Authors: Jingwei Yi, Junhao Yin, Ju Xu, Peng Bao, Yongliang Wang, Wei Fan, Hao Wang
Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities in understanding multimodal inputs and have been widely integrated into Retrieval-Augmented Generation (RAG) based conversational systems. While current VLM-powered chatbots can provide textual source references in their responses, they exhibit significant limitations in referencing contextually relevant images during conversations. In this paper, we introduce Contextual Image Reference -- the ability to appropriately reference relevant images from retrieval documents based on conversation context -- and systematically investigate VLMs' capability in this aspect. We conduct the first evaluation for contextual image referencing, comprising a dedicated testing dataset and evaluation metrics. Furthermore, we propose ImageRef-VL, a method that significantly enhances open-source VLMs' image referencing capabilities through instruction fine-tuning on a large-scale, manually curated multimodal conversation dataset. Experimental results demonstrate that ImageRef-VL not only outperforms proprietary models but also achieves an 88% performance improvement over state-of-the-art open-source VLMs in contextual image referencing tasks. Our code is available at https://github.com/bytedance/ImageRef-VL.
Authors: Tabinda Aman, Mohammad Nadeem, Shahab Saquib Sohail, Mohammad Anas, Erik Cambria
Abstract: Animal stereotypes are deeply embedded in human culture and language. They often shape our perceptions and expectations of various species. Our study investigates how animal stereotypes manifest in vision-language models during the task of image generation. Through targeted prompts, we explore whether DALL-E perpetuates stereotypical representations of animals, such as "owls as wise," "foxes as unfaithful," etc. Our findings reveal significant stereotyped instances where the model consistently generates images aligned with cultural biases. The current work is the first of its kind to examine animal stereotyping in vision-language models systematically and to highlight a critical yet underexplored dimension of bias in AI-generated visual content.
Authors: Adarsh Kumar Kosta, Amogh Joshi, Arjun Roy, Rohan Kumar Manna, Manish Nagaraj, Kaushik Roy
Abstract: Object detection and tracking is an essential perception task for enabling fully autonomous navigation in robotic systems. Edge robot systems such as small drones need to execute complex maneuvers at high-speeds with limited resources, which places strict constraints on the underlying algorithms and hardware. Traditionally, frame-based cameras are used for vision-based perception due to their rich spatial information and simplified synchronous sensing capabilities. However, obtaining detailed information across frames incurs high energy consumption and may not even be required. In addition, their low temporal resolution renders them ineffective in high-speed motion scenarios. Event-based cameras offer a biologically-inspired solution to this by capturing only changes in intensity levels at exceptionally high temporal resolution and low power consumption, making them ideal for high-speed motion scenarios. However, their asynchronous and sparse outputs are not natively suitable with conventional deep learning methods. In this work, we propose TOFFE, a lightweight hybrid framework for performing event-based object motion estimation (including pose, direction, and speed estimation), referred to as Object Flow. TOFFE integrates bio-inspired Spiking Neural Networks (SNNs) and conventional Analog Neural Networks (ANNs), to efficiently process events at high temporal resolutions while being simple to train. Additionally, we present a novel event-based synthetic dataset involving high-speed object motion to train TOFFE. Our experimental results show that TOFFE achieves 5.7x/8.3x reduction in energy consumption and 4.6x/5.8x reduction in latency on edge GPU(Jetson TX2)/hybrid hardware(Loihi-2 and Jetson TX2), compared to previous event-based object detection baselines.
Authors: Yufeng Xie, Hanzhi Wu, Hongxiang Tong, Lei Xiao, Wenwen Zhou, Ling Li, Thomas Cherico Wanger
Abstract: Delineating farmland boundaries is essential for agricultural management such as crop monitoring and agricultural census. Traditional methods using remote sensing imagery have been efficient but limited in generalisation. The Segment Anything Model (SAM), known for its impressive zero shot performance, has been adapted for remote sensing tasks through prompt learning and fine tuning. Here, we propose a SAM based farmland boundary delineation framework 'fabSAM' that combines a Deeplabv3+ based Prompter and SAM. Also, a fine tuning strategy was introduced to enable SAMs decoder to improve the use of prompt information. Experimental results on the AI4Boundaries and AI4SmallFarms datasets have shown that fabSAM has a significant improvement in farmland region identification and boundary delineation. Compared to zero shot SAM, fabSAM surpassed it by 23.5% and 15.1% in mIOU on the AI4Boundaries and AI4SmallFarms datasets, respectively. For Deeplabv3+, fabSAM outperformed it by 4.9% and 12.5% in mIOU, respectively. These results highlight the effectiveness of fabSAM, which also means that we can more easily obtain the global farmland region and boundary maps from open source satellite image datasets like Sentinel2.
