonstrate how a deeper understanding of VLMs' latent representations can enhance reliability and enable novel capabilities, such as zero-shot segmentation.
Authors: Jianrui Zhang, Mu Cai, Yong Jae Lee
Abstract: There has been growing sentiment recently that modern large multimodal models (LMMs) have addressed most of the key challenges related to short video comprehension. As a result, both academia and industry are gradually shifting their attention towards the more complex challenges posed by understanding long-form videos. However, is this really the case? Our studies indicate that LMMs still lack many fundamental reasoning capabilities even when dealing with short videos. We introduce Vinoground, a temporal counterfactual LMM evaluation benchmark encompassing 1000 short and natural video-caption pairs. We demonstrate that existing LMMs severely struggle to distinguish temporal differences between different actions and object transformations. For example, the best model GPT-4o only obtains ~50% on our text and video scores, showing a large gap compared to the human baseline of ~90%. All open-source multimodal models and CLIP-based models perform much worse, producing mostly random chance performance. Through this work, we shed light onto the fact that temporal reasoning in short videos is a problem yet to be fully solved. The dataset and evaluation code are available at https://vinoground.github.io.
Authors: Mingyang Xie, Haoming Cai, Sachin Shah, Yiran Xu, Brandon Y. Feng, Jia-Bin Huang, Christopher A. Metzler
Abstract: We introduce a simple yet effective approach for separating transmitted and reflected light. Our key insight is that the powerful novel view synthesis capabilities provided by modern inverse rendering methods (e.g.,~3D Gaussian splatting) allow one to perform flash/no-flash reflection separation using unpaired measurements -- this relaxation dramatically simplifies image acquisition over conventional paired flash/no-flash reflection separation methods. Through extensive real-world experiments, we demonstrate our method, Flash-Splat, accurately reconstructs both transmitted and reflected scenes in 3D. Our method outperforms existing 3D reflection separation methods, which do not leverage illumination control, by a large margin. Our project webpage is at https://flash-splat.github.io/.
Authors: Olga Glazunova, Cecile J. A. Wolfs, Frank Verhaegen
Abstract: Objective: Radiotherapy uses precise doses of radiation to treat cancer, requiring accurate verification, e.g. using the Electronic Portal Imaging Device (EPID), to guide treatment. To develop an effective artificial intelligence (AI) model for error detection and treatment verification, a large and well-annotated dataset of EPID images is needed, however, acquiring such high quality real data is difficult. While synthetic EPID data could be a viable alternative, it is critical to ensure that this data is as realistic as possible to effectively train an accurate and reliable AI model. The measurement uncertainty that is not modeled in EPID predictions but is present on real measured EPID images can hinder downstream tasks such as error detection and classification. Our research aims to improve synthetic EPID data through image-to-image (I2I) translation based on deep generative modeling. Approach: A dataset of 989 predicted EPID images and corresponding measured EPID images was used. We evaluate both paired and unpaired generative modeling approaches for this task. For the former, we introduce a novel modification of Variational Autoencoder (VAE) to I2I, a method that, to the best of our knowledge, has not been previously explored for this task. For the latter, we use UNsupervised Image-to-Image Translation Networks (UNIT). Results: Our results show that both models achieved some degree of I2I translation, with our novel modification of the VAE model outperforming the UNIT model in improving key metrics (mean absolute error: 4.1 cGy vs 6.4 cGy; relative dose difference in-field: 2.5% vs 5.5%; absolute dose difference in-field: 5.3 cGy vs 10.8 cGy). Significance: This enhanced synthetic data is expected to improve downstream tasks such as training neural networks for automated error detection and error classification in radiotherapy.
Authors: Rikathi Pal, Anik Basu Bhaumik, Arpan Murmu, Sanoar Hossain, Biswajit Maity, Soumya Sen
Abstract: Diseases in plants cause significant danger to productive and secure agriculture. Plant diseases can be detected early and accurately, reducing crop losses and pesticide use. Traditional methods of plant disease identification, on the other hand, are generally time-consuming and require professional expertise. It would be beneficial to the farmers if they could detect the disease quickly by taking images of the leaf directly. This will be a time-saving process and they can take remedial actions immediately. To achieve this a novel feature extraction approach for detecting tomato plant illnesses from leaf photos using low-cost computing systems such as mobile phones is proposed in this study. The proposed approach integrates various types of Deep Learning techniques to extract robust and discriminative features from leaf images. After the proposed feature extraction comparisons have been made on five cutting-edge deep learning models: AlexNet, ResNet50, VGG16, VGG19, and MobileNet. The dataset contains 10,000 leaf photos from ten classes of tomato illnesses and one class of healthy leaves. Experimental findings demonstrate that AlexNet has an accuracy score of 87%, with the benefit of being quick and lightweight, making it appropriate for use on embedded systems and other low-processing devices like smartphones.
Authors: Vasilis Siomos, Sergio Naval-Marimont, Jonathan Passerat-Palmbach, Giacomo Tarroni
Abstract: Federated learning is a decentralized collaborative training paradigm that preserves stakeholders' data ownership while improving performance and generalization. However, statistical heterogeneity among client datasets poses a fundamental challenge by degrading system performance. To address this issue, we propose Adaptive Normalization-free Feature Recalibration (ANFR), an architecture-level approach that combines weight standardization and channel attention. Weight standardization normalizes the weights of layers instead of activations. This is less susceptible to mismatched client statistics and inconsistent averaging, thereby more robust under heterogeneity. Channel attention produces learnable scaling factors for feature maps, suppressing those that are inconsistent between clients due to heterogeneity. We demonstrate that combining these techniques boosts model performance beyond their individual contributions, by enhancing class selectivity and optimizing channel attention weight distribution. ANFR operates independently of the aggregation method and is effective in both global and personalized federated learning settings, with minimal computational overhead. Furthermore, when training with differential privacy, ANFR achieves an appealing balance between privacy and utility, enabling strong privacy guarantees without sacrificing performance. By integrating weight standardization and channel attention in the backbone model, ANFR offers a novel and versatile approach to the challenge of statistical heterogeneity. We demonstrate through extensive experiments that ANFR consistently outperforms established baselines across various aggregation methods, datasets, and heterogeneity conditions.
Authors: Lie Ju, Siyuan Yan, Yukun Zhou, Yang Nan, Xiaodan Xing, Peibo Duan, Zongyuan Ge
Abstract: Long-tailed learning is considered to be an extremely challenging problem in data imbalance learning. It aims to train well-generalized models from a large number of images that follow a long-tailed class distribution. In the medical field, many diagnostic imaging exams such as dermoscopy and chest radiography yield a long-tailed distribution of complex clinical findings. Recently, long-tailed learning in medical image analysis has garnered significant attention. However, the field currently lacks a unified, strictly formulated, and comprehensive benchmark, which often leads to unfair comparisons and inconclusive results. To help the community improve the evaluation and advance, we build a unified, well-structured codebase called Medical OpeN-source Long-taIled ClassifiCAtion (MONICA), which implements over 30 methods developed in relevant fields and evaluated on 12 long-tailed medical datasets covering 6 medical domains. Our work provides valuable practical guidance and insights for the field, offering detailed analysis and discussion on the effectiveness of individual components within the inbuilt state-of-the-art methodologies. We hope this codebase serves as a comprehensive and reproducible benchmark, encouraging further advancements in long-tailed medical image learning. The codebase is publicly available on https://github.com/PyJulie/MONICA.
Authors: Mahmudul Hasan, Xiaoling Hu, Shahira Abousamra, Prateek Prasanna, Joel Saltz, Chao Chen
Abstract: Despite the strong prediction power of deep learning models, their interpretability remains an important concern. Disentanglement models increase interpretability by decomposing the latent space into interpretable subspaces. In this paper, we propose the first disentanglement method for pathology images. We focus on the task of detecting tumor-infiltrating lymphocytes (TIL). We propose different ideas including cascading disentanglement, novel architecture, and reconstruction branches. We achieve superior performance on complex pathology images, thus improving the interpretability and even generalization power of TIL detection deep learning models. Our codes are available at https://github.com/Shauqi/SS-cVAE.
Authors: Amir-Hossein Shahidzadeh, Gabriele Caddeo, Koushik Alapati, Lorenzo Natale, Cornelia Ferm\"uller, Yiannis Aloimonos
Abstract: In this paper, we tackle the problem of estimating 3D contact forces using vision-based tactile sensors. In particular, our goal is to estimate contact forces over a large range (up to 15 N) on any objects while generalizing across different vision-based tactile sensors. Thus, we collected a dataset of over 200K indentations using a robotic arm that pressed various indenters onto a GelSight Mini sensor mounted on a force sensor and then used the data to train a multi-head transformer for force regression. Strong generalization is achieved via accurate data collection and multi-objective optimization that leverages depth contact images. Despite being trained only on primitive shapes and textures, the regressor achieves a mean absolute error of 4\% on a dataset of unseen real-world objects. We further evaluate our approach's generalization capability to other GelSight mini and DIGIT sensors, and propose a reproducible calibration procedure for adapting the pre-trained model to other vision-based sensors. Furthermore, the method was evaluated on real-world tasks, including weighing objects and controlling the deformation of delicate objects, which relies on accurate force feedback. Project webpage: http://prg.cs.umd.edu/FeelAnyForce
Authors: Xiao Yu, Baolin Peng, Vineeth Vajipey, Hao Cheng, Michel Galley, Jianfeng Gao, Zhou Yu
Abstract: Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such as GPT-4o, still fall short of human-level performance, particularly in intricate web environments and long-horizon planning tasks. To address these limitations, we introduce Reflective Monte Carlo Tree Search (R-MCTS), a novel test-time algorithm designed to enhance the ability of AI agents, e.g., powered by GPT-4o, to explore decision space on the fly. R-MCTS extends traditional MCTS by 1) incorporating contrastive reflection, allowing agents to learn from past interactions and dynamically improve their search efficiency; and 2) using multi-agent debate to provide reliable state evaluation. Moreover, we improve the agent's performance by fine-tuning GPT-4o through self-learning, using R-MCTS generated tree traversals without any human-provided labels. On the challenging VisualWebArena benchmark, our GPT-4o-based R-MCTS agent achieves a 6% to 30% relative improvement across various tasks compared to the previous state-of-the-art. Additionally, we show that the knowledge gained from test-time search can be effectively transferred back to GPT-4o via fine-tuning. The fine-tuned GPT-4o matches 97% of R-MCTS's performance while reducing compute usage by a factor of four at test time. Furthermore, qualitative results reveal that the fine-tuned GPT-4o model demonstrates the ability to explore the environment, evaluate a state, and backtrack to viable ones when it detects that the current state cannot lead to success. Moreover, our work demonstrates the compute scaling properties in both training - data collection with R-MCTS - and testing time. These results suggest a promising research direction to enhance VLMs' reasoning and planning capabilities for agentic applications via test-time search and self-learning.
Authors: Mohammadamin Moradi, Shirin Panahi, Erik Bollt, Ying-Cheng Lai
Abstract: Deep learning models have revolutionized various domains, with Multi-Layer Perceptrons (MLPs) being a cornerstone for tasks like data regression and image classification. However, a recent study has introduced Kolmogorov-Arnold Networks (KANs) as promising alternatives to MLPs, leveraging activation functions placed on edges rather than nodes. This structural shift aligns KANs closely with the Kolmogorov-Arnold representation theorem, potentially enhancing both model accuracy and interpretability. In this study, we explore the efficacy of KANs in the context of data representation via autoencoders, comparing their performance with traditional Convolutional Neural Networks (CNNs) on the MNIST, SVHN, and CIFAR-10 datasets. Our results demonstrate that KAN-based autoencoders achieve competitive performance in terms of reconstruction accuracy, thereby suggesting their viability as effective tools in data analysis tasks.
Authors: Vishal Purohit, Matthew Repasky, Jianfeng Lu, Qiang Qiu, Yao Xie, Xiuyuan Cheng
Abstract: Posterior sampling in high-dimensional spaces using generative models holds significant promise for various applications, including but not limited to inverse problems and guided generation tasks. Despite many recent developments, generating diverse posterior samples remains a challenge, as existing methods require restarting the entire generative process for each new sample, making the procedure computationally expensive. In this work, we propose efficient posterior sampling by simulating Langevin dynamics in the noise space of a pre-trained generative model. By exploiting the mapping between the noise and data spaces which can be provided by distilled flows or consistency models, our method enables seamless exploration of the posterior without the need to re-run the full sampling chain, drastically reducing computational overhead. Theoretically, we prove a guarantee for the proposed noise-space Langevin dynamics to approximate the posterior, assuming that the generative model sufficiently approximates the prior distribution. Our framework is experimentally validated on image restoration tasks involving noisy linear and nonlinear forward operators applied to LSUN-Bedroom (256 x 256) and ImageNet (64 x 64) datasets. The results demonstrate that our approach generates high-fidelity samples with enhanced semantic diversity even under a limited number of function evaluations, offering superior efficiency and performance compared to existing diffusion-based posterior sampling techniques.
Authors: Minoh Jeong, Min Namgung, Zae Myung Kim, Dongyeop Kang, Yao-Yi Chiang, Alfred Hero
Abstract: Multimodal learning plays a crucial role in enabling machine learning models to fuse and utilize diverse data sources, such as text, images, and audio, to support a variety of downstream tasks. A unified representation across various modalities is particularly important for improving efficiency and performance. Recent binding methods, such as ImageBind (Girdhar et al., 2023), typically use a fixed anchor modality to align multimodal data in the anchor modal embedding space. In this paper, we mathematically analyze the fixed anchor binding methods and uncover notable limitations: (1) over-reliance on the choice of the anchor modality, (2) failure to capture intra-modal information, and (3) failure to account for inter-modal correlation among non-anchored modalities. To address these limitations, we propose CentroBind, a simple yet powerful approach that eliminates the need for a fixed anchor; instead, it employs dynamically adjustable centroid-based anchors generated from all available modalities, resulting in a balanced and rich representation space. We theoretically demonstrate that our method captures three crucial properties of multimodal learning: intra-modal learning, inter-modal learning, and multimodal alignment, while also constructing a robust unified representation across all modalities. Our experiments on both synthetic and real-world datasets demonstrate the superiority of the proposed method, showing that dynamic anchor methods outperform all fixed anchor binding methods as the former captures more nuanced multimodal interactions.
Authors: Sabine Muzellec, Drew Linsley, Alekh K. Ashok, Ennio Mingolla, Girik Malik, Rufin VanRullen, Thomas Serre
Abstract: Objects we encounter often change appearance as we interact with them. Changes in illumination (shadows), object pose, or movement of nonrigid objects can drastically alter available image features. How do biological visual systems track objects as they change? It may involve specific attentional mechanisms for reasoning about the locations of objects independently of their appearances -- a capability that prominent neuroscientific theories have associated with computing through neural synchrony. We computationally test the hypothesis that the implementation of visual attention through neural synchrony underlies the ability of biological visual systems to track objects that change in appearance over time. We first introduce a novel deep learning circuit that can learn to precisely control attention to features separately from their location in the world through neural synchrony: the complex-valued recurrent neural network (CV-RNN). Next, we compare object tracking in humans, the CV-RNN, and other deep neural networks (DNNs), using FeatureTracker: a large-scale challenge that asks observers to track objects as their locations and appearances change in precisely controlled ways. While humans effortlessly solved FeatureTracker, state-of-the-art DNNs did not. In contrast, our CV-RNN behaved similarly to humans on the challenge, providing a computational proof-of-concept for the role of phase synchronization as a neural substrate for tracking appearance-morphing objects as they move about.
Authors: Jin Yang, Daniel S. Marcus, Aristeidis Sotiras
Abstract: Convolutional neural networks (CNNs) have shown great effectiveness in medical image segmentation. However, they may be limited in modeling large inter-subject variations in organ shapes and sizes and exploiting global long-range contextual information. This is because CNNs typically employ convolutions with fixed-sized local receptive fields and lack the mechanisms to utilize global information. To address these limitations, we developed Dynamic Multi-Resolution Convolution (DMRC) and Dynamic Multi-Scale Convolution (DMSC) modules. Both modules enhance the representation capabilities of single convolutions to capture varying scaled features and global contextual information. This is achieved in the DMRC module by employing a convolutional filter on images with different resolutions and subsequently utilizing dynamic mechanisms to model global inter-dependencies between features. In contrast, the DMSC module extracts features at different scales by employing convolutions with different kernel sizes and utilizing dynamic mechanisms to extract global contextual information. The utilization of convolutions with different kernel sizes in the DMSC module may increase computational complexity. To lessen this burden, we propose to use a lightweight design for convolution layers with a large kernel size. Thus, DMSC and DMRC modules are designed as lightweight drop-in replacements for single convolutions, and they can be easily integrated into general CNN architectures for end-to-end training. The segmentation network was proposed by incorporating our DMSC and DMRC modules into a standard U-Net architecture, termed Dynamic Multi-scale and Multi-resolution Convolution network (DMC-Net). The results demonstrate that our proposed DMSC and DMRC can enhance the representation capabilities of single convolutions and improve segmentation accuracy.