Authors: Josh Bruegger, Diana Ioana Catana, Vanja Macovaz, Matias Valdenegro-Toro, Matthia Sabatelli, Marco Zullich
Abstract: The attribution of the author of an art piece is typically a laborious manual process, usually relying on subjective evaluations of expert figures. However, there are some situations in which quantitative features of the artwork can support these evaluations. The extraction of these features can sometimes be automated, for instance, with the use of Machine Learning (ML) techniques. An example of these features is represented by repeated, mechanically impressed patterns, called punches, present chiefly in 13th and 14th-century panel paintings from Tuscany. Previous research in art history showcased a strong connection between the shapes of punches and specific artists or workshops, suggesting the possibility of using these quantitative cues to support the attribution. In the present work, we first collect a dataset of large-scale images of these panel paintings. Then, using YOLOv10, a recent and popular object detection model, we train a ML pipeline to perform object detection on the punches contained in the images. Due to the large size of the images, the detection procedure is split across multiple frames by adopting a sliding-window approach with overlaps, after which the predictions are combined for the whole image using a custom non-maximal suppression routine. Our results indicate how art historians working in the field can reliably use our method for the identification and extraction of punches.
Authors: Yanming Xiu, Tim Scargill, Maria Gorlatova
Abstract: In Augmented Reality (AR), virtual content enhances user experience by providing additional information. However, improperly positioned or designed virtual content can be detrimental to task performance, as it can impair users' ability to accurately interpret real-world information. In this paper we examine two types of task-detrimental virtual content: obstruction attacks, in which virtual content prevents users from seeing real-world objects, and information manipulation attacks, in which virtual content interferes with users' ability to accurately interpret real-world information. We provide a mathematical framework to characterize these attacks and create a custom open-source dataset for attack evaluation. To address these attacks, we introduce ViDDAR (Vision language model-based Task-Detrimental content Detector for Augmented Reality), a comprehensive full-reference system that leverages Vision Language Models (VLMs) and advanced deep learning techniques to monitor and evaluate virtual content in AR environments, employing a user-edge-cloud architecture to balance performance with low latency. To the best of our knowledge, ViDDAR is the first system to employ VLMs for detecting task-detrimental content in AR settings. Our evaluation results demonstrate that ViDDAR effectively understands complex scenes and detects task-detrimental content, achieving up to 92.15% obstruction detection accuracy with a detection latency of 533 ms, and an 82.46% information manipulation content detection accuracy with a latency of 9.62 s.
Authors: Fadel M. Megahed, Ying-Ju Chen, Bianca Maria Colosimo, Marco Luigi Giuseppe Grasso, L. Allison Jones-Farmer, Sven Knoth, Hongyue Sun, Inez Zwetsloot
Abstract: This expository paper introduces a simplified approach to image-based quality inspection in manufacturing using OpenAI's CLIP (Contrastive Language-Image Pretraining) model adapted for few-shot learning. While CLIP has demonstrated impressive capabilities in general computer vision tasks, its direct application to manufacturing inspection presents challenges due to the domain gap between its training data and industrial applications. We evaluate CLIP's effectiveness through five case studies: metallic pan surface inspection, 3D printing extrusion profile analysis, stochastic textured surface evaluation, automotive assembly inspection, and microstructure image classification. Our results show that CLIP can achieve high classification accuracy with relatively small learning sets (50-100 examples per class) for single-component and texture-based applications. However, the performance degrades with complex multi-component scenes. We provide a practical implementation framework that enables quality engineers to quickly assess CLIP's suitability for their specific applications before pursuing more complex solutions. This work establishes CLIP-based few-shot learning as an effective baseline approach that balances implementation simplicity with robust performance, demonstrated in several manufacturing quality control applications.
Authors: Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, Eric Granger
Abstract: Weakly supervised object localization (WSOL) using classification models trained with only image-class labels remains an important challenge in computer vision. Given their reliance on classification objectives, traditional WSOL methods like class activation mapping focus on the most discriminative object parts, often missing the full spatial extent. In contrast, recent WSOL methods based on vision-language models like CLIP require ground truth classes or external classifiers to produce a localization map, limiting their deployment in downstream tasks. Moreover, methods like GenPromp attempt to address these issues but introduce considerable complexity due to their reliance on conditional denoising processes and intricate prompt learning. This paper introduces Text Distillation for Localization (TeD-Loc), an approach that directly distills knowledge from CLIP text embeddings into the model backbone and produces patch-level localization. Multiple instance learning of these image patches allows for accurate localization and classification using one model without requiring external classifiers. Such integration of textual and visual modalities addresses the longstanding challenge of achieving accurate localization and classification concurrently, as WSOL methods in the literature typically converge at different epochs. Extensive experiments show that leveraging text embeddings and localization cues provides a cost-effective WSOL model. TeD-Loc improves Top-1 LOC accuracy over state-of-the-art models by about 5% on both CUB and ILSVRC datasets, while significantly reducing computational complexity compared to GenPromp.
Authors: Dunwei Tu, Huiyu Yi, Yuchi Wang, Baile Xu, Jian Zhao, Furao Shen
Abstract: Continual learning requires machine learning models to continuously acquire new knowledge in dynamic environments while avoiding the forgetting of previous knowledge. Prompt-based continual learning methods effectively address the issue of catastrophic forgetting through prompt expansion and selection. However, existing approaches often suffer from low accuracy in prompt selection, which can result in the model receiving biased knowledge and making biased predictions. To address this issue, we propose the Multiple Queries with Multiple Keys (MQMK) prompt matching paradigm for precise prompt selection. The goal of MQMK is to select the prompts whose training data distribution most closely matches that of the test sample. Specifically, Multiple Queries enable precise breadth search by introducing task-specific knowledge, while Multiple Keys perform deep search by representing the feature distribution of training samples at a fine-grained level. Experiments show that MQMK enhances the prompt matching rate by over 30% in challenging scenarios and achieves state-of-the-art performance on three widely adopted continual learning benchmarks. Once this paper is accepted, we will release the code.
Authors: Hung Nguyen, Blark Runfa Li, Truong Nguyen
Abstract: Neural Radiance Fields (NeRF) has achieved superior performance in novel view synthesis and 3D scene representation, but its practical applications are hindered by slow convergence and reliance on dense training views. To this end, we present DWTNeRF, a unified framework based on Instant-NGP's fast-training hash encoding. It is coupled with regularization terms designed for few-shot NeRF, which operates on sparse training views. Our DWTNeRF includes a novel Discrete Wavelet loss that allows explicit prioritization of low frequencies directly in the training objective, reducing few-shot NeRF's overfitting on high frequencies in earlier training stages. We additionally introduce a model-based approach, based on multi-head attention, that is compatible with INGP-based models, which are sensitive to architectural changes. On the 3-shot LLFF benchmark, DWTNeRF outperforms Vanilla NeRF by 15.07% in PSNR, 24.45% in SSIM and 36.30% in LPIPS. Our approach encourages a re-thinking of current few-shot approaches for INGP-based models.
Authors: Takumi Fukuzawa, Kensho Hara, Hirokatsu Kataoka, Toru Tamaki
Abstract: In this paper, we address the issue of static bias in zero-shot action recognition. Action recognition models need to represent the action itself, not the appearance. However, some fully-supervised works show that models often rely on static appearances, such as the background and objects, rather than human actions. This issue, known as static bias, has not been investigated for zero-shot. Although CLIP-based zero-shot models are now common, it remains unclear if they sufficiently focus on human actions, as CLIP primarily captures appearance features related to languages. In this paper, we investigate the influence of static bias in zero-shot action recognition with CLIP-based models. Our approach involves masking backgrounds, objects, and people differently during training and validation. Experiments with masking background show that models depend on background bias as their performance decreases for Kinetics400. However, for Mimetics, which has a weak background bias, masking the background leads to improved performance even if the background is masked during validation. Furthermore, masking both the background and objects in different colors improves performance for SSv2, which has a strong object bias. These results suggest that masking the background or objects during training prevents models from overly depending on static bias and makes them focus more on human action.