Authors: Trung X. Pham, Tri Ton, Chang D. Yoo
Abstract: We introduce MDSGen, a novel framework for vision-guided open-domain sound generation optimized for model parameter size, memory consumption, and inference speed. This framework incorporates two key innovations: (1) a redundant video feature removal module that filters out unnecessary visual information, and (2) a temporal-aware masking strategy that leverages temporal context for enhanced audio generation accuracy. In contrast to existing resource-heavy Unet-based models, MDSGen employs denoising masked diffusion transformers, facilitating efficient generation without reliance on pre-trained diffusion models. Evaluated on the benchmark VGGSound dataset, our smallest model (5M parameters) achieves 97.9% alignment accuracy, using 172x fewer parameters, 371% less memory, and offering 36x faster inference than the current 860M-parameter state-of-the-art model (93.9% accuracy). The larger model (131M parameters) reaches nearly 99% accuracy while requiring 6.5x fewer parameters. These results highlight the scalability and effectiveness of our approach.
Authors: Wanpeng Zhang, Zilong Xie, Yicheng Feng, Yijiang Li, Xingrun Xing, Sipeng Zheng, Zongqing Lu
Abstract: Multimodal Large Language Models have made significant strides in integrating visual and textual information, yet they often struggle with effectively aligning these modalities. We introduce a novel image tokenizer that bridges this gap by applying the principle of Byte-Pair Encoding (BPE) to visual data. Unlike conventional approaches that rely on separate visual encoders, our method directly incorporates structural prior information into image tokens, mirroring the successful tokenization strategies used in text-only Large Language Models. This innovative approach enables Transformer models to more effectively learn and reason across modalities. Through theoretical analysis and extensive experiments, we demonstrate that our BPE Image Tokenizer significantly enhances MLLMs' multimodal understanding capabilities, even with limited training data. Our method not only improves performance across various benchmarks but also shows promising scalability, potentially paving the way for more efficient and capable multimodal foundation models.
Authors: Saurabh Singh, Ian Fischer
Abstract: Deterministic flow models, such as rectified flows, offer a general framework for learning a deterministic transport map between two distributions, realized as the vector field for an ordinary differential equation (ODE). However, they are sensitive to model estimation and discretization errors and do not permit different samples conditioned on an intermediate state, limiting their application. We present a general method to turn the underlying ODE of such flow models into a family of stochastic differential equations (SDEs) that have the same marginal distributions. This method permits us to derive families of \emph{stochastic samplers}, for fixed (e.g., previously trained) \emph{deterministic} flow models, that continuously span the spectrum of deterministic and stochastic sampling, given access to the flow field and the score function. Our method provides additional degrees of freedom that help alleviate the issues with the deterministic samplers and empirically outperforms them. We empirically demonstrate advantages of our method on a toy Gaussian setup and on the large scale ImageNet generation task. Further, our family of stochastic samplers provide an additional knob for controlling the diversity of generation, which we qualitatively demonstrate in our experiments.
Authors: Arvin Tashakori, Zenan Jiang, Amir Servati, Saeid Soltanian, Harishkumar Narayana, Katherine Le, Caroline Nakayama, Chieh-ling Yang, Z. Jane Wang, Janice J. Eng, Peyman Servati
Abstract: Accurate real-time tracking of dexterous hand movements and interactions has numerous applications in human-computer interaction, metaverse, robotics, and tele-health. Capturing realistic hand movements is challenging because of the large number of articulations and degrees of freedom. Here, we report accurate and dynamic tracking of articulated hand and finger movements using stretchable, washable smart gloves with embedded helical sensor yarns and inertial measurement units. The sensor yarns have a high dynamic range, responding to low 0.005 % to high 155 % strains, and show stability during extensive use and washing cycles. We use multi-stage machine learning to report average joint angle estimation root mean square errors of 1.21 and 1.45 degrees for intra- and inter-subjects cross-validation, respectively, matching accuracy of costly motion capture cameras without occlusion or field of view limitations. We report a data augmentation technique that enhances robustness to noise and variations of sensors. We demonstrate accurate tracking of dexterous hand movements during object interactions, opening new avenues of applications including accurate typing on a mock paper keyboard, recognition of complex dynamic and static gestures adapted from American Sign Language and object identification.
Authors: Tianchi Xie, Jiangning Zhu, Guozu Ma, Minzhi Lin, Wei Chen, Weikai Yang, Shixia Liu
Abstract: Sample selection improves the efficiency and effectiveness of machine learning models by providing informative and representative samples. Typically, samples can be modeled as a sample graph, where nodes are samples and edges represent their similarities. Most existing methods are based on local information, such as the training difficulty of samples, thereby overlooking global information, such as connectivity patterns. This oversight can result in suboptimal selection because global information is crucial for ensuring that the selected samples well represent the structural properties of the graph. To address this issue, we employ structural entropy to quantify global information and losslessly decompose it from the whole graph to individual nodes using the Shapley value. Based on the decomposition, we present $\textbf{S}$tructural-$\textbf{E}$ntropy-based sample $\textbf{S}$election ($\textbf{SES}$), a method that integrates both global and local information to select informative and representative samples. SES begins by constructing a $k$NN-graph among samples based on their similarities. It then measures sample importance by combining structural entropy (global metric) with training difficulty (local metric). Finally, SES applies importance-biased blue noise sampling to select a set of diverse and representative samples. Comprehensive experiments on three learning scenarios -- supervised learning, active learning, and continual learning -- clearly demonstrate the effectiveness of our method.
Authors: Genta Indra Winata, David Anugraha, Lucky Susanto, Garry Kuwanto, Derry Tanti Wijaya
Abstract: Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metric captures the diverse aspects of these preferences, as metrics often excel in one particular area but not across all dimensions. To address this, it is essential to systematically calibrate metrics to specific aspects of human preference, catering to the unique characteristics of each aspect. We introduce MetaMetrics, a calibrated meta-metric designed to evaluate generation tasks across different modalities in a supervised manner. MetaMetrics optimizes the combination of existing metrics to enhance their alignment with human preferences. Our metric demonstrates flexibility and effectiveness in both language and vision downstream tasks, showing significant benefits across various multilingual and multi-domain scenarios. MetaMetrics aligns closely with human preferences and is highly extendable and easily integrable into any application. This makes MetaMetrics a powerful tool for improving the evaluation of generation tasks, ensuring that metrics are more representative of human judgment across diverse contexts.
Authors: Seyedmorteza Sadat, Otmar Hilliges, Romann M. Weber
Abstract: Classifier-free guidance (CFG) is crucial for improving both generation quality and alignment between the input condition and final output in diffusion models. While a high guidance scale is generally required to enhance these aspects, it also causes oversaturation and unrealistic artifacts. In this paper, we revisit the CFG update rule and introduce modifications to address this issue. We first decompose the update term in CFG into parallel and orthogonal components with respect to the conditional model prediction and observe that the parallel component primarily causes oversaturation, while the orthogonal component enhances image quality. Accordingly, we propose down-weighting the parallel component to achieve high-quality generations without oversaturation. Additionally, we draw a connection between CFG and gradient ascent and introduce a new rescaling and momentum method for the CFG update rule based on this insight. Our approach, termed adaptive projected guidance (APG), retains the quality-boosting advantages of CFG while enabling the use of higher guidance scales without oversaturation. APG is easy to implement and introduces practically no additional computational overhead to the sampling process. Through extensive experiments, we demonstrate that APG is compatible with various conditional diffusion models and samplers, leading to improved FID, recall, and saturation scores while maintaining precision comparable to CFG, making our method a superior plug-and-play alternative to standard classifier-free guidance.
Authors: Ramy Mounir, Sudeep Sarkar
Abstract: Sequential memory, the ability to form and accurately recall a sequence of events or stimuli in the correct order, is a fundamental prerequisite for biological and artificial intelligence as it underpins numerous cognitive functions (e.g., language comprehension, planning, episodic memory formation, etc.) However, existing methods of sequential memory suffer from catastrophic forgetting, limited capacity, slow iterative learning procedures, low-order Markov memory, and, most importantly, the inability to represent and generate multiple valid future possibilities stemming from the same context. Inspired by biologically plausible neuroscience theories of cognition, we propose \textit{Predictive Attractor Models (PAM)}, a novel sequence memory architecture with desirable generative properties. PAM is a streaming model that learns a sequence in an online, continuous manner by observing each input \textit{only once}. Additionally, we find that PAM avoids catastrophic forgetting by uniquely representing past context through lateral inhibition in cortical minicolumns, which prevents new memories from overwriting previously learned knowledge. PAM generates future predictions by sampling from a union set of predicted possibilities; this generative ability is realized through an attractor model trained alongside the predictor. We show that PAM is trained with local computations through Hebbian plasticity rules in a biologically plausible framework. Other desirable traits (e.g., noise tolerance, CPU-based learning, capacity scaling) are discussed throughout the paper. Our findings suggest that PAM represents a significant step forward in the pursuit of biologically plausible and computationally efficient sequential memory models, with broad implications for cognitive science and artificial intelligence research.
Authors: Gurucharan Marthi Krishna Kumar, Aman Chadha, Janine Mendola, Amir Shmuel
Abstract: Large Language Models (LLMs), known for their versatility in textual data, are increasingly being explored for their potential to enhance medical image segmentation, a crucial task for accurate diagnostic imaging. This study explores enhancing Vision Transformers (ViTs) for medical image segmentation by integrating pre-trained LLM transformer blocks. Our approach, which incorporates a frozen LLM transformer block into the encoder of a ViT-based model, leads to substantial improvements in segmentation performance across various medical imaging modalities. We propose a Hybrid Attention Mechanism that combines global and local feature learning with a Multi-Scale Fusion Block for aggregating features across different scales. The enhanced model shows significant performance gains, including an average Dice score increase from 0.74 to 0.79 and improvements in accuracy, precision, and the Jaccard Index. These results demonstrate the effectiveness of LLM-based transformers in refining medical image segmentation, highlighting their potential to significantly boost model accuracy and robustness. The source code and our implementation are available at: https://bit.ly/3zf2CVs
URLs: https://bit.ly/3zf2CVs
Authors: Yunhao Chen, Xingjun Ma, Difan Zou, Yu-Gang Jiang
Abstract: As diffusion probabilistic models (DPMs) are being employed as mainstream models for Generative Artificial Intelligence (GenAI), the study of their memorization of training data has attracted growing attention. Existing works in this direction aim to establish an understanding of whether or to what extent DPMs learn via memorization. Such an understanding is crucial for identifying potential risks of data leakage and copyright infringement in diffusion models and, more importantly, for trustworthy application of GenAI. Existing works revealed that conditional DPMs are more prone to training data memorization than unconditional DPMs, and the motivated data extraction methods are mostly for conditional DPMs. However, these understandings are primarily empirical, and extracting training data from unconditional models has been found to be extremely challenging. In this work, we provide a theoretical understanding of memorization in both conditional and unconditional DPMs under the assumption of model convergence. Our theoretical analysis indicates that extracting data from unconditional models can also be effective by constructing a proper surrogate condition. Based on this result, we propose a novel data extraction method named \textbf{Surrogate condItional Data Extraction (SIDE)} that leverages a time-dependent classifier trained on the generated data as a surrogate condition to extract training data from unconditional DPMs. Empirical results demonstrate that our SIDE can extract training data in challenging scenarios where previous methods fail, and it is, on average, over 50\% more effective across different scales of the CelebA dataset.
Authors: Jiashu Xu
Abstract: Medical image segmentation plays a crucial role in clinical diagnosis and treatment planning. Although models based on convolutional neural networks (CNNs) and Transformers have achieved remarkable success in medical image segmentation tasks, they still face challenges such as high computational complexity and the loss of local features when capturing long-range dependencies. To address these limitations, we propose Med-TTT, a visual backbone network integrated with Test-Time Training (TTT) layers, which incorporates dynamic adjustment capabilities. Med-TTT introduces the Vision-TTT layer, which enables effective modeling of long-range dependencies with linear computational complexity and adaptive parameter adjustment during inference. Furthermore, we designed a multi-resolution fusion mechanism to combine image features at different scales, facilitating the identification of subtle lesion characteristics in complex backgrounds. At the same time, we adopt a frequency domain feature enhancement strategy based on high pass filtering, which can better capture texture and fine-grained details in images. Experimental results demonstrate that Med-TTT significantly outperforms existing methods on multiple medical image datasets, exhibiting strong segmentation capabilities, particularly in complex image backgrounds. The model achieves leading performance in terms of accuracy, sensitivity, and Dice coefficient, providing an efficient and robust solution for the field of medical image segmentation.The code is available at https://github.com/Jiashu-Xu/Med-TTT .
Authors: James Walsh, Daniel G. Gass, Raul Ramos Pollan, Paul J. Wright, Richard Galvez, Noah Kasmanoff, Jason Naradowsky, Anne Spalding, James Parr, At{\i}l{\i}m G\"une\c{s} Baydin
Abstract: SDO-FM is a foundation model using data from NASA's Solar Dynamics Observatory (SDO) spacecraft; integrating three separate instruments to encapsulate the Sun's complex physical interactions into a multi-modal embedding space. This model can be used to streamline scientific investigations involving SDO by making the enormous datasets more computationally accessible for heliophysics research and enable investigations that require instrument fusion. We discuss four key components: an ingestion pipeline to create machine learning ready datasets, the model architecture and training approach, resultant embeddings and fine-tunable models, and finally downstream fine-tuned applications. A key component of this effort has been to include subject matter specialists at each stage of development; reviewing the scientific value and providing guidance for model architecture, dataset, and training paradigm decisions. This paper marks release of our pretrained models and embedding datasets, available to the community on Hugging Face and sdofm.org.
Authors: Gurucharan Marthi Krishna Kumar, Janine Mendola, Amir Shmuel
Abstract: Deformable image registration is crucial for aligning medical images in a non-linear fashion across different modalities, allowing for precise spatial correspondence between varying anatomical structures. This paper presents NestedMorph, a novel network utilizing a Nested Attention Fusion approach to improve intra-subject deformable registration between T1-weighted (T1w) MRI and diffusion MRI (dMRI) data. NestedMorph integrates high-resolution spatial details from an encoder with semantic information from a decoder using a multi-scale framework, enhancing both local and global feature extraction. Our model notably outperforms existing methods, including CNN-based approaches like VoxelMorph, MIDIR, and CycleMorph, as well as Transformer-based models such as TransMorph and ViT-V-Net, and traditional techniques like NiftyReg and SyN. Evaluations on the HCP dataset demonstrate that NestedMorph achieves superior performance across key metrics, including SSIM, HD95, and SDlogJ, with the highest SSIM of 0.89, and the lowest HD95 of 2.5 and SDlogJ of 0.22. These results highlight NestedMorph's ability to capture both local and global image features effectively, leading to superior registration performance. The promising outcomes of this study underscore NestedMorph's potential to significantly advance deformable medical image registration, providing a robust framework for future research and clinical applications. The source code and our implementation are available at: https://bit.ly/3zdVqcg
URLs: https://bit.ly/3zdVqcg
Authors: Marco S\'anchez-Beeckman (IAC3 & Departament de Matem\`atiques i Inform\`atica, Universitat de les Illes Balears), Antoni Buades (IAC3 & Departament de Matem\`atiques i Inform\`atica, Universitat de les Illes Balears), Nicola Brandonisio (Huawei Technologies France), Bilel Kanoun (Huawei Technologies France)
Abstract: Denoising is one of the fundamental steps of the processing pipeline that converts data captured by a camera sensor into a display-ready image or video. It is generally performed early in the pipeline, usually before demosaicking, although studies swapping their order or even conducting them jointly have been proposed. With the advent of deep learning, the quality of denoising algorithms has steadily increased. Even so, modern neural networks still have a hard time adapting to new noise levels and scenes, which is indispensable for real-world applications. With those in mind, we propose a self-similarity-based denoising scheme that weights both a pre- and a post-demosaicking denoiser for Bayer-patterned CFA video data. We show that a balance between the two leads to better image quality, and we empirically find that higher noise levels benefit from a higher influence pre-demosaicking. We also integrate temporal trajectory prefiltering steps before each denoiser, which further improve texture reconstruction. The proposed method only requires an estimation of the noise model at the sensor, accurately adapts to any noise level, and is competitive with the state of the art, making it suitable for real-world videography.