Authors: Qian Tao, Xiaoyang Fan, Yong Xu, Xingquan Zhu, Yufei Tang
Abstract: Zero-shot visual question answering (ZS-VQA), an emerged critical research area, intends to answer visual questions without providing training samples. Existing research in ZS-VQA has proposed to leverage knowledge graphs or large language models (LLMs), respectively, as external information sources to help VQA model comprehend images and questions. However, LLMs often struggle in accurately interpreting specific question meanings. Meanwhile, although knowledge graph has rich entity relationships, it is challenging to effectively connect entities to individual image content for visual question answers. In this paper, we propose a novel design to combine knowledge graph and LLMs for zero-shot visual question answer. Our approach uses LLMs' powerful understanding capabilities to accurately interpret image content through a strategic question search mechanism. Meanwhile, the knowledge graph is used to expand and connect users' queries to the image content for better visual question answering. An optimization algorithm is further used to determine the optimal weights for the loss functions derived from different information sources, towards a globally optimal set of candidate answers. Experimental results on two benchmark datasets demonstrate that our model achieves state-of-the-art (SOTA) performance. Both source code and benchmark data will be released for public access.
Authors: Yuan Bian, Min Liu, Yunqi Yi, Xueping Wang, Yunfeng Ma, Yaonan Wang
Abstract: Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality re-id models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omni-modality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively.
Authors: Zitang Sun, Yen-Ju Chen, Yung-Hao Yang, Yuan Li, Shin'ya Nishida
Abstract: Our research aims to develop machines that learn to perceive visual motion as do humans. While recent advances in computer vision (CV) have enabled DNN-based models to accurately estimate optical flow in naturalistic images, a significant disparity remains between CV models and the biological visual system in both architecture and behavior. This disparity includes humans' ability to perceive the motion of higher-order image features (second-order motion), which many CV models fail to capture because of their reliance on the intensity conservation law. Our model architecture mimics the cortical V1-MT motion processing pathway, utilizing a trainable motion energy sensor bank and a recurrent graph network. Supervised learning employing diverse naturalistic videos allows the model to replicate psychophysical and physiological findings about first-order (luminance-based) motion perception. For second-order motion, inspired by neuroscientific findings, the model includes an additional sensing pathway with nonlinear preprocessing before motion energy sensing, implemented using a simple multilayer 3D CNN block. When exploring how the brain acquired the ability to perceive second-order motion in natural environments, in which pure second-order signals are rare, we hypothesized that second-order mechanisms were critical when estimating robust object motion amidst optical fluctuations, such as highlights on glossy surfaces. We trained our dual-pathway model on novel motion datasets with varying material properties of moving objects. We found that training to estimate object motion from non-Lambertian materials naturally endowed the model with the capacity to perceive second-order motion, as can humans. The resulting model effectively aligns with biological systems while generalizing to both first- and second-order motion phenomena in natural scenes.
Authors: Alessio Quercia, Erenus Yildiz, Zhuo Cao, Kai Krajsek, Abigail Morrison, Ira Assent, Hanno Scharr
Abstract: Monocular depth estimation (MDE) is a challenging task in computer vision, often hindered by the cost and scarcity of high-quality labeled datasets. We tackle this challenge using auxiliary datasets from related vision tasks for an alternating training scheme with a shared decoder built on top of a pre-trained vision foundation model, while giving a higher weight to MDE. Through extensive experiments we demonstrate the benefits of incorporating various in-domain auxiliary datasets and tasks to improve MDE quality on average by ~11%. Our experimental analysis shows that auxiliary tasks have different impacts, confirming the importance of task selection, highlighting that quality gains are not achieved by merely adding data. Remarkably, our study reveals that using semantic segmentation datasets as Multi-Label Dense Classification (MLDC) often results in additional quality gains. Lastly, our method significantly improves the data efficiency for the considered MDE datasets, enhancing their quality while reducing their size by at least 80%. This paves the way for using auxiliary data from related tasks to improve MDE quality despite limited availability of high-quality labeled data. Code is available at https://jugit.fz-juelich.de/ias-8/mdeaux.