Authors: Ming Lu, Zhihao Duan, Wuyang Cong, Dandan Ding, Fengqing Zhu, Zhan Ma
Abstract: The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods but also impressive complexity efficiency, enabling real-time processing with a significantly smaller memory footprint on standard GPUs. These remarkable advancements stem from the use of hierarchical predictive coding. Each video frame is uniformly transformed into multiscale representations through hierarchical variational autoencoders. For a specific scale's feature representation of a frame, its corresponding latent residual variables are generated by referencing lower-scale spatial features from the same frame and then conditionally entropy-encoded using a probabilistic model whose parameters are predicted using same-scale temporal reference from previous frames and lower-scale spatial reference of the current frame. This feature-space processing operates from the lowest to the highest scale of each frame, completely eliminating the need for the complexity-intensive motion estimation and compensation techniques that have been standard in video codecs for decades. The hierarchical approach facilitates parallel processing, accelerating both encoding and decoding, and supports transmission-friendly progressive decoding, making it particularly advantageous for networked video applications in the presence of packet loss. Source codes will be made available.
Authors: Mayank Daswani, Mathias M. J. Bellaiche, Marc Wilson, Desislav Ivanov, Mikhail Papkov, Eva Schnider, Jing Tang, Kay Lamerigts, Gabriela Botea, Michael A. Sanchez, Yojan Patel, Shruthi Prabhakara, Shravya Shetty, Umesh Telang
Abstract: While multimodal foundation models can now natively work with data beyond text, they remain underutilized in analyzing the considerable amounts of multi-dimensional time-series data in fields like healthcare, finance, and social sciences, representing a missed opportunity for richer, data-driven insights. This paper proposes a simple but effective method that leverages the existing vision encoders of these models to "see" time-series data via plots, avoiding the need for additional, potentially costly, model training. Our empirical evaluations show that this approach outperforms providing the raw time-series data as text, with the additional benefit that visual time-series representations demonstrate up to a 90% reduction in model API costs. We validate our hypothesis through synthetic data tasks of increasing complexity, progressing from simple functional form identification on clean data, to extracting trends from noisy scatter plots. To demonstrate generalizability from synthetic tasks with clear reasoning steps to more complex, real-world scenarios, we apply our approach to consumer health tasks - specifically fall detection, activity recognition, and readiness assessment - which involve heterogeneous, noisy data and multi-step reasoning. The overall success in plot performance over text performance (up to an 120% performance increase on zero-shot synthetic tasks, and up to 150% performance increase on real-world tasks), across both GPT and Gemini model families, highlights our approach's potential for making the best use of the native capabilities of foundation models.
Authors: Zhiyuan Li, Yanhui Zhou, Hao Wei, Chenyang Ge, Ajmal Mian
Abstract: Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both fidelity and efficiency. To address these two issues, we present Relay Residual Diffusion Extreme Image Compression (RDEIC), which leverages compressed feature initialization and residual diffusion. Specifically, we first use the compressed latent features of the image with added noise, instead of pure noise, as the starting point to eliminate the unnecessary initial stages of the denoising process. Second, we design a novel relay residual diffusion that reconstructs the raw image by iteratively removing the added noise and the residual between the compressed and target latent features. Notably, our relay residual diffusion network seamlessly integrates pre-trained stable diffusion to leverage its robust generative capability for high-quality reconstruction. Third, we propose a fixed-step fine-tuning strategy to eliminate the discrepancy between the training and inference phases, further improving the reconstruction quality. Extensive experiments demonstrate that the proposed RDEIC achieves state-of-the-art visual quality and outperforms existing diffusion-based extreme image compression methods in both fidelity and efficiency. The source code will be provided in https://github.com/huai-chang/RDEIC.
Authors: Nikolaos Stathoulopoulos, Vidya Sumathy, Christoforos Kanellakis, George Nikolakopoulos
Abstract: Recent advances in robotics are pushing real-world autonomy, enabling robots to perform long-term and large-scale missions. A crucial component for successful missions is the incorporation of loop closures through place recognition, which effectively mitigates accumulated pose estimation drift. Despite computational advancements, optimizing performance for real-time deployment remains challenging, especially in resource-constrained mobile robots and multi-robot systems since, conventional keyframe sampling practices in place recognition often result in retaining redundant information or overlooking relevant data, as they rely on fixed sampling intervals or work directly in the 3D space instead of the feature space. To address these concerns, we introduce the concept of sample space in place recognition and demonstrate how different sampling techniques affect the query process and overall performance. We then present a novel keyframe sampling approach for LiDAR-based place recognition, which focuses on redundancy minimization and information preservation in the hyper-dimensional descriptor space. This approach is applicable to both learning-based and handcrafted descriptors, and through the experimental validation across multiple datasets and descriptor frameworks, we demonstrate the effectiveness of our proposed method, showing it can jointly minimize redundancy and preserve essential information in real-time. The proposed approach maintains robust performance across various datasets without requiring parameter tuning, contributing to more efficient and reliable place recognition for a wide range of robotic applications.
Authors: Somesh Singh, Yaman K Singla, Harini SI, Balaji Krishnamurthy
Abstract: LLMs are increasingly being used in workflows involving generating content to be consumed by humans (e.g., marketing) and also in directly interacting with humans (e.g., through chatbots). The development of such systems that are capable of generating verifiably persuasive messages presents both opportunities and challenges for society. On the one hand, such systems could positively impact domains like advertising and social good, such as addressing drug addiction, and on the other, they could be misused for spreading misinformation and shaping political opinions. To channel LLMs' impact on society, we need to develop systems to measure and benchmark their persuasiveness. With this motivation, we introduce PersuasionBench and PersuasionArena, the first large-scale benchmark and arena containing a battery of tasks to measure the persuasion ability of generative models automatically. We investigate to what extent LLMs know and leverage linguistic patterns that can help them generate more persuasive language. Our findings indicate that the persuasiveness of LLMs correlates positively with model size, but smaller models can also be made to have a higher persuasiveness than much larger models. Notably, targeted training using synthetic and natural datasets significantly enhances smaller models' persuasive capabilities, challenging scale-dependent assumptions. Our findings carry key implications for both model developers and policymakers. For instance, while the EU AI Act and California's SB-1047 aim to regulate AI models based on the number of floating point operations, we demonstrate that simple metrics like this alone fail to capture the full scope of AI's societal impact. We invite the community to explore and contribute to PersuasionArena and PersuasionBench, available at https://bit.ly/measure-persuasion, to advance our understanding of AI-driven persuasion and its societal implications.
Authors: Zakhar Shumaylov, Peter Zaika, James Rowbottom, Ferdia Sherry, Melanie Weber, Carola-Bibiane Sch\"onlieb
Abstract: The quest for robust and generalizable machine learning models has driven recent interest in exploiting symmetries through equivariant neural networks. In the context of PDE solvers, recent works have shown that Lie point symmetries can be a useful inductive bias for Physics-Informed Neural Networks (PINNs) through data and loss augmentation. Despite this, directly enforcing equivariance within the model architecture for these problems remains elusive. This is because many PDEs admit non-compact symmetry groups, oftentimes not studied beyond their infinitesimal generators, making them incompatible with most existing equivariant architectures. In this work, we propose Lie aLgebrA Canonicalization (LieLAC), a novel approach that exploits only the action of infinitesimal generators of the symmetry group, circumventing the need for knowledge of the full group structure. To achieve this, we address existing theoretical issues in the canonicalization literature, establishing connections with frame averaging in the case of continuous non-compact groups. Operating within the framework of canonicalization, LieLAC can easily be integrated with unconstrained pre-trained models, transforming inputs to a canonical form before feeding them into the existing model, effectively aligning the input for model inference according to allowed symmetries. LieLAC utilizes standard Lie group descent schemes, achieving equivariance in pre-trained models. Finally, we showcase LieLAC's efficacy on tasks of invariant image classification and Lie point symmetry equivariant neural PDE solvers using pre-trained models.
Authors: Romoke Grace Akindele, Samuel Adebayo, Paul Shekonya Kanda, Ming Yu
Abstract: Alzheimer's disease (AD) is a progressive neurodegenerative disorder with increasing prevalence among the aging population, necessitating early and accurate diagnosis for effective disease management. In this study, we present a novel hybrid deep learning framework that integrates both 2D Convolutional Neural Networks (2D-CNN) and 3D Convolutional Neural Networks (3D-CNN), along with a custom loss function and volumetric data augmentation, to enhance feature extraction and improve classification performance in AD diagnosis. According to extensive experiments, AlzhiNet outperforms standalone 2D and 3D models, highlighting the importance of combining these complementary representations of data. The depth and quality of 3D volumes derived from the augmented 2D slices also significantly influence the model's performance. The results indicate that carefully selecting weighting factors in hybrid predictions is imperative for achieving optimal results. Our framework has been validated on the Magnetic Resonance Imaging (MRI) from Kaggle and MIRIAD datasets, obtaining accuracies of 98.9% and 99.99%, respectively, with an AUC of 100%. Furthermore, AlzhiNet was studied under a variety of perturbation scenarios on the Alzheimer's Kaggle dataset, including Gaussian noise, brightness, contrast, salt and pepper noise, color jitter, and occlusion. The results obtained show that AlzhiNet is more robust to perturbations than ResNet-18, making it an excellent choice for real-world applications. This approach represents a promising advancement in the early diagnosis and treatment planning for Alzheimer's disease.
Authors: Jefferson Hernandez, Ruben Villegas, Vicente Ordonez
Abstract: We propose ViC-MAE, a model that combines both Masked AutoEncoders (MAE) and contrastive learning. ViC-MAE is trained using a global featured obtained by pooling the local representations learned under an MAE reconstruction loss and leveraging this representation under a contrastive objective across images and video frames. We show that visual representations learned under ViC-MAE generalize well to both video and image classification tasks. Particularly, ViC-MAE obtains state-of-the-art transfer learning performance from video to images on Imagenet-1k compared to the recently proposed OmniMAE by achieving a top-1 accuracy of 86% (+1.3% absolute improvement) when trained on the same data and 87.1% (+2.4% absolute improvement) when training on extra data. At the same time ViC-MAE outperforms most other methods on video benchmarks by obtaining 75.9% top-1 accuracy on the challenging Something something-v2 video benchmark . When training on videos and images from a diverse combination of datasets, our method maintains a balanced transfer-learning performance between video and image classification benchmarks, coming only as a close second to the best supervised method.
Authors: Julio Silva-Rodr\'iguez, Jose Dolz, Ismail Ben Ayed
Abstract: The recent popularity of foundation models and the pre-train-and-adapt paradigm, where a large-scale model is transferred to downstream tasks, is gaining attention for volumetric medical image segmentation. However, current transfer learning strategies devoted to full fine-tuning for transfer learning may require significant resources and yield sub-optimal results when the labeled data of the target task is scarce. This makes its applicability in real clinical settings challenging since these institutions are usually constrained on data and computational resources to develop proprietary solutions. To address this challenge, we formalize Few-Shot Efficient Fine-Tuning (FSEFT), a novel and realistic scenario for adapting medical image segmentation foundation models. This setting considers the key role of both data- and parameter- efficiency during adaptation. Building on a foundation model pre-trained on open-access CT organ segmentation sources, we propose leveraging Parameter-Efficient Fine-Tuning and black-box Adapters to address such challenges. Furthermore, novel efficient adaptation methodologies are introduced in this work, which include Spatial black-box Adapters that are more appropriate for dense prediction tasks and constrained transductive inference, leveraging task-specific prior knowledge. Our comprehensive transfer learning experiments confirm the suitability of foundation models in medical image segmentation and unveil the limitations of popular fine-tuning strategies in few-shot scenarios.
Authors: Taorong Liu, Liang Liao, Delin Chen, Jing Xiao, Zheng Wang, Chia-Wen Lin, Shin'ichi Satoh
Abstract: Image inpainting for completing complicated semantic environments and diverse hole patterns of corrupted images is challenging even for state-of-the-art learning-based inpainting methods trained on large-scale data. A reference image capturing the same scene of a corrupted image offers informative guidance for completing the corrupted image as it shares similar texture and structure priors to that of the holes of the corrupted image. In this work, we propose a transformer-based encoder-decoder network, named TransRef, for reference-guided image inpainting. Specifically, the guidance is conducted progressively through a reference embedding procedure, in which the referencing features are subsequently aligned and fused with the features of the corrupted image. For precise utilization of the reference features for guidance, a reference-patch alignment (Ref-PA) module is proposed to align the patch features of the reference and corrupted images and harmonize their style differences, while a reference-patch transformer (Ref-PT) module is proposed to refine the embedded reference feature. Moreover, to facilitate the research of reference-guided image restoration tasks, we construct a publicly accessible benchmark dataset containing 50K pairs of input and reference images. Both quantitative and qualitative evaluations demonstrate the efficacy of the reference information and the proposed method over the state-of-the-art methods in completing complex holes. Code and dataset can be accessed at https://github.com/Cameltr/TransRef.
Authors: Yiran Wang, Min Shi, Jiaqi Li, Chaoyi Hong, Zihao Huang, Juewen Peng, Zhiguo Cao, Jianming Zhang, Ke Xian, Guosheng Lin
Abstract: Video depth estimation aims to infer temporally consistent depth. One approach is to finetune a single-image model on each video with geometry constraints, which proves inefficient and lacks robustness. An alternative is learning to enforce consistency from data, which requires well-designed models and sufficient video depth data. To address both challenges, we introduce NVDS+ that stabilizes inconsistent depth estimated by various single-image models in a plug-and-play manner. We also elaborate a large-scale Video Depth in the Wild (VDW) dataset, which contains 14,203 videos with over two million frames, making it the largest natural-scene video depth dataset. Additionally, a bidirectional inference strategy is designed to improve consistency by adaptively fusing forward and backward predictions. We instantiate a model family ranging from small to large scales for different applications. The method is evaluated on VDW dataset and three public benchmarks. To further prove the versatility, we extend NVDS+ to video semantic segmentation and several downstream applications like bokeh rendering, novel view synthesis, and 3D reconstruction. Experimental results show that our method achieves significant improvements in consistency, accuracy, and efficiency. Our work serves as a solid baseline and data foundation for learning-based video depth estimation. Code and dataset are available at: https://github.com/RaymondWang987/NVDS
Authors: G. Madhuri, Atul Negi, Kaluri V. Rangarao
Abstract: Dimensionality reduction-based dictionary learning methods in the literature have often used iterative random projections. The dimensionality of such a random projection matrix is a random number that might not lead to a separable subspace structure in the transformed space. The convergence of such methods highly depends on the initial seed values used. Also, gradient descent-based updates might result in local minima. This paper proposes a constructive approach to derandomize the projection matrix using the Johnson-Lindenstrauss lemma. Rather than reducing dimensionality via random projections, a projection matrix derived from the proposed Modified Supervised PC analysis is used. A heuristic is proposed to decide the data perturbation levels and the dictionary atom's corresponding suitable description length. The projection matrix is derived in a single step, provides maximum feature-label consistency of the transformed space, and preserves the geometry of the original data. The projection matrix thus constructed is proved to be a JL-embedding. Despite confusing classes in the OCR datasets, the dictionary trained in the transformed space generates discriminative sparse coefficients with reduced complexity. Empirical study demonstrates that the proposed method performs well even when the number of classes and dimensionality increase. Experimentation on OCR and face recognition datasets shows better classification performance than other algorithms.
Authors: Li Li, Qingqing Li, Guozheng Xu, Pengwei Zhou, Jingmin Tu, Jie Li, Mingming Li, Jian Yao
Abstract: Roof plane segmentation from airborne LiDAR point clouds is an important technology for 3D building model reconstruction. One of the key issues of plane segmentation is how to design powerful features that can exactly distinguish adjacent planar patches. The quality of point feature directly determines the accuracy of roof plane segmentation. Most of existing approaches use handcrafted features to extract roof planes. However, the abilities of these features are relatively low, especially in boundary area. To solve this problem, we propose a boundary-aware point clustering approach in Euclidean and embedding spaces constructed by a multi-task deep network for roof plane segmentation. We design a three-branch network to predict semantic labels, point offsets and extract deep embedding features. In the first branch, we classify the input data as non-roof, boundary and plane points. In the second branch, we predict point offsets for shifting each point toward its respective instance center. In the third branch, we constrain that points of the same plane instance should have the similar embeddings. We aim to ensure that points of the same plane instance are close as much as possible in both Euclidean and embedding spaces. However, although deep network has strong feature representative ability, it is still hard to accurately distinguish points near plane instance boundary. Therefore, we first group plane points into many clusters in the two spaces, and then we assign the rest boundary points to their closest clusters to generate final complete roof planes. In this way, we can effectively reduce the influence of unreliable boundary points. In addition, we prepare a synthetic dataset and two real datasets to train and evaluate our approach. The experiments results show that the proposed approach significantly outperforms the existing state-of-the-art approaches.
Authors: Hiroki Nakamura, Masashi Okada, Tadahiro Taniguchi
Abstract: In this paper, we propose a new self-supervised learning (SSL) method for representations that enable logic operations. Representation learning has been applied to various tasks, such as image generation and retrieval. The logical controllability of representations is important for these tasks. Although some methods have been shown to enable the intuitive control of representations using natural languages as the inputs, representation control via logic operations between representations has not been demonstrated. Some SSL methods using representation synthesis (e.g., elementwise mean and maximum operations) have been proposed, but the operations performed in these methods do not incorporate logic operations. In this work, we propose a logic-operable self-supervised representation learning method by replacing the existing representation synthesis with the OR operation on the probabilistic extension of many-valued logic. The representations comprise a set of feature-possession degrees, which are truth values indicating the presence or absence of each feature in the image, and realize the logic operations (e.g., OR and AND). Our method can generate a representation that has the features of both representations or only those features common to both representations. In addition, the expression of the ambiguous presence of a feature is realized by indicating the feature-possession degree by the probability distribution of truth values of the many-valued logic. We showed that our method performs competitively in single and multi-label classification tasks compared with prior SSL methods using synthetic representations. Moreover, experiments on image retrieval using MNIST and PascalVOC showed that the representations of our method can be operated by OR and AND operations.
Authors: Xinyu Zhang, Yuhan Liu, Yuting Wang, Abdeslam Boularias
Abstract: Few-shot object detection aims at detecting novel categories given only a few example images. It is a basic skill for a robot to perform tasks in open environments. Recent methods focus on finetuning strategies, with complicated procedures that prohibit a wider application. In this paper, we introduce DE-ViT, a few-shot object detector without the need for finetuning. DE-ViT's novel architecture is based on a new region-propagation mechanism for localization. The propagated region masks are transformed into bounding boxes through a learnable spatial integral layer. Instead of training prototype classifiers, we propose to use prototypes to project ViT features into a subspace that is robust to overfitting on base classes. We evaluate DE-ViT on few-shot, and one-shot object detection benchmarks with Pascal VOC, COCO, and LVIS. DE-ViT establishes new state-of-the-art results on all benchmarks. Notably, for COCO, DE-ViT surpasses the few-shot SoTA by 15 mAP on 10-shot and 7.2 mAP on 30-shot and one-shot SoTA by 2.8 AP50. For LVIS, DE-ViT outperforms few-shot SoTA by 17 box APr. Further, we evaluate DE-ViT with a real robot by building a pick-and-place system for sorting novel objects based on example images. The videos of our robot demonstrations, the source code and the models of DE-ViT can be found at https://mlzxy.github.io/devit.
Authors: Xu Yuan, Zheng Zhang, Xunguang Wang, Lin Wu
Abstract: Deep hashing has been intensively studied and successfully applied in large-scale image retrieval systems due to its efficiency and effectiveness. Recent studies have recognized that the existence of adversarial examples poses a security threat to deep hashing models, that is, adversarial vulnerability. Notably, it is challenging to efficiently distill reliable semantic representatives for deep hashing to guide adversarial learning, and thereby it hinders the enhancement of adversarial robustness of deep hashing-based retrieval models. Moreover, current researches on adversarial training for deep hashing are hard to be formalized into a unified minimax structure. In this paper, we explore Semantic-Aware Adversarial Training (SAAT) for improving the adversarial robustness of deep hashing models. Specifically, we conceive a discriminative mainstay features learning (DMFL) scheme to construct semantic representatives for guiding adversarial learning in deep hashing. Particularly, our DMFL with the strict theoretical guarantee is adaptively optimized in a discriminative learning manner, where both discriminative and semantic properties are jointly considered. Moreover, adversarial examples are fabricated by maximizing the Hamming distance between the hash codes of adversarial samples and mainstay features, the efficacy of which is validated in the adversarial attack trials. Further, we, for the first time, formulate the formalized adversarial training of deep hashing into a unified minimax optimization under the guidance of the generated mainstay codes. Extensive experiments on benchmark datasets show superb attack performance against the state-of-the-art algorithms, meanwhile, the proposed adversarial training can effectively eliminate adversarial perturbations for trustworthy deep hashing-based retrieval. Our code is available at https://github.com/xandery-geek/SAAT.
Authors: Animesh Sinha, Bo Sun, Anmol Kalia, Arantxa Casanova, Elliot Blanchard, David Yan, Winnie Zhang, Tony Nelli, Jiahui Chen, Hardik Shah, Licheng Yu, Mitesh Kumar Singh, Ankit Ramchandani, Maziar Sanjabi, Sonal Gupta, Amy Bearman, Dhruv Mahajan
Abstract: We introduce Style Tailoring, a recipe to finetune Latent Diffusion Models (LDMs) in a distinct domain with high visual quality, prompt alignment and scene diversity. We choose sticker image generation as the target domain, as the images significantly differ from photorealistic samples typically generated by large-scale LDMs. We start with a competent text-to-image model, like Emu, and show that relying on prompt engineering with a photorealistic model to generate stickers leads to poor prompt alignment and scene diversity. To overcome these drawbacks, we first finetune Emu on millions of sticker-like images collected using weak supervision to elicit diversity. Next, we curate human-in-the-loop (HITL) Alignment and Style datasets from model generations, and finetune to improve prompt alignment and style alignment respectively. Sequential finetuning on these datasets poses a tradeoff between better style alignment and prompt alignment gains. To address this tradeoff, we propose a novel fine-tuning method called Style Tailoring, which jointly fits the content and style distribution and achieves best tradeoff. Evaluation results show our method improves visual quality by 14%, prompt alignment by 16.2% and scene diversity by 15.3%, compared to prompt engineering the base Emu model for stickers generation.
Authors: Keunwoo Peter Yu, Zheyuan Zhang, Fengyuan Hu, Shane Storks, Joyce Chai
Abstract: A major reason behind the recent success of large language models (LLMs) is their \textit{in-context learning} capability, which makes it possible to rapidly adapt them to downstream text-based tasks by prompting them with a small number of relevant demonstrations. While large vision-language models (VLMs) have recently been developed for tasks requiring both text and images, they largely lack in-context learning over visual information, especially in understanding and generating text about videos. In this work, we implement \textbf{E}mergent \textbf{I}n-context \textbf{Le}arning on \textbf{V}ideos (\eilev{}), a novel training paradigm that induces in-context learning over video and text by capturing key properties of pre-training data found by prior work to be essential for in-context learning in transformers. In our experiments, we show that \eilev-trained models outperform other off-the-shelf VLMs in few-shot video narration for novel, rare actions. Furthermore, we demonstrate that these key properties of bursty distributions, skewed marginal distributions, and dynamic meaning each contribute to varying degrees to VLMs' in-context learning capability in narrating procedural videos. Our results, analysis, and \eilev{}-trained models yield numerous insights about the emergence of in-context learning over video and text, creating a foundation for future work to optimize and scale VLMs for open-domain video understanding and reasoning. Our code and demo are available at \url{https://github.com/yukw777/EILEV}.
Authors: Christian Benz, Volker Rodehorst
Abstract: To effectively assess structural damage, it is essential to localize the instances of damage in the physical world of a civil structure. ENSTRECT is a stage-based approach designed to accomplish 2.5D structural damage detection. The method requires an image collection, the relative orientation, and a point cloud. Using these inputs, surface damages are segmented at the image level and then mapped into the point cloud space, resulting in a segmented point cloud. To enable further quantitative analyses, the segmented point cloud is transformed into measurable damage instances: cracks are extracted by contracting the clustered point cloud into a corresponding medial axis. For areal damages, such as spalling and corrosion, a procedure is proposed to compute the bounding polygon based on PCA and alpha shapes. With a localization tolerance of 4cm, ENSTRECT can achieve IoUs of over 90% for cracks, 82% for corrosion, and 41% for spalling. Detection at the instance level yields an AP50 of about 45% (cracks, spalling) and 56% (corrosion).
Authors: Tianyang Han, Qing Lian, Rui Pan, Renjie Pi, Jipeng Zhang, Shizhe Diao, Yong Lin, Tong Zhang
Abstract: Large language models (LLMs) have recently experienced remarkable progress, where the advent of multi-modal large language models (MLLMs) has endowed LLMs with visual capabilities, leading to impressive performances in various multi-modal tasks. However, those powerful MLLMs such as GPT-4V still fail spectacularly when presented with certain image and text inputs. In this paper, we identify a typical class of inputs that baffles MLLMs, which consist of images that are highly relevant but inconsistent with answers, causing MLLMs to suffer from visual illusion. To quantify the effect, we propose CorrelationQA, the first benchmark that assesses the visual illusion level given spurious images. This benchmark contains 7,308 text-image pairs across 13 categories. Based on the proposed CorrelationQA, we conduct a thorough analysis on 9 mainstream MLLMs, illustrating that they universally suffer from this instinctive bias to varying degrees. We hope that our curated benchmark and evaluation results aid in better assessments of the MLLMs' robustness in the presence of misleading images. The code and datasets are available at https://github.com/MasaiahHan/CorrelationQA.
Authors: Yuxuan Wang, Yueqian Wang, Pengfei Wu, Jianxin Liang, Dongyan Zhao, Yang Liu, Zilong Zheng
Abstract: Despite progress in multimodal large language models (MLLMs), the challenge of interpreting long-form videos in response to linguistic queries persists, largely due to the inefficiency in temporal grounding and limited pre-trained context window size. In this work, we introduce Temporal Grounding Bridge (TGB), a novel framework that bootstraps MLLMs with advanced temporal grounding capabilities and broadens their contextual scope. Our framework significantly enhances the temporal capabilities of current MLLMs through three key innovations: an efficient multi-span temporal grounding algorithm applied to low-dimension temporal features projected from flow; a multimodal length extrapolation training paradigm that utilizes low-dimension temporal features to extend the training context window size; and a bootstrapping framework that bridges our model with pluggable MLLMs without requiring annotation. We validate TGB across seven video benchmarks and demonstrate substantial performance improvements compared with prior MLLMs. Notably, our model, initially trained on sequences of four frames, effectively handles sequences up to 16 longer without sacrificing performance, highlighting its scalability and effectiveness in real-world applications. Our code is publicly available at https://github.com/bigai-nlco/VideoTGB
Authors: Jiayi Wu, Xiaomin Lin, Shahriar Negahdaripour, Cornelia Ferm\"uller, Yiannis Aloimonos
Abstract: Tasks such as autonomous navigation, 3D reconstruction, and object recognition near the water surfaces are crucial in marine robotics applications. However, challenges arise due to dynamic disturbances, e.g., light reflections and refraction from the random air-water interface, irregular liquid flow, and similar factors, which can lead to potential failures in perception and navigation systems. Traditional computer vision algorithms struggle to differentiate between real and virtual image regions, significantly complicating tasks. A virtual image region is an apparent representation formed by the redirection of light rays, typically through reflection or refraction, creating the illusion of an object's presence without its actual physical location. This work proposes a novel approach for segmentation on real and virtual image regions, exploiting synthetic images combined with domain-invariant information, a Motion Entropy Kernel, and Epipolar Geometric Consistency. Our segmentation network does not need to be re-trained if the domain changes. We show this by deploying the same segmentation network in two different domains: simulation and the real world. By creating realistic synthetic images that mimic the complexities of the water surface, we provide fine-grained training data for our network (MARVIS) to discern between real and virtual images effectively. By motion & geometry-aware design choices and through comprehensive experimental analysis, we achieve state-of-the-art real-virtual image segmentation performance in unseen real world domain, achieving an IoU over 78% and a F1-Score over 86% while ensuring a small computational footprint. MARVIS offers over 43 FPS (8 FPS) inference rates on a single GPU (CPU core). Our code and dataset are available here https://github.com/jiayi-wu-umd/MARVIS.
Authors: Alexander Hepburn, Raul Santos-Rodriguez, Javier Portilla
Abstract: The two-alternative forced choice (2AFC) experimental method is popular in the visual perception literature, where practitioners aim to understand how human observers perceive distances within triplets made of a reference image and two distorted versions. In the past, this had been conducted in controlled environments, with triplets sharing images, so it was possible to rank the perceived quality. This ranking would then be used to evaluate perceptual distance models against the experimental data. Recently, crowd-sourced perceptual datasets have emerged, with no images shared between triplets, making ranking infeasible. Evaluating perceptual distance models using this data reduces the judgements on a triplet to a binary decision, namely, whether the distance model agrees with the human decision - which is suboptimal and prone to misleading conclusions. Instead, we statistically model the underlying decision-making process during 2AFC experiments using a binomial distribution. Having enough empirical data, we estimate a smooth and consistent distribution of the judgements on the reference-distorted distance plane, according to each distance model. By applying maximum likelihood, we estimate the parameter of the local binomial distribution, and a global measurement of the expected log-likelihood of the measured responses. We calculate meaningful and well-founded metrics for the distance model, beyond the mere prediction accuracy as percentage agreement, even with variable numbers of judgements per triplet -- key advantages over both classical and neural network methods.
Authors: Ali Abedi, Shehroz S. Khan
Abstract: Engagement in virtual learning is crucial for a variety of factors including student satisfaction, performance, and compliance with learning programs, but measuring it is a challenging task. There is therefore considerable interest in utilizing artificial intelligence and affective computing to measure engagement in natural settings as well as on a large scale. This paper introduces a novel, privacy-preserving method for engagement measurement from videos. It uses facial landmarks, which carry no personally identifiable information, extracted from videos via the MediaPipe deep learning solution. The extracted facial landmarks are fed to Spatial-Temporal Graph Convolutional Networks (ST-GCNs) to output the engagement level of the student in the video. To integrate the ordinal nature of the engagement variable into the training process, ST-GCNs undergo training in a novel ordinal learning framework based on transfer learning. Experimental results on two video student engagement measurement datasets show the superiority of the proposed method compared to previous methods with improved state-of-the-art on the EngageNet dataset with a 3.1% improvement in four-class engagement level classification accuracy and on the Online Student Engagement dataset with a 1.5% improvement in binary engagement classification accuracy. Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to the developed ST-GCNs to interpret the engagement measurements obtained by the proposed method in both the spatial and temporal domains. The relatively lightweight and fast ST-GCN and its integration with the real-time MediaPipe make the proposed approach capable of being deployed on virtual learning platforms and measuring engagement in real-time.
Authors: Xingyu Zheng, Xianglong Liu, Haotong Qin, Xudong Ma, Mingyuan Zhang, Haojie Hao, Jiakai Wang, Zixiang Zhao, Jinyang Guo, Michele Magno
Abstract: With the advancement of diffusion models (DMs) and the substantially increased computational requirements, quantization emerges as a practical solution to obtain compact and efficient low-bit DMs. However, the highly discrete representation leads to severe accuracy degradation, hindering the quantization of diffusion models to ultra-low bit-widths. This paper proposes a novel weight binarization approach for DMs, namely BinaryDM, pushing binarized DMs to be accurate and efficient by improving the representation and optimization. From the representation perspective, we present an Evolvable-Basis Binarizer (EBB) to enable a smooth evolution of DMs from full-precision to accurately binarized. EBB enhances information representation in the initial stage through the flexible combination of multiple binary bases and applies regularization to evolve into efficient single-basis binarization. The evolution only occurs in the head and tail of the DM architecture to retain the stability of training. From the optimization perspective, a Low-rank Representation Mimicking (LRM) is applied to assist the optimization of binarized DMs. The LRM mimics the representations of full-precision DMs in low-rank space, alleviating the direction ambiguity of the optimization process caused by fine-grained alignment. Comprehensive experiments demonstrate that BinaryDM achieves significant accuracy and efficiency gains compared to SOTA quantization methods of DMs under ultra-low bit-widths. With 1-bit weight and 4-bit activation (W1A4), BinaryDM achieves as low as 7.74 FID and saves the performance from collapse (baseline FID 10.87). As the first binarization method for diffusion models, W1A4 BinaryDM achieves impressive 15.2x OPs and 29.2x model size savings, showcasing its substantial potential for edge deployment.