Authors: Aghiles Kebaili, J\'er\^ome Lapuyade-Lahorgue, Pierre Vera, Su Ruan
Abstract: In clinical practice, full imaging is not always feasible, often due to complex acquisition protocols, stringent privacy regulations, or specific clinical needs. However, missing MR modalities pose significant challenges for tasks like brain tumor segmentation, especially in deep learning-based segmentation, as each modality provides complementary information crucial for improving accuracy. A promising solution is missing data imputation, where absent modalities are generated from available ones. While generative models have been widely used for this purpose, most state-of-the-art approaches are limited to single or dual target translations, lacking the adaptability to generate missing modalities based on varying input configurations. To address this, we propose an Adaptive Multi-Modality Diffusion Network (AMM-Diff), a novel diffusion-based generative model capable of handling any number of input modalities and generating the missing ones. We designed an Image-Frequency Fusion Network (IFFN) that learns a unified feature representation through a self-supervised pretext task across the full input modalities and their selected high-frequency Fourier components. The proposed diffusion model leverages this representation, encapsulating prior knowledge of the complete modalities, and combines it with an adaptive reconstruction strategy to achieve missing modality completion. Experimental results on the BraTS 2021 dataset demonstrate the effectiveness of our approach.
Authors: Ruicheng Zhang, Haowei Guo, Zeyu Zhang, Puxin Yan, Shen Zhao
Abstract: Multi-organ segmentation is a critical yet challenging task due to complex anatomical backgrounds, blurred boundaries, and diverse morphologies. This study introduces the Gradient-aware Adaptive Momentum Evolution Deep Snake (GAMED-Snake) model, which establishes a novel paradigm for contour-based segmentation by integrating gradient-based learning with adaptive momentum evolution mechanisms. The GAMED-Snake model incorporates three major innovations: First, the Distance Energy Map Prior (DEMP) generates a pixel-level force field that effectively attracts contour points towards the true boundaries, even in scenarios with complex backgrounds and blurred edges. Second, the Differential Convolution Inception Module (DCIM) precisely extracts comprehensive energy gradients, significantly enhancing segmentation accuracy. Third, the Adaptive Momentum Evolution Mechanism (AMEM) employs cross-attention to establish dynamic features across different iterations of evolution, enabling precise boundary alignment for diverse morphologies. Experimental results on four challenging multi-organ segmentation datasets demonstrate that GAMED-Snake improves the mDice metric by approximately 2% compared to state-of-the-art methods. Code will be available at https://github.com/SYSUzrc/GAMED-Snake.
Authors: Xianglong Shi, Yunhan Jiang, Xiaoheng Jiang, Mingling Xu, Yang Liu
Abstract: Crack Segmentation in industrial concrete surfaces is a challenging task because cracks usually exhibit intricate morphology with slender appearances. Traditional segmentation methods often struggle to accurately locate such cracks, leading to inefficiencies in maintenance and repair processes. In this paper, we propose a novel diffusion-based model with a cross-conditional encoder-decoder, named CrossDiff, which is the first to introduce the diffusion probabilistic model for the crack segmentation task. Specifically, CrossDiff integrates a cross-encoder and a cross-decoder into the diffusion model to constitute a cross-shaped diffusion model structure. The cross-encoder enhances the ability to retain crack details and the cross-decoder helps extract the semantic features of cracks. As a result, CrossDiff can better handle slender cracks. Extensive experiments were conducted on five challenging crack datasets including CFD, CrackTree200, DeepCrack, GAPs384, and Rissbilder. The results demonstrate that the proposed CrossDiff model achieves impressive performance, outperforming other state-of-the-art methods by 8.0% in terms of both Dice score and IoU. The code will be open-source soon.
Authors: Wenhao Gu, Li Gu, Ziqiang Wang, Ching Yee Suen, Yang Wang
Abstract: Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder~(MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets.
Authors: Edurne Bernal-Berdun, Ana Serrano, Belen Masia, Matheus Gadelha, Yannick Hold-Geoffroy, Xin Sun, Diego Gutierrez
Abstract: Images as an artistic medium often rely on specific camera angles and lens distortions to convey ideas or emotions; however, such precise control is missing in current text-to-image models. We propose an efficient and general solution that allows precise control over the camera when generating both photographic and artistic images. Unlike prior methods that rely on predefined shots, we rely solely on four simple extrinsic and intrinsic camera parameters, removing the need for pre-existing geometry, reference 3D objects, and multi-view data. We also present a novel dataset with more than 57,000 images, along with their text prompts and ground-truth camera parameters. Our evaluation shows precise camera control in text-to-image generation, surpassing traditional prompt engineering approaches. Our data, model, and code are publicly available at https://graphics.unizar.es/projects/PreciseCam2024.
Authors: Kaiyu Li, Xiangyong Cao, Yupeng Deng, Chao Pang, Zepeng Xin, Deyu Meng, Zhi Wang
Abstract: Monitoring Earth's evolving land covers requires methods capable of detecting changes across a wide range of categories and contexts. Existing change detection methods are hindered by their dependency on predefined classes, reducing their effectiveness in open-world applications. To address this issue, we introduce open-vocabulary change detection (OVCD), a novel task that bridges vision and language to detect changes across any category. Considering the lack of high-quality data and annotation, we propose two training-free frameworks, M-C-I and I-M-C, which leverage and integrate off-the-shelf foundation models for the OVCD task. The insight behind the M-C-I framework is to discover all potential changes and then classify these changes, while the insight of I-M-C framework is to identify all targets of interest and then determine whether their states have changed. Based on these two frameworks, we instantiate to obtain several methods, e.g., SAM-DINOv2-SegEarth-OV, Grounding-DINO-SAM2-DINO, etc. Extensive evaluations on 5 benchmark datasets demonstrate the superior generalization and robustness of our OVCD methods over existing supervised and unsupervised methods. To support continued exploration, we release DynamicEarth, a dedicated codebase designed to advance research and application of OVCD. https://likyoo.github.io/DynamicEarth
Authors: Ruisi Zhao, Zechuan Zhang, Zongxin Yang, Yi Yang
Abstract: Object manipulation in images aims to not only edit the object's presentation but also gift objects with motion. Previous methods encountered challenges in concurrently handling static editing and dynamic generation, while also struggling to achieve fidelity in object appearance and scene lighting. In this work, we introduce \textbf{OMG3D}, a novel framework that integrates the precise geometric control with the generative power of diffusion models, thus achieving significant enhancements in visual performance. Our framework first converts 2D objects into 3D, enabling user-directed modifications and lifelike motions at the geometric level. To address texture realism, we propose CustomRefiner, a texture refinement module that pre-train a customized diffusion model, aligning the details and style of coarse renderings of 3D rough model with the original image, further refine the texture. Additionally, we introduce IllumiCombiner, a lighting processing module that estimates and corrects background lighting to match human visual perception, resulting in more realistic shadow effects. Extensive experiments demonstrate the outstanding visual performance of our approach in both static and dynamic scenarios. Remarkably, all these steps can be done using one NVIDIA 3090. Project page is at https://whalesong-zrs.github.io/OMG3D-projectpage/
Authors: Saahil Islam, Venkatesh N. Murthy, Dominik Neumann, Serkan Cimen, Puneet Sharma, Andreas Maier, Dorin Comaniciu, Florin C. Ghesu
Abstract: To restore proper blood flow in blocked coronary arteries via angioplasty procedure, accurate placement of devices such as catheters, balloons, and stents under live fluoroscopy or diagnostic angiography is crucial. Identified balloon markers help in enhancing stent visibility in X-ray sequences, while the catheter tip aids in precise navigation and co-registering vessel structures, reducing the need for contrast in angiography. However, accurate detection of these devices in interventional X-ray sequences faces significant challenges, particularly due to occlusions from contrasted vessels and other devices and distractions from surrounding, resulting in the failure to track such small objects. While most tracking methods rely on spatial correlation of past and current appearance, they often lack strong motion comprehension essential for navigating through these challenging conditions, and fail to effectively detect multiple instances in the scene. To overcome these limitations, we propose a self-supervised learning approach that enhances its spatio-temporal understanding by incorporating supplementary cues and learning across multiple representation spaces on a large dataset. Followed by that, we introduce a generic real-time tracking framework that effectively leverages the pretrained spatio-temporal network and also takes the historical appearance and trajectory data into account. This results in enhanced localization of multiple instances of device landmarks. Our method outperforms state-of-the-art methods in interventional X-ray device tracking, especially stability and robustness, achieving an 87% reduction in max error for balloon marker detection and a 61% reduction in max error for catheter tip detection.