Authors: Jing Gu, Nanxuan Zhao, Wei Xiong, Qing Liu, Zhifei Zhang, He Zhang, Jianming Zhang, HyunJoon Jung, Yilin Wang, Xin Eric Wang
Abstract: Effective editing of personal content holds a pivotal role in enabling individuals to express their creativity, weaving captivating narratives within their visual stories, and elevate the overall quality and impact of their visual content. Therefore, in this work, we introduce SwapAnything, a novel framework that can swap any objects in an image with personalized concepts given by the reference, while keeping the context unchanged. Compared with existing methods for personalized subject swapping, SwapAnything has three unique advantages: (1) precise control of arbitrary objects and parts rather than the main subject, (2) more faithful preservation of context pixels, (3) better adaptation of the personalized concept to the image. First, we propose targeted variable swapping to apply region control over latent feature maps and swap masked variables for faithful context preservation and initial semantic concept swapping. Then, we introduce appearance adaptation, to seamlessly adapt the semantic concept into the original image in terms of target location, shape, style, and content during the image generation process. Extensive results on both human and automatic evaluation demonstrate significant improvements of our approach over baseline methods on personalized swapping. Furthermore, SwapAnything shows its precise and faithful swapping abilities across single object, multiple objects, partial object, and cross-domain swapping tasks. SwapAnything also achieves great performance on text-based swapping and tasks beyond swapping such as object insertion.
Authors: Wenyu Zhang, Li Shen, Chuan-Sheng Foo
Abstract: Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to a related but unlabeled target domain. While the source model is a key avenue for acquiring target pseudolabels, the generated pseudolabels may exhibit source bias. In the conventional SFDA pipeline, a large data (e.g. ImageNet) pre-trained feature extractor is used to initialize the source model at the start of source training, and subsequently discarded. Despite having diverse features important for generalization, the pre-trained feature extractor can overfit to the source data distribution during source training and forget relevant target domain knowledge. Rather than discarding this valuable knowledge, we introduce an integrated framework to incorporate pre-trained networks into the target adaptation process. The proposed framework is flexible and allows us to plug modern pre-trained networks into the adaptation process to leverage their stronger representation learning capabilities. For adaptation, we propose the Co-learn algorithm to improve target pseudolabel quality collaboratively through the source model and a pre-trained feature extractor. Building on the recent success of the vision-language model CLIP in zero-shot image recognition, we present an extension Co-learn++ to further incorporate CLIP's zero-shot classification decisions. We evaluate on 4 benchmark datasets and include more challenging scenarios such as open-set, partial-set and open-partial SFDA. Experimental results demonstrate that our proposed strategy improves adaptation performance and can be successfully integrated with existing SFDA methods. Project code is available at https://github.com/zwenyu/colearn-plus.
Authors: Zhu Yu, Runmin Zhang, Jiacheng Ying, Junchen Yu, Xiaohai Hu, Lun Luo, Si-Yuan Cao, Hui-Liang Shen
Abstract: Vision-based Semantic Scene Completion (SSC) has gained much attention due to its widespread applications in various 3D perception tasks. Existing sparse-to-dense approaches typically employ shared context-independent queries across various input images, which fails to capture distinctions among them as the focal regions of different inputs vary and may result in undirected feature aggregation of cross-attention. Additionally, the absence of depth information may lead to points projected onto the image plane sharing the same 2D position or similar sampling points in the feature map, resulting in depth ambiguity. In this paper, we present a novel context and geometry aware voxel transformer. It utilizes a context aware query generator to initialize context-dependent queries tailored to individual input images, effectively capturing their unique characteristics and aggregating information within the region of interest. Furthermore, it extend deformable cross-attention from 2D to 3D pixel space, enabling the differentiation of points with similar image coordinates based on their depth coordinates. Building upon this module, we introduce a neural network named CGFormer to achieve semantic scene completion. Simultaneously, CGFormer leverages multiple 3D representations (i.e., voxel and TPV) to boost the semantic and geometric representation abilities of the transformed 3D volume from both local and global perspectives. Experimental results demonstrate that CGFormer achieves state-of-the-art performance on the SemanticKITTI and SSCBench-KITTI-360 benchmarks, attaining a mIoU of 16.87 and 20.05, as well as an IoU of 45.99 and 48.07, respectively. Remarkably, CGFormer even outperforms approaches employing temporal images as inputs or much larger image backbone networks.
Authors: Minghao Guo, Bohan Wang, Kaiming He, Wojciech Matusik
Abstract: We introduce TetSphere Splatting, a Lagrangian geometry representation designed for high-quality 3D shape modeling. TetSphere splatting leverages an underused yet powerful geometric primitive -- volumetric tetrahedral meshes. It represents 3D shapes by deforming a collection of tetrahedral spheres, with geometric regularizations and constraints that effectively resolve common mesh issues such as irregular triangles, non-manifoldness, and floating artifacts. Experimental results on multi-view and single-view reconstruction highlight TetSphere splatting's superior mesh quality while maintaining competitive reconstruction accuracy compared to state-of-the-art methods. Additionally, TetSphere splatting demonstrates versatility by seamlessly integrating into generative modeling tasks, such as image-to-3D and text-to-3D generation.
Authors: Zeyi Sun, Tong Wu, Pan Zhang, Yuhang Zang, Xiaoyi Dong, Yuanjun Xiong, Dahua Lin, Jiaqi Wang
Abstract: Recent years have witnessed remarkable progress in multi-view diffusion models for 3D content creation. However, there remains a significant gap in image quality and prompt-following ability compared to 2D diffusion models. A critical bottleneck is the scarcity of high-quality 3D objects with detailed captions. To address this challenge, we propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images to assist in training multi-view diffusion models. Specifically, we introduce a data generation pipeline that employs (1) 2D and video diffusion models to generate multi-view images based on constructed text prompts, and (2) our fine-tuned 3D-aware MV-LLaVA for filtering high-quality data and rewriting inaccurate captions. Leveraging this pipeline, we have generated 1 million high-quality synthetic multi-view images with dense descriptive captions to address the shortage of high-quality 3D data. Furthermore, we present a Training Timestep Reschedule (TTR) strategy that leverages the denoising process to learn multi-view consistency while maintaining the original 2D diffusion prior. Extensive experiments demonstrate that Bootstrap3D can generate high-quality multi-view images with superior aesthetic quality, image-text alignment, and maintained view consistency.
Authors: Xiefan Guo, Jinlin Liu, Miaomiao Cui, Liefeng Bo, Di Huang
Abstract: Text-to-video generation has trailed behind text-to-image generation in terms of quality and diversity, primarily due to the inherent complexities of spatio-temporal modeling and the limited availability of video-text datasets. Recent text-to-video diffusion models employ the image as an intermediate step, significantly enhancing overall performance but incurring high training costs. In this paper, we present I4VGen, a novel video diffusion inference pipeline to leverage advanced image techniques to enhance pre-trained text-to-video diffusion models, which requires no additional training. Instead of the vanilla text-to-video inference pipeline, I4VGen consists of two stages: anchor image synthesis and anchor image-augmented text-to-video synthesis. Correspondingly, a simple yet effective generation-selection strategy is employed to achieve visually-realistic and semantically-faithful anchor image, and an innovative noise-invariant video score distillation sampling (NI-VSDS) is developed to animate the image to a dynamic video by distilling motion knowledge from video diffusion models, followed by a video regeneration process to refine the video. Extensive experiments show that the proposed method produces videos with higher visual realism and textual fidelity. Furthermore, I4VGen also supports being seamlessly integrated into existing image-to-video diffusion models, thereby improving overall video quality.
Authors: Hritik Bansal, Zongyu Lin, Tianyi Xie, Zeshun Zong, Michal Yarom, Yonatan Bitton, Chenfanfu Jiang, Yizhou Sun, Kai-Wei Chang, Aditya Grover
Abstract: Recent advances in internet-scale video data pretraining have led to the development of text-to-video generative models that can create high-quality videos across a broad range of visual concepts, synthesize realistic motions and render complex objects. Hence, these generative models have the potential to become general-purpose simulators of the physical world. However, it is unclear how far we are from this goal with the existing text-to-video generative models. To this end, we present VideoPhy, a benchmark designed to assess whether the generated videos follow physical commonsense for real-world activities (e.g. marbles will roll down when placed on a slanted surface). Specifically, we curate diverse prompts that involve interactions between various material types in the physical world (e.g., solid-solid, solid-fluid, fluid-fluid). We then generate videos conditioned on these captions from diverse state-of-the-art text-to-video generative models, including open models (e.g., CogVideoX) and closed models (e.g., Lumiere, Dream Machine). Our human evaluation reveals that the existing models severely lack the ability to generate videos adhering to the given text prompts, while also lack physical commonsense. Specifically, the best performing model, CogVideoX-5B, generates videos that adhere to the caption and physical laws for 39.6% of the instances. VideoPhy thus highlights that the video generative models are far from accurately simulating the physical world. Finally, we propose an auto-evaluator, VideoCon-Physics, to assess the performance reliably for the newly released models.
Authors: Sajjad Amini, Mohammadreza Teymoorianfard, Shiqing Ma, Amir Houmansadr
Abstract: We present a simple yet effective method to improve the robustness of both Convolutional and attention-based Neural Networks against adversarial examples by post-processing an adversarially trained model. Our technique, MeanSparse, cascades the activation functions of a trained model with novel operators that sparsify mean-centered feature vectors. This is equivalent to reducing feature variations around the mean, and we show that such reduced variations merely affect the model's utility, yet they strongly attenuate the adversarial perturbations and decrease the attacker's success rate. Our experiments show that, when applied to the top models in the RobustBench leaderboard, MeanSparse achieves a new robustness record of 75.28% (from 73.71%), 44.78% (from 42.67%) and 62.12% (from 59.56%) on CIFAR-10, CIFAR-100 and ImageNet, respectively, in terms of AutoAttack accuracy. Code is available at https://github.com/SPIN-UMass/MeanSparse
Authors: Jinnan Chen, Chen Li, Jianfeng Zhang, Lingting Zhu, Buzhen Huang, Hanlin Chen, Gim Hee Lee
Abstract: In this work, we tackle the task of learning generalizable 3D human Gaussians from a single image. The main challenge for this task is to recover detailed geometry and appearance, especially for the unobserved regions. To this end, we propose single-view generalizable Human Gaussian model (HGM), a diffusion-guided framework for 3D human modeling from a single image. We design a diffusion-based coarse-to-fine pipeline, where the diffusion model is adapted to refine novel-view images rendered from a coarse human Gaussian model. The refined images are then used together with the input image to learn a refined human Gaussian model. Although effective in hallucinating the unobserved views, the approach may generate unrealistic human pose and shapes due to the lack of supervision. We circumvent this problem by further encoding the geometric priors from SMPL model. Specifically, we propagate geometric features from SMPL volume to the predicted Gaussians via sparse convolution and attention mechanism. We validate our approach on publicly available datasets and demonstrate that it significantly surpasses state-of-the-art methods in terms of PSNR and SSIM. Additionally, our method exhibits strong generalization for in-the-wild images.
Authors: Felix O'Mahony, Yulong Yang, Christine Allen-Blanchette
Abstract: Group equivariant convolutional neural networks have been designed for a variety of geometric transformations from 2D and 3D rotation groups, to semi-groups such as scale. Despite the improved interpretability, accuracy and generalizability afforded by these architectures, group equivariant networks have seen limited application in the context of perceptual quantities such as hue and saturation, even though their variation can lead to significant reductions in classification performance. In this paper, we introduce convolutional neural networks equivariant to variations in hue and saturation by design. To achieve this, we leverage the observation that hue and saturation transformations can be identified with the 2D rotation and 1D translation groups respectively. Our hue-, saturation-, and fully color-equivariant networks achieve equivariance to these perceptual transformations without an increase in network parameters. We demonstrate the utility of our networks on synthetic and real world datasets where color and lighting variations are commonplace.
Authors: Shayan Shekarforoush, David B. Lindell, Marcus A. Brubaker, David J. Fleet
Abstract: Cryo-EM is an increasingly popular method for determining the atomic resolution 3D structure of macromolecular complexes (eg, proteins) from noisy 2D images captured by an electron microscope. The computational task is to reconstruct the 3D density of the particle, along with 3D pose of the particle in each 2D image, for which the posterior pose distribution is highly multi-modal. Recent developments in cryo-EM have focused on deep learning for which amortized inference has been used to predict pose. Here, we address key problems with this approach, and propose a new semi-amortized method, cryoSPIN, in which reconstruction begins with amortized inference and then switches to a form of auto-decoding to refine poses locally using stochastic gradient descent. Through evaluation on synthetic datasets, we demonstrate that cryoSPIN is able to handle multi-modal pose distributions during the amortized inference stage, while the later, more flexible stage of direct pose optimization yields faster and more accurate convergence of poses compared to baselines. On experimental data, we show that cryoSPIN outperforms the state-of-the-art cryoAI in speed and reconstruction quality.
Authors: Jefferson Hernandez, Ruben Villegas, Vicente Ordonez
Abstract: We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by curating a new multimodal instruction-following set using GPT-4V and existing datasets for image generation and editing. Using this instruction set and the existing LLaVA-Finetune instruction set for visual understanding tasks, we produce GenLLaVA, a Generative Large Language and Visual Assistant. GenLLaVA is built through a strategy that combines three types of large pretrained models through instruction finetuning: Mistral for language modeling, SigLIP for image-text matching, and StableDiffusion for text-to-image generation. Our model demonstrates visual understanding capabilities superior to LLaVA and additionally demonstrates competitive results with native multimodal models such as Unified-IO 2, paving the way for building advanced general-purpose visual assistants by effectively re-using existing multimodal models. We open-source our dataset, codebase, and model checkpoints to foster further research and application in this domain.
Authors: Renjie Li, Panwang Pan, Bangbang Yang, Dejia Xu, Shijie Zhou, Xuanyang Zhang, Zeming Li, Achuta Kadambi, Zhangyang Wang, Zhengzhong Tu, Zhiwen Fan
Abstract: The blooming of virtual reality and augmented reality (VR/AR) technologies has driven an increasing demand for the creation of high-quality, immersive, and dynamic environments. However, existing generative techniques either focus solely on dynamic objects or perform outpainting from a single perspective image, failing to meet the requirements of VR/AR applications that need free-viewpoint, 360$^{\circ}$ virtual views where users can move in all directions. In this work, we tackle the challenging task of elevating a single panorama to an immersive 4D experience. For the first time, we demonstrate the capability to generate omnidirectional dynamic scenes with 360$^{\circ}$ views at 4K (4096 $\times$ 2048) resolution, thereby providing an immersive user experience. Our method introduces a pipeline that facilitates natural scene animations and optimizes a set of dynamic Gaussians using efficient splatting techniques for real-time exploration. To overcome the lack of scene-scale annotated 4D data and models, especially in panoramic formats, we propose a novel \textbf{Panoramic Denoiser} that adapts generic 2D diffusion priors to animate consistently in 360$^{\circ}$ images, transforming them into panoramic videos with dynamic scenes at targeted regions. Subsequently, we propose \textbf{Dynamic Panoramic Lifting} to elevate the panoramic video into a 4D immersive environment while preserving spatial and temporal consistency. By transferring prior knowledge from 2D models in the perspective domain to the panoramic domain and the 4D lifting with spatial appearance and geometry regularization, we achieve high-quality Panorama-to-4D generation at a resolution of 4K for the first time.
Authors: Mohamed Fadhlallah Guerri, Cosimo Distante, Paolo Spagnolo, Fares Bougourzi, Abdelmalik Taleb-Ahmed
Abstract: During the process of classifying Hyperspectral Image (HSI), every pixel sample is categorized under a land-cover type. CNN-based techniques for HSI classification have notably advanced the field by their adept feature representation capabilities. However, acquiring deep features remains a challenge for these CNN-based methods. In contrast, transformer models are adept at extracting high-level semantic features, offering a complementary strength. This paper's main contribution is the introduction of an HSI classification model that includes two convolutional blocks, a Gate-Shift-Fuse (GSF) block and a transformer block. This model leverages the strengths of CNNs in local feature extraction and transformers in long-range context modelling. The GSF block is designed to strengthen the extraction of local and global spatial-spectral features. An effective attention mechanism module is also proposed to enhance the extraction of information from HSI cubes. The proposed method is evaluated on four well-known datasets (the Indian Pines, Pavia University, WHU-WHU-Hi-LongKou and WHU-Hi-HanChuan), demonstrating that the proposed framework achieves superior results compared to other models.
Authors: Min Zhao, Hongzhou Zhu, Chendong Xiang, Kaiwen Zheng, Chongxuan Li, Jun Zhu
Abstract: Diffusion models have obtained substantial progress in image-to-video generation. However, in this paper, we find that these models tend to generate videos with less motion than expected. We attribute this to the issue called conditional image leakage, where the image-to-video diffusion models (I2V-DMs) tend to over-rely on the conditional image at large time steps. We further address this challenge from both inference and training aspects. First, we propose to start the generation process from an earlier time step to avoid the unreliable large-time steps of I2V-DMs, as well as an initial noise distribution with optimal analytic expressions (Analytic-Init) by minimizing the KL divergence between it and the actual marginal distribution to bridge the training-inference gap. Second, we design a time-dependent noise distribution (TimeNoise) for the conditional image during training, applying higher noise levels at larger time steps to disrupt it and reduce the model's dependency on it. We validate these general strategies on various I2V-DMs on our collected open-domain image benchmark and the UCF101 dataset. Extensive results show that our methods outperform baselines by producing higher motion scores with lower errors while maintaining image alignment and temporal consistency, thereby yielding superior overall performance and enabling more accurate motion control. The project page: \url{https://cond-image-leak.github.io/}.
Authors: Yixin Liu, Ruoxi Chen, Xun Chen, Lichao Sun
Abstract: Personalized diffusion models (PDMs) have become prominent for adapting pretrained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations, leading to significant degradation when fine-tuned on corrupted datasets. These vulnerabilities are exploited to create protective perturbations that prevent unauthorized image generation. Existing purification methods attempt to mitigate this issue but often over-purify images, resulting in information loss. In this work, we conduct an in-depth analysis of the fine-tuning process of PDMs through the lens of shortcut learning. We hypothesize and empirically demonstrate that adversarial perturbations induce a latent-space misalignment between images and their text prompts in the CLIP embedding space. This misalignment causes the model to erroneously associate noisy patterns with unique identifiers during fine-tuning, resulting in poor generalization. Based on these insights, we propose a systematic defense framework that includes data purification and contrastive decoupling learning. We first employ off-the-shelf image restoration techniques to realign images with their original semantic meanings in latent space. Then, we introduce contrastive decoupling learning with noise tokens to decouple the learning of personalized concepts from spurious noise patterns. Our study not only uncovers fundamental shortcut learning vulnerabilities in PDMs but also provides a comprehensive evaluation framework for developing stronger protection. Our extensive evaluation demonstrates its superiority over existing purification methods and stronger robustness against adaptive perturbation.
Authors: Wenqi Zhang, Zhenglin Cheng, Yuanyu He, Mengna Wang, Yongliang Shen, Zeqi Tan, Guiyang Hou, Mingqian He, Yanna Ma, Weiming Lu, Yueting Zhuang
Abstract: Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilities remains quite rudimentary. They often struggle with simple daily tasks, such as reading time from a clock, understanding a flowchart, or planning a route using a road map. In light of this, we design a multi-modal self-instruct, utilizing large language models and their code capabilities to synthesize massive abstract images and visual reasoning instructions across daily scenarios. Our strategy effortlessly creates a multimodal benchmark with 11,193 instructions for eight visual scenarios: charts, tables, simulated maps, dashboards, flowcharts, relation graphs, floor plans, and visual puzzles. \textbf{This benchmark, constructed with simple lines and geometric elements, exposes the shortcomings of most advanced LMMs} like Claude-3.5-Sonnet and GPT-4o in abstract image understanding, spatial relations reasoning, and visual element induction. Besides, to verify the quality of our synthetic data, we fine-tune an LMM using 62,476 synthetic chart, table and road map instructions. The results demonstrate improved chart understanding and map navigation performance, and also demonstrate potential benefits for other visual reasoning tasks. Our code is available at: \url{https://github.com/zwq2018/Multi-modal-Self-instruct}.
Authors: Hao Fang, Jiawei Kong, Bin Chen, Tao Dai, Hao Wu, Shu-Tao Xia
Abstract: Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios. Recent studies have introduced \textit{single-target} generative attacks that train a generator for each target class to generate highly transferable perturbations, resulting in substantial computational overhead when handling multiple classes. \textit{Multi-target} attacks address this by training only one class-conditional generator for multiple classes. However, the generator simply uses class labels as conditions, failing to leverage the rich semantic information of the target class. To this end, we design a \textbf{C}LIP-guided \textbf{G}enerative \textbf{N}etwork with \textbf{C}ross-attention modules (CGNC) to enhance multi-target attacks by incorporating textual knowledge of CLIP into the generator. Extensive experiments demonstrate that CGNC yields significant improvements over previous multi-target generative attacks, e.g., a 21.46\% improvement in success rate from ResNet-152 to DenseNet-121. Moreover, we propose a masked fine-tuning mechanism to further strengthen our method in attacking a single class, which surpasses existing single-target methods.
Authors: Santosh V. Patapati
Abstract: Major Depressive Disorder (MDD) is a pervasive mental health condition that affects 300 million people worldwide. This work presents a novel, BiLSTM-based tri-modal model-level fusion architecture for the binary classification of depression from clinical interview recordings. The proposed architecture incorporates Mel Frequency Cepstral Coefficients, Facial Action Units, and uses a two-shot learning based GPT-4 model to process text data. This is the first work to incorporate large language models into a multi-modal architecture for this task. It achieves impressive results on the DAIC-WOZ AVEC 2016 Challenge cross-validation split and Leave-One-Subject-Out cross-validation split, surpassing all baseline models and multiple state-of-the-art models. In Leave-One-Subject-Out testing, it achieves an accuracy of 91.01%, an F1-Score of 85.95%, a precision of 80%, and a recall of 92.86%.
Authors: Yimian Dai, Peiwen Pan, Yulei Qian, Yuxuan Li, Xiang Li, Jian Yang, Huan Wang
Abstract: Infrared small target detection faces the inherent challenge of precisely localizing dim targets amidst complex background clutter. Traditional approaches struggle to balance detection precision and false alarm rates. To break this dilemma, we propose SeRankDet, a deep network that achieves high accuracy beyond the conventional hit-miss trade-off, by following the ``Pick of the Bunch'' principle. At its core lies our Selective Rank-Aware Attention (SeRank) module, employing a non-linear Top-K selection process that preserves the most salient responses, preventing target signal dilution while maintaining constant complexity. Furthermore, we replace the static concatenation typical in U-Net structures with our Large Selective Feature Fusion (LSFF) module, a dynamic fusion strategy that empowers SeRankDet with adaptive feature integration, enhancing its ability to discriminate true targets from false alarms. The network's discernment is further refined by our Dilated Difference Convolution (DDC) module, which merges differential convolution aimed at amplifying subtle target characteristics with dilated convolution to expand the receptive field, thereby substantially improving target-background separation. Despite its lightweight architecture, the proposed SeRankDet sets new benchmarks in state-of-the-art performance across multiple public datasets. The code is available at https://github.com/GrokCV/SeRankDet.
Authors: Aditya Taparia, Som Sagar, Ransalu Senanayake
Abstract: Concept-based explanations have become a popular choice for explaining deep neural networks post-hoc because, unlike most other explainable AI techniques, they can be used to test high-level visual "concepts" that are not directly related to feature attributes. For instance, the concept of "stripes" is important to classify an image as a zebra. Concept-based explanation methods, however, require practitioners to guess and collect multiple candidate concept image sets, which can often be imprecise and labor-intensive. Addressing this limitation, in this paper, we frame concept image set creation as an image generation problem. However, since naively using a generative model does not result in meaningful concepts, we devise a reinforcement learning-based preference optimization (RLPO) algorithm that fine-tunes the vision-language generative model from approximate textual descriptions of concepts. Through a series of experiments, we demonstrate the capability of our method to articulate complex and abstract concepts which aligns with the test class that are otherwise challenging to craft manually. In addition to showing the efficacy and reliability of our method, we show how our method can be used as a diagnostic tool for analyzing neural networks.
Authors: Nischal Khanal, Shivanand Venkanna Sheshappanavar
Abstract: Due to their text-to-image synthesis feature, diffusion models have recently seen a rise in visual perception tasks, such as depth estimation. The lack of good-quality datasets makes the extraction of a fine-grain semantic context challenging for the diffusion models. The semantic context with fewer details further worsens the process of creating effective text embeddings that will be used as input for diffusion models. In this paper, we propose a novel EDADepth, an enhanced data augmentation method to estimate monocular depth without using additional training data. We use Swin2SR, a super-resolution model, to enhance the quality of input images. We employ the BEiT pre-trained semantic segmentation model for better extraction of text embeddings. We use BLIP-2 tokenizer to generate tokens from these text embeddings. The novelty of our approach is the introduction of Swin2SR, the BEiT model, and the BLIP-2 tokenizer in the diffusion-based pipeline for the monocular depth estimation. Our model achieves state-of-the-art results (SOTA) on the delta3 metric on NYUv2 and KITTI datasets. It also achieves results comparable to those of the SOTA models in the RMSE and REL metrics. Finally, we also show improvements in the visualization of the estimated depth compared to the SOTA diffusion-based monocular depth estimation models. Code: https://github.com/edadepthmde/EDADepth_ICMLA.
Authors: Mingze Sun, Chen Guo, Puhua Jiang, Shiwei Mao, Yurun Chen, Ruqi Huang
Abstract: In this paper, we propose SRIF, a novel Semantic shape Registration framework based on diffusion-based Image morphing and Flow estimation. More concretely, given a pair of extrinsically aligned shapes, we first render them from multi-views, and then utilize an image interpolation framework based on diffusion models to generate sequences of intermediate images between them. The images are later fed into a dynamic 3D Gaussian splatting framework, with which we reconstruct and post-process for intermediate point clouds respecting the image morphing processing. In the end, tailored for the above, we propose a novel registration module to estimate continuous normalizing flow, which deforms source shape consistently towards the target, with intermediate point clouds as weak guidance. Our key insight is to leverage large vision models (LVMs) to associate shapes and therefore obtain much richer semantic information on the relationship between shapes than the ad-hoc feature extraction and alignment. As a consequence, SRIF achieves high-quality dense correspondences on challenging shape pairs, but also delivers smooth, semantically meaningful interpolation in between. Empirical evidence justifies the effectiveness and superiority of our method as well as specific design choices. The code is released at https://github.com/rqhuang88/SRIF.
Authors: Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, Junyang Lin
Abstract: We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. This approach allows the model to generate more efficient and accurate visual representations, closely aligning with human perceptual processes. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion of positional information across text, images, and videos. We employ a unified paradigm for processing both images and videos, enhancing the model's visual perception capabilities. To explore the potential of large multimodal models, Qwen2-VL investigates the scaling laws for large vision-language models (LVLMs). By scaling both the model size-with versions at 2B, 8B, and 72B parameters-and the amount of training data, the Qwen2-VL Series achieves highly competitive performance. Notably, the Qwen2-VL-72B model achieves results comparable to leading models such as GPT-4o and Claude3.5-Sonnet across various multimodal benchmarks, outperforming other generalist models. Code is available at https://github.com/QwenLM/Qwen2-VL .
Authors: Ali Badiezadeh, Amin Malekmohammadi, Seyed Mostafa Mirhassani, Parisa Gifani, Majid Vafaeezadeh
Abstract: Accurate segmentation of prostate cancer histopathology images is crucial for diagnosis and treatment planning. This study presents a comparative analysis of three deep learning-based methods, Mamba, SAM, and YOLO, for segmenting prostate cancer histopathology images. We evaluated the performance of these models on two comprehensive datasets, Gleason 2019 and SICAPv2, using Dice score, precision, and recall metrics. Our results show that the High-order Vision Mamba UNet (H-vmunet) model outperforms the other two models, achieving the highest scores across all metrics on both datasets. The H-vmunet model's advanced architecture, which integrates high-order visual state spaces and 2D-selective-scan operations, enables efficient and sensitive lesion detection across different scales. Our study demonstrates the potential of the H-vmunet model for clinical applications and highlights the importance of robust validation and comparison of deep learning-based methods for medical image analysis. The findings of this study contribute to the development of accurate and reliable computer-aided diagnosis systems for prostate cancer. The code is available at http://github.com/alibdz/prostate-segmentation.
Authors: Jing He, Haodong Li, Wei Yin, Yixun Liang, Leheng Li, Kaiqiang Zhou, Hongbo Zhang, Bingbing Liu, Ying-Cong Chen
Abstract: Leveraging the visual priors of pre-trained text-to-image diffusion models offers a promising solution to enhance zero-shot generalization in dense prediction tasks. However, existing methods often uncritically use the original diffusion formulation, which may not be optimal due to the fundamental differences between dense prediction and image generation. In this paper, we provide a systemic analysis of the diffusion formulation for the dense prediction, focusing on both quality and efficiency. And we find that the original parameterization type for image generation, which learns to predict noise, is harmful for dense prediction; the multi-step noising/denoising diffusion process is also unnecessary and challenging to optimize. Based on these insights, we introduce Lotus, a diffusion-based visual foundation model with a simple yet effective adaptation protocol for dense prediction. Specifically, Lotus is trained to directly predict annotations instead of noise, thereby avoiding harmful variance. We also reformulate the diffusion process into a single-step procedure, simplifying optimization and significantly boosting inference speed. Additionally, we introduce a novel tuning strategy called detail preserver, which achieves more accurate and fine-grained predictions. Without scaling up the training data or model capacity, Lotus achieves SoTA performance in zero-shot depth and normal estimation across various datasets. It also enhances efficiency, being significantly faster than most existing diffusion-based methods. Lotus' superior quality and efficiency also enable a wide range of practical applications, such as joint estimation, single/multi-view 3D reconstruction, etc. Project page: https://lotus3d.github.io/.
Authors: Mengwen Ye, Yingzi Huangfu, You Li, Zekuan Yu
Abstract: Fundus image classification is crucial in the computer aided diagnosis tasks, but label noise significantly impairs the performance of deep neural networks. To address this challenge, we propose a robust framework, Self-Supervised Pre-training with Robust Adaptive Credal Loss (SSP-RACL), for handling label noise in fundus image datasets. First, we use Masked Autoencoders (MAE) for pre-training to extract features, unaffected by label noise. Subsequently, RACL employ a superset learning framework, setting confidence thresholds and adaptive label relaxation parameter to construct possibility distributions and provide more reliable ground-truth estimates, thus effectively suppressing the memorization effect. Additionally, we introduce clinical knowledge-based asymmetric noise generation to simulate real-world noisy fundus image datasets. Experimental results demonstrate that our proposed method outperforms existing approaches in handling label noise, showing superior performance.
Authors: Diogo Gl\'oria-Silva, David Semedo, Jo\~ao Magalh\~aes
Abstract: Guiding users through complex procedural plans is an inherently multimodal task in which having visually illustrated plan steps is crucial to deliver an effective plan guidance. However, existing works on plan-following language models (LMs) often are not capable of multimodal input and output. In this work, we present MM-PlanLLM, the first multimodal LLM designed to assist users in executing instructional tasks by leveraging both textual plans and visual information. Specifically, we bring cross-modality through two key tasks: Conversational Video Moment Retrieval, where the model retrieves relevant step-video segments based on user queries, and Visually-Informed Step Generation, where the model generates the next step in a plan, conditioned on an image of the user's current progress. MM-PlanLLM is trained using a novel multitask-multistage approach, designed to gradually expose the model to multimodal instructional-plans semantic layers, achieving strong performance on both multimodal and textual dialogue in a plan-grounded setting. Furthermore, we show that the model delivers cross-modal temporal and plan-structure representations aligned between textual plan steps and instructional video moments.
Authors: Jihai Zhang, Xiaoye Qu, Tong Zhu, Yu Cheng
Abstract: In recent years, Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in multimodal intelligence. However, recent studies have identified that the information loss in the CLIP encoding process is substantial, and CLIP tends to capture only coarse-grained features from the input. This deficiency significantly limits the ability of a single CLIP model to handle images rich in visual detail. In this work, we propose a simple yet effective model-agnostic strategy, Diversified Multiplet Upcycling (DMU), for CLIP. DMU efficiently fine-tunes a series of CLIP models that capture different feature spaces, from a dense pre-trained CLIP checkpoint, sharing parameters except for the Feed-Forward Network (FFN). These models can then be transformed into a CLIP-MoE with a larger model capacity, leading to significantly enhanced performance with minimal computational overhead. To the best of our knowledge, Diversified Multiplet Upcycling is the first approach to introduce sparsely activated MoE into CLIP foundation models. Extensive experiments demonstrate the significant performance of CLIP-MoE across various zero-shot retrieval, zero-shot image classification tasks, and downstream Multimodal Large Language Model (MLLM) benchmarks by serving as a vision encoder. Furthermore, Diversified Multiplet Upcycling enables the conversion of any dense CLIP model into CLIP-MoEs, which can seamlessly replace CLIP in a plug-and-play manner without requiring further adaptation in downstream frameworks. Through Diversified Multiplet Upcycling, we aim to provide valuable insights for future research on developing more efficient and effective multimodal learning systems.
Authors: Zheyuan Zhan, Defang Chen, Jian-Ping Mei, Zhenghe Zhao, Jiawei Chen, Chun Chen, Siwei Lyu, Can Wang
Abstract: Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has become a highly effective way for conditional image synthesis, leading to exponential growth in the literature. However, the complexity of diffusion-based modeling, the wide range of image synthesis tasks, and the diversity of conditioning mechanisms present significant challenges for researchers to keep up with rapid developments and understand the core concepts on this topic. In this survey, we categorize existing works based on how conditions are integrated into the two fundamental components of diffusion-based modeling, i.e., the denoising network and the sampling process. We specifically highlight the underlying principles, advantages, and potential challenges of various conditioning approaches in the training, re-purposing, and specialization stages to construct a desired denoising network. We also summarize six mainstream conditioning mechanisms in the essential sampling process. All discussions are centered around popular applications. Finally, we pinpoint some critical yet still open problems to be solved in the future and suggest some possible solutions. Our reviewed works are itemized at https://github.com/zju-pi/Awesome-Conditional-Diffusion-Models.
URLs: https://github.com/zju-pi/Awesome-Conditional-Diffusion-Models.
Authors: Arunava Chakravarty, Taha Emre, Dmitrii Lachinov, Antoine Rivail, Hendrik Scholl, Lars Fritsche, Sobha Sivaprasad, Daniel Rueckert, Andrew Lotery, Ursula Schmidt-Erfurth, Hrvoje Bogunovi\'c
Abstract: Predicting future disease progression risk from medical images is challenging due to patient heterogeneity, and subtle or unknown imaging biomarkers. Moreover, deep learning (DL) methods for survival analysis are susceptible to image domain shifts across scanners. We tackle these issues in the task of predicting late dry Age-related Macular Degeneration (dAMD) onset from retinal OCT scans. We propose a novel DL method for survival prediction to jointly predict from the current scan a risk score, inversely related to time-to-conversion, and the probability of conversion within a time interval $t$. It uses a family of parallel hyperplanes generated by parameterizing the bias term as a function of $t$. In addition, we develop unsupervised losses based on intra-subject image pairs to ensure that risk scores increase over time and that future conversion predictions are consistent with AMD stage prediction using actual scans of future visits. Such losses enable data-efficient fine-tuning of the trained model on new unlabeled datasets acquired with a different scanner. Extensive evaluation on two large datasets acquired with different scanners resulted in a mean AUROCs of 0.82 for Dataset-1 and 0.83 for Dataset-2, across prediction intervals of 6,12 and 24 months.
Authors: Michal Balcerak, Tamaz Amiranashvili, Andreas Wagner, Jonas Weidner, Petr Karnakov, Johannes C. Paetzold, Ivan Ezhov, Petros Koumoutsakos, Benedikt Wiestler, Bjoern Menze
Abstract: Physical models in the form of partial differential equations represent an important prior for many under-constrained problems. One example is tumor treatment planning, which heavily depends on accurate estimates of the spatial distribution of tumor cells in a patient's anatomy. Medical imaging scans can identify the bulk of the tumor, but they cannot reveal its full spatial distribution. Tumor cells at low concentrations remain undetectable, for example, in the most frequent type of primary brain tumors, glioblastoma. Deep-learning-based approaches fail to estimate the complete tumor cell distribution due to a lack of reliable training data. Most existing works therefore rely on physics-based simulations to match observed tumors, providing anatomically and physiologically plausible estimations. However, these approaches struggle with complex and unknown initial conditions and are limited by overly rigid physical models. In this work, we present a novel method that balances data-driven and physics-based cost functions. In particular, we propose a unique discretization scheme that quantifies the adherence of our learned spatiotemporal tumor and brain tissue distributions to their corresponding growth and elasticity equations. This quantification, serving as a regularization term rather than a hard constraint, enables greater flexibility and proficiency in assimilating patient data than existing models. We demonstrate improved coverage of tumor recurrence areas compared to existing techniques on real-world data from a cohort of patients. The method holds the potential to enhance clinical adoption of model-driven treatment planning for glioblastoma.
Authors: Hua Yan, Heng Tan, Yi Ding, Pengfei Zhou, Vinod Namboodiri, Yu Yang
Abstract: Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is critical for applications in healthcare, safety, and industrial production. However, variations in activity patterns, device types, and sensor placements create distribution gaps across datasets, reducing the performance of HAR models. To address this, we propose LanHAR, a novel system that leverages Large Language Models (LLMs) to generate semantic interpretations of sensor readings and activity labels for cross-dataset HAR. This approach not only mitigates cross-dataset heterogeneity but also enhances the recognition of new activities. LanHAR employs an iterative re-generation method to produce high-quality semantic interpretations with LLMs and a two-stage training framework that bridges the semantic interpretations of sensor readings and activity labels. This ultimately leads to a lightweight sensor encoder suitable for mobile deployment, enabling any sensor reading to be mapped into the semantic interpretation space. Experiments on four public datasets demonstrate that our approach significantly outperforms state-of-the-art methods in both cross-dataset HAR and new activity recognition. The source code will be made publicly available.
Authors: Dexuan Ding, Lei Wang, Liyun Zhu, Tom Gedeon, Piotr Koniusz
Abstract: In computer vision tasks, features often come from diverse representations, domains, and modalities, such as text, images, and videos. Effectively fusing these features is essential for robust performance, especially with the availability of powerful pre-trained models like vision-language models. However, common fusion methods, such as concatenation, element-wise operations, and non-linear techniques, often fail to capture structural relationships, deep feature interactions, and suffer from inefficiency or misalignment of features across domains. In this paper, we shift from high-dimensional feature space to a lower-dimensional, interpretable graph space by constructing similarity graphs that encode feature relationships at different levels, e.g., clip, frame, patch, token, etc. To capture deeper interactions, we use graph power expansions and introduce a learnable graph fusion operator to combine these graph powers for more effective fusion. Our approach is relationship-centric, operates in a homogeneous space, and is mathematically principled, resembling element-wise similarity score aggregation via multilinear polynomials. We demonstrate the effectiveness of our graph-based fusion method on video anomaly detection, showing strong performance across multi-representational, multi-modal, and multi-domain feature fusion tasks.
Authors: Francesc Net, Lluis Gomez
Abstract: The intersection of Artificial Intelligence and Digital Humanities enables researchers to explore cultural heritage collections with greater depth and scale. In this paper, we present EUFCC-CIR, a dataset designed for Composed Image Retrieval (CIR) within Galleries, Libraries, Archives, and Museums (GLAM) collections. Our dataset is built on top of the EUFCC-340K image labeling dataset and contains over 180K annotated CIR triplets. Each triplet is composed of a multi-modal query (an input image plus a short text describing the desired attribute manipulations) and a set of relevant target images. The EUFCC-CIR dataset fills an existing gap in CIR-specific resources for Digital Humanities. We demonstrate the value of the EUFCC-CIR dataset by highlighting its unique qualities in comparison to other existing CIR datasets and evaluating the performance of several zero-shot CIR baselines.
Authors: Sina Mavali, Jonas Ricker, David Pape, Yash Sharma, Asja Fischer, Lea Sch\"onherr
Abstract: While generative AI (GenAI) offers countless possibilities for creative and productive tasks, artificially generated media can be misused for fraud, manipulation, scams, misinformation campaigns, and more. To mitigate the risks associated with maliciously generated media, forensic classifiers are employed to identify AI-generated content. However, current forensic classifiers are often not evaluated in practically relevant scenarios, such as the presence of an attacker or when real-world artifacts like social media degradations affect images. In this paper, we evaluate state-of-the-art AI-generated image (AIGI) detectors under different attack scenarios. We demonstrate that forensic classifiers can be effectively attacked in realistic settings, even when the attacker does not have access to the target model and post-processing occurs after the adversarial examples are created, which is standard on social media platforms. These attacks can significantly reduce detection accuracy to the extent that the risks of relying on detectors outweigh their benefits. Finally, we propose a simple defense mechanism to make CLIP-based detectors, which are currently the best-performing detectors, robust against these attacks.
Authors: Zhenyue Qin, Yu Yin, Dylan Campbell, Xuansheng Wu, Ke Zou, Yih-Chung Tham, Ninghao Liu, Xiuzhen Zhang, Qingyu Chen
Abstract: Ophthalmology relies heavily on detailed image analysis for diagnosis and treatment planning. While large vision-language models (LVLMs) have shown promise in understanding complex visual information, their performance on ophthalmology images remains underexplored. We introduce LMOD, a dataset and benchmark for evaluating LVLMs on ophthalmology images, covering anatomical understanding, diagnostic analysis, and demographic extraction. LMODincludes 21,993 images spanning optical coherence tomography, scanning laser ophthalmoscopy, eye photos, surgical scenes, and color fundus photographs. We benchmark 13 state-of-the-art LVLMs and find that they are far from perfect for comprehending ophthalmology images. Models struggle with diagnostic analysis and demographic extraction, reveal weaknesses in spatial reasoning, diagnostic analysis, handling out-of-domain queries, and safeguards for handling biomarkers of ophthalmology images.
Authors: Mengzhao Jia, Wenhao Yu, Kaixin Ma, Tianqing Fang, Zhihan Zhang, Siru Ouyang, Hongming Zhang, Meng Jiang, Dong Yu
Abstract: Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple text-rich images are especially challenging, as they require not only understanding the content of individual images but reasoning about inter-relationships and logical flows across multiple visual inputs. Despite the importance of these scenarios, current multimodal large language models (MLLMs) struggle to handle such tasks due to two key challenges: (1) the scarcity of high-quality instruction tuning datasets for text-rich multi-image scenarios, and (2) the difficulty in balancing image resolution with visual feature sequence length. To address these challenges, we propose Leopard, a MLLM designed specifically for handling vision-language tasks involving multiple text-rich images. First, we curated about one million high-quality multimodal instruction-tuning data, tailored to text-rich, multi-image scenarios. Second, we developed an adaptive high-resolution multi-image encoding module to dynamically optimize the allocation of visual sequence length based on the original aspect ratios and resolutions of the input images. Experiments across a wide range of benchmarks demonstrate our model's superior capabilities in text-rich, multi-image evaluations and competitive performance in general domain evaluations.
Authors: Yang Deng, Ce Wang, Yuan Hui, Qian Li, Jun Li, Shiwei Luo, Mengke Sun, Quan Quan, Shuxin Yang, You Hao, Pengbo Liu, Honghu Xiao, Chunpeng Zhao, Xinbao Wu, S. Kevin Zhou
Abstract: Spine-related diseases have high morbidity and cause a huge burden of social cost. Spine imaging is an essential tool for noninvasively visualizing and assessing spinal pathology. Segmenting vertebrae in computed tomography (CT) images is the basis of quantitative medical image analysis for clinical diagnosis and surgery planning of spine diseases. Current publicly available annotated datasets on spinal vertebrae are small in size. Due to the lack of a large-scale annotated spine image dataset, the mainstream deep learning-based segmentation methods, which are data-driven, are heavily restricted. In this paper, we introduce a large-scale spine CT dataset, called CTSpine1K, curated from multiple sources for vertebra segmentation, which contains 1,005 CT volumes with over 11,100 labeled vertebrae belonging to different spinal conditions. Based on this dataset, we conduct several spinal vertebrae segmentation experiments to set the first benchmark. We believe that this large-scale dataset will facilitate further research in many spine-related image analysis tasks, including but not limited to vertebrae segmentation, labeling, 3D spine reconstruction from biplanar radiographs, image super-resolution, and enhancement.
Authors: Wenguan Wang, Yi Yang, Fei Wu
Abstract: Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence (AI) for many years. As NeSy shows promise of reconciling the advantages of reasoning and interpretability of symbolic representation and robust learning in neural networks, it may serve as a catalyst for the next generation of AI. In the present paper, we provide a systematic overview of the recent developments and important contributions of NeSy research. Firstly, we introduce study history of this area, covering early work and foundations. We further discuss background concepts and identify key driving factors behind the development of NeSy. Afterward, we categorize recent landmark approaches along several main characteristics that underline this research paradigm, including neural-symbolic integration, knowledge representation, knowledge embedding, and functionality. Next, we briefly discuss the successful application of modern NeSy approaches in several domains. Then, we benchmark several NeSy methods on three representative application tasks. Finally, we identify the open problems together with potential future research directions. This survey is expected to help new researchers enter this rapidly evolving field and accelerate the progress towards data-and knowledge-driven AI.
Authors: Luigi Sigillo, Eleonora Grassucci, Aurelio Uncini, Danilo Comminiello
Abstract: Neural network generalizability is becoming a broad research field due to the increasing availability of datasets from different sources and for various tasks. This issue is even wider when processing medical data, where a lack of methodological standards causes large variations being provided by different imaging centers or acquired with various devices and cofactors. To overcome these limitations, we introduce a novel, generalizable, data- and task-agnostic framework able to extract salient features from medical images. The proposed quaternion wavelet network (QUAVE) can be easily integrated with any pre-existing medical image analysis or synthesis task, and it can be involved with real, quaternion, or hypercomplex-valued models, generalizing their adoption to single-channel data. QUAVE first extracts different sub-bands through the quaternion wavelet transform, resulting in both low-frequency/approximation bands and high-frequency/fine-grained features. Then, it weighs the most representative set of sub-bands to be involved as input to any other neural model for image processing, replacing standard data samples. We conduct an extensive experimental evaluation comprising different datasets, diverse image analysis, and synthesis tasks including reconstruction, segmentation, and modality translation. We also evaluate QUAVE in combination with both real and quaternion-valued models. Results demonstrate the effectiveness and the generalizability of the proposed framework that improves network performance while being flexible to be adopted in manifold scenarios and robust to domain shifts. The full code is available at: https://github.com/ispamm/QWT.
Authors: Haoran He, Chenjia Bai, Ling Pan, Weinan Zhang, Bin Zhao, Xuelong Li
Abstract: Learning a generalist embodied agent capable of completing multiple tasks poses challenges, primarily stemming from the scarcity of action-labeled robotic datasets. In contrast, a vast amount of human videos exist, capturing intricate tasks and interactions with the physical world. Promising prospects arise for utilizing actionless human videos for pre-training and transferring the knowledge to facilitate robot policy learning through limited robot demonstrations. However, it remains a challenge due to the domain gap between humans and robots. Moreover, it is difficult to extract useful information representing the dynamic world from human videos, because of its noisy and multimodal data structure. In this paper, we introduce a novel framework to tackle these challenges, which leverages a unified discrete diffusion to combine generative pre-training on human videos and policy fine-tuning on a small number of action-labeled robot videos. We start by compressing both human and robot videos into unified video tokens. In the pre-training stage, we employ a discrete diffusion model with a mask-and-replace diffusion strategy to predict future video tokens in the latent space. In the fine-tuning stage, we harness the imagined future videos to guide low-level action learning with a limited set of robot data. Experiments demonstrate that our method generates high-fidelity future videos for planning and enhances the fine-tuned policies compared to previous state-of-the-art approaches with superior performance. Our project website is available at https://video-diff.github.io/.
Authors: Zehao Wang, Yuping Wang, Zhuoyuan Wu, Hengbo Ma, Zhaowei Li, Hang Qiu, Jiachen Li
Abstract: The confluence of the advancement of Autonomous Vehicles (AVs) and the maturity of Vehicle-to-Everything (V2X) communication has enabled the capability of cooperative connected and automated vehicles (CAVs). Building on top of cooperative perception, this paper explores the feasibility and effectiveness of cooperative motion prediction. Our method, CMP, takes LiDAR signals as model input to enhance tracking and prediction capabilities. Unlike previous work that focuses separately on either cooperative perception or motion prediction, our framework, to the best of our knowledge, is the first to address the unified problem where CAVs share information in both perception and prediction modules. Incorporated into our design is the unique capability to tolerate realistic V2X bandwidth limitations and transmission delays, while dealing with bulky perception representations. We also propose a prediction aggregation module, which unifies the predictions obtained by different CAVs and generates the final prediction. Through extensive experiments and ablation studies on the OPV2V and V2V4Real datasets, we demonstrate the effectiveness of our method in cooperative perception, tracking, and motion prediction. In particular, CMP reduces the average prediction error by 16.4\% with fewer missing detections compared with the no cooperation setting and by 12.3\% compared with the strongest baseline. Our work marks a significant step forward in the cooperative capabilities of CAVs, showcasing enhanced performance in complex scenarios. The code can be found on the project website: https://cmp-cooperative-prediction.github.io/.
Authors: Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, Abhra Chaudhuri, Anjan Dutta
Abstract: When neural networks are trained on biased datasets, they tend to inadvertently learn spurious correlations, leading to challenges in achieving strong generalization and robustness. Current approaches to address such biases typically involve utilizing bias annotations, reweighting based on pseudo-bias labels, or enhancing diversity within bias-conflicting data points through augmentation techniques. We introduce DeNetDM, a novel debiasing method based on the observation that shallow neural networks prioritize learning core attributes, while deeper ones emphasize biases when tasked with acquiring distinct information. Using a training paradigm derived from Product of Experts, we create both biased and debiased branches with deep and shallow architectures and then distill knowledge to produce the target debiased model. Extensive experiments and analyses demonstrate that our approach outperforms current debiasing techniques, achieving a notable improvement of around 5% in three datasets, encompassing both synthetic and real-world data. Remarkably, DeNetDM accomplishes this without requiring annotations pertaining to bias labels or bias types, while still delivering performance on par with supervised counterparts. Furthermore, our approach effectively harnesses the diversity of bias-conflicting points within the data, surpassing previous methods and obviating the need for explicit augmentation-based methods to enhance the diversity of such bias-conflicting points. The source code will be available upon acceptance.
Authors: Yekun Chai, Qingyi Liu, Jingwu Xiao, Shuohuan Wang, Yu Sun, Hua Wu
Abstract: The integration of visual and textual information represents a promising direction in the advancement of language models. In this paper, we explore the dual modality of language--both visual and textual--within an autoregressive framework, pre-trained on both document images and texts. Our method employs a multimodal training strategy, utilizing visual data through next patch prediction with a regression head and/or textual data through next token prediction with a classification head. We focus on understanding the interaction between these two modalities and their combined impact on model performance. Our extensive evaluation across a wide range of benchmarks shows that incorporating both visual and textual data significantly improves the performance of pixel-based language models. Remarkably, we find that a unidirectional pixel-based model trained solely on visual data can achieve comparable results to state-of-the-art bidirectional models on several language understanding tasks. This work uncovers the untapped potential of integrating visual and textual modalities for more effective language modeling. We release our code, data, and model checkpoints at \url{https://github.com/ernie-research/pixelgpt}.
Authors: Antonio Emanuele Cin\`a, J\'er\^ome Rony, Maura Pintor, Luca Demetrio, Ambra Demontis, Battista Biggio, Ismail Ben Ayed, Fabio Roli
Abstract: Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental setups, hyperparameter settings, and number of forward and backward calls to the target models. This provides overly-optimistic and even biased evaluations that may unfairly favor one particular attack over the others. In this work, we aim to overcome these limitations by proposing AttackBench, i.e., the first evaluation framework that enables a fair comparison among different attacks. To this end, we first propose a categorization of gradient-based attacks, identifying their main components and differences. We then introduce our framework, which evaluates their effectiveness and efficiency. We measure these characteristics by (i) defining an optimality metric that quantifies how close an attack is to the optimal solution, and (ii) limiting the number of forward and backward queries to the model, such that all attacks are compared within a given maximum query budget. Our extensive experimental analysis compares more than $100$ attack implementations with a total of over $800$ different configurations against CIFAR-10 and ImageNet models, highlighting that only very few attacks outperform all the competing approaches. Within this analysis, we shed light on several implementation issues that prevent many attacks from finding better solutions or running at all. We release AttackBench as a publicly-available benchmark, aiming to continuously update it to include and evaluate novel gradient-based attacks for optimizing adversarial examples.
Authors: Pranab Sahoo, Prabhash Meharia, Akash Ghosh, Sriparna Saha, Vinija Jain, Aman Chadha
Abstract: The rapid advancement of foundation models (FMs) across language, image, audio, and video domains has shown remarkable capabilities in diverse tasks. However, the proliferation of FMs brings forth a critical challenge: the potential to generate hallucinated outputs, particularly in high-stakes applications. The tendency of foundation models to produce hallucinated content arguably represents the biggest hindrance to their widespread adoption in real-world scenarios, especially in domains where reliability and accuracy are paramount. This survey paper presents a comprehensive overview of recent developments that aim to identify and mitigate the problem of hallucination in FMs, spanning text, image, video, and audio modalities. By synthesizing recent advancements in detecting and mitigating hallucination across various modalities, the paper aims to provide valuable insights for researchers, developers, and practitioners. Essentially, it establishes a clear framework encompassing definition, taxonomy, and detection strategies for addressing hallucination in multimodal foundation models, laying the foundation for future research in this pivotal area.
Authors: Nicolas Zilberstein, Morteza Mardani, Santiago Segarra
Abstract: Score Distillation Sampling (SDS) has been pivotal for leveraging pre-trained diffusion models in downstream tasks such as inverse problems, but it faces two major challenges: $(i)$ mode collapse and $(ii)$ latent space inversion, which become more pronounced in high-dimensional data. To address mode collapse, we introduce a novel variational framework for posterior sampling. Utilizing the Wasserstein gradient flow interpretation of SDS, we propose a multimodal variational approximation with a repulsion mechanism that promotes diversity among particles by penalizing pairwise kernel-based similarity. This repulsion acts as a simple regularizer, encouraging a more diverse set of solutions. To mitigate latent space ambiguity, we extend this framework with an augmented variational distribution that disentangles the latent and data. This repulsive augmented formulation balances computational efficiency, quality, and diversity. Extensive experiments on linear and nonlinear inverse tasks with high-resolution images ($512 \times 512$) using pre-trained Stable Diffusion models demonstrate the effectiveness of our approach.
Authors: Xidong Wang, Dingjie Song, Shunian Chen, Chen Zhang, Benyou Wang
Abstract: Expanding the long-context capabilities of Multi-modal Large Language Models~(MLLMs) is crucial for video understanding, high-resolution image understanding, and multi-modal agents. This involves a series of systematic optimizations, including model architecture, data construction and training strategy, particularly addressing challenges such as \textit{degraded performance with more images} and \textit{high computational costs}. In this paper, we adapt the model architecture to a hybrid of Mamba and Transformer blocks, approach data construction with both temporal and spatial dependencies among multiple images and employ a progressive training strategy. The released model \textbf{LongLLaVA}~(\textbf{Long}-Context \textbf{L}arge \textbf{L}anguage \textbf{a}nd \textbf{V}ision \textbf{A}ssistant) is the first hybrid MLLM, which achieved a better balance between efficiency and effectiveness. LongLLaVA not only achieves competitive results across various benchmarks, but also maintains high throughput and low memory consumption. Especially, it could process nearly a thousand images on a single A100 80GB GPU, showing promising application prospects for a wide range of tasks.
Authors: Tianao Li, Manxiu Cui, Cheng Ma, Emma Alexander
Abstract: Photoacoustic computed tomography (PACT) is a non-invasive imaging modality with wide medical applications. Conventional PACT image reconstruction algorithms suffer from wavefront distortion caused by the heterogeneous speed of sound (SOS) in tissue, which leads to image degradation. Accounting for these effects improves image quality, but measuring the SOS distribution is experimentally expensive. An alternative approach is to perform joint reconstruction of the initial pressure image and SOS using only the PA signals. Existing joint reconstruction methods come with limitations: high computational cost, inability to directly recover SOS, and reliance on inaccurate simplifying assumptions. Implicit neural representation, or neural fields, is an emerging technique in computer vision to learn an efficient and continuous representation of physical fields with a coordinate-based neural network. In this work, we introduce NF-APACT, an efficient self-supervised framework utilizing neural fields to estimate the SOS in service of an accurate and robust multi-channel deconvolution. Our method removes SOS aberrations an order of magnitude faster and more accurately than existing methods. We demonstrate the success of our method on a novel numerical phantom as well as an experimentally collected phantom and in vivo data. Our code and numerical phantom are available at https://github.com/Lukeli0425/NF-APACT.
Authors: Amin Malekmohammadi, Ali Badiezadeh, Seyed Mostafa Mirhassani, Parisa Gifani, Majid Vafaeezadeh
Abstract: Prostate cancer ranks among the leading health issues impacting men, with the Gleason scoring system serving as the primary method for diagnosis and prognosis. This system relies on expert pathologists to evaluate samples of prostate tissue and assign a Gleason grade, a task that requires significant time and manual effort. To address this challenge, artificial intelligence (AI) solutions have been explored to automate the grading process. In light of these challenges, this study evaluates and compares the effectiveness of three deep learning methodologies, YOLO, Vision Transformers, and Vision Mamba, in accurately classifying Gleason grades from histopathology images. The goal is to enhance diagnostic precision and efficiency in prostate cancer management. This study utilized two publicly available datasets, Gleason2019 and SICAPv2, to train and test the performance of YOLO, Vision Transformers, and Vision Mamba models. Each model was assessed based on its ability to classify Gleason grades accurately, considering metrics such as false positive rate, false negative rate, precision, and recall. The study also examined the computational efficiency and applicability of each method in a clinical setting. Vision Mamba demonstrated superior performance across all metrics, achieving high precision and recall rates while minimizing false positives and negatives. YOLO showed promise in terms of speed and efficiency, particularly beneficial for real-time analysis. Vision Transformers excelled in capturing long-range dependencies within images, although they presented higher computational complexity compared to the other models. Vision Mamba emerges as the most effective model for Gleason grade classification in histopathology images, offering a balance between accuracy and computational efficiency.
Authors: Ming Zhong, Aston Zhang, Xuewei Wang, Rui Hou, Wenhan Xiong, Chenguang Zhu, Zhengxing Chen, Liang Tan, Chloe Bi, Mike Lewis, Sravya Popuri, Sharan Narang, Melanie Kambadur, Dhruv Mahajan, Sergey Edunov, Jiawei Han, Laurens van der Maaten
Abstract: The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities. However, this overlooks the intersection of multiple abilities across different types of expertise that are often required for real-world tasks, which we term cross capabilities. To systematically explore this concept, we first define seven core individual capabilities and then pair them to form seven common cross capabilities, each supported by a manually constructed taxonomy. Building on these definitions, we introduce CrossEval, a benchmark comprising 1,400 human-annotated prompts, with 100 prompts for each individual and cross capability. To ensure reliable evaluation, we involve expert annotators to assess 4,200 model responses, gathering 8,400 human ratings with detailed explanations to serve as reference examples. Our findings reveal that, in both static evaluations and attempts to enhance specific abilities, current LLMs consistently exhibit the "Law of the Weakest Link," where cross-capability performance is significantly constrained by the weakest component. Specifically, across 58 cross-capability scores from 17 models, 38 scores are lower than all individual capabilities, while 20 fall between strong and weak, but closer to the weaker ability. These results highlight the under-performance of LLMs in cross-capability tasks, making the identification and improvement of the weakest capabilities a critical priority for future research to optimize performance in complex, multi-dimensional scenarios.
Authors: Aidana Massalimova, Florentin Liebmann, Sascha Jecklin, Fabio Carrillo, Farshad Mazda, Philipp F\"urnstahl
Abstract: State-of-the-art computer- and robot-assisted surgery systems heavily depend on intraoperative imaging technologies such as CT and fluoroscopy to generate detailed 3D visualization of the patient's anatomy. While imaging techniques are highly accurate, they are based on ionizing radiation and expose patients and clinicians. This study introduces an alternative, radiation-free approach for reconstructing the 3D spine anatomy using RGB-D data. Drawing inspiration from the 3D "mental map" that surgeons form during surgeries, we introduce SurgPointTransformer, a shape completion approach for surgical applications that can accurately reconstruct the unexposed spine regions from sparse observations of the exposed surface. Our method involves two main steps: segmentation and shape completion. The segmentation step includes spinal column localization and segmentation, followed by vertebra-wise segmentation. The segmented vertebra point clouds are then subjected to SurgPointTransformer, which leverages an attention mechanism to learn patterns between visible surface features and the underlying anatomy. For evaluation, we utilize an ex-vivo dataset of nine specimens. Their CT data is used to establish ground truth data that were used to compare to the outputs of our methods. Our method significantly outperforms the state-of-the-art baselines, achieving an average Chamfer Distance of 5.39, an F-Score of 0.85, an Earth Mover's Distance of 0.011, and a Signal-to-Noise Ratio of 22.90 dB. This study demonstrates the potential of our reconstruction method for 3D vertebral shape completion. It enables 3D reconstruction of the entire lumbar spine and surgical guidance without ionizing radiation or invasive imaging. Our work contributes to computer-aided and robot-assisted surgery, advancing the perception and intelligence of these systems.
Authors: Gai Zhang, Xinfeng Zhang, Lv Tang, Yue Li, Kai Zhang, Li Zhang
Abstract: For decades, video compression technology has been a prominent research area. Traditional hybrid video compression framework and end-to-end frameworks continue to explore various intra- and inter-frame reference and prediction strategies based on discrete transforms and deep learning techniques. However, the emerging implicit neural representation (INR) technique models entire videos as basic units, automatically capturing intra-frame and inter-frame correlations and obtaining promising performance. INR uses a compact neural network to store video information in network parameters, effectively eliminating spatial and temporal redundancy in the original video. However, in this paper, our exploration and verification reveal that current INR video compression methods do not fully exploit their potential to preserve information. We investigate the potential of enhancing network parameter storage through parameter reuse. By deepening the network, we designed a feasible INR parameter reuse scheme to further improve compression performance. Extensive experimental results show that our method significantly enhances the rate-distortion performance of INR video compression.
Authors: Sedjro Salomon Hotegni, Sebastian Peitz
Abstract: Extensive research has shown that deep neural networks (DNNs) are vulnerable to slight adversarial perturbations$-$small changes to the input data that appear insignificant but cause the model to produce drastically different outputs. In addition to augmenting training data with adversarial examples generated from a specific attack method, most of the current defense strategies necessitate modifying the original model architecture components to improve robustness or performing test-time data purification to handle adversarial attacks. In this work, we demonstrate that strong feature representation learning during training can significantly enhance the original model's robustness. We propose MOREL, a multi-objective feature representation learning approach, encouraging classification models to produce similar features for inputs within the same class, despite perturbations. Our training method involves an embedding space where cosine similarity loss and multi-positive contrastive loss are used to align natural and adversarial features from the model encoder and ensure tight clustering. Concurrently, the classifier is motivated to achieve accurate predictions. Through extensive experiments, we demonstrate that our approach significantly enhances the robustness of DNNs against white-box and black-box adversarial attacks, outperforming other methods that similarly require no architectural changes or test-time data purification. Our code is available at https://github.com/salomonhotegni/MOREL