Authors: Pierre Onghena, Santiago Velasco-Forero, Beatriz Marcotegui
Abstract: Point clouds are a set of data points in space to represent the 3D geometry of objects. A fundamental step in the processing is to identify a subset of points to represent the shape. While traditional sampling methods often ignore to incorporate geometrical information, recent developments in learning-based sampling models have achieved significant levels of performance. With the integration of geometrical priors, the ability to learn and preserve the underlying structure can be enhanced when sampling. To shed light into the shape, a qualitative skeleton serves as an effective descriptor to guide sampling for both local and global geometries. In this paper, we introduce MorphoSkel3D as a new technique based on morphology to facilitate an efficient skeletonization of shapes. With its low computational cost, MorphoSkel3D is a unique, rule-based algorithm to benchmark its quality and performance on two large datasets, ModelNet and ShapeNet, under different sampling ratios. The results show that training with MorphoSkel3D leads to an informed and more accurate sampling in the practical application of object classification and point cloud retrieval.
Authors: Jiahao Wang, Ning Kang, Lewei Yao, Mengzhao Chen, Chengyue Wu, Songyang Zhang, Shuchen Xue, Yong Liu, Taiqiang Wu, Xihui Liu, Kaipeng Zhang, Shifeng Zhang, Wenqi Shao, Zhenguo Li, Ping Luo
Abstract: In commonly used sub-quadratic complexity modules, linear attention benefits from simplicity and high parallelism, making it promising for image synthesis tasks. However, the architectural design and learning strategy for linear attention remain underexplored in this field. In this paper, we offer a suite of ready-to-use solutions for efficient linear diffusion Transformers. Our core contributions include: (1) Simplified Linear Attention using few heads, observing the free-lunch effect of performance without latency increase. (2) Weight inheritance from a fully pre-trained diffusion Transformer: initializing linear Transformer using pre-trained diffusion Transformer and loading all parameters except for those related to linear attention. (3) Hybrid knowledge distillation objective: using a pre-trained diffusion Transformer to help the training of the student linear Transformer, supervising not only the predicted noise but also the variance of the reverse diffusion process. These guidelines lead to our proposed Linear Diffusion Transformer (LiT), an efficient text-to-image Transformer that can be deployed offline on a laptop. Experiments show that in class-conditional 256*256 and 512*512 ImageNet benchmark LiT achieves highly competitive FID while reducing training steps by 80% and 77% compared to DiT. LiT also rivals methods based on Mamba or Gated Linear Attention. Besides, for text-to-image generation, LiT allows for the rapid synthesis of up to 1K resolution photorealistic images. Project page: https://techmonsterwang.github.io/LiT/.
Authors: Xu Zhang, Huan Zhang, Guoli Wang, Qian Zhang, Lefei Zhang, Bo Du
Abstract: Existing underwater image restoration (UIR) methods generally only handle color distortion or jointly address color and haze issues, but they often overlook the more complex degradations that can occur in underwater scenes. To address this limitation, we propose a Universal Underwater Image Restoration method, termed as UniUIR, considering the complex scenario of real-world underwater mixed distortions as an all-in-one manner. To decouple degradation-specific issues and explore the inter-correlations among various degradations in UIR task, we designed the Mamba Mixture-of-Experts module. This module enables each expert to identify distinct types of degradation and collaboratively extract task-specific priors while maintaining global feature representation based on linear complexity. Building upon this foundation, to enhance degradation representation and address the task conflicts that arise when handling multiple types of degradation, we introduce the spatial-frequency prior generator. This module extracts degradation prior information in both spatial and frequency domains, and adaptively selects the most appropriate task-specific prompts based on image content, thereby improving the accuracy of image restoration. Finally, to more effectively address complex, region-dependent distortions in UIR task, we incorporate depth information derived from a large-scale pre-trained depth prediction model, thereby enabling the network to perceive and leverage depth variations across different image regions to handle localized degradation. Extensive experiments demonstrate that UniUIR can produce more attractive results across qualitative and quantitative comparisons, and shows strong generalization than state-of-the-art methods.
Authors: Louis Aberdeen, Mark Hansen, Melvyn L. Smith, Lyndon Smith
Abstract: As the density of spacecraft in Earth's orbit increases, their recognition, pose and trajectory identification becomes crucial for averting potential collisions and executing debris removal operations. However, training models able to identify a spacecraft and its pose presents a significant challenge due to a lack of available image data for model training. This paper puts forth an innovative framework for generating realistic synthetic datasets of Resident Space Object (RSO) imagery. Using the International Space Station (ISS) as a test case, it goes on to combine image regression with image restoration methodologies to estimate pose from blurred images. An analysis of the proposed image recovery and regression techniques was undertaken, providing insights into the performance, potential enhancements and limitations when applied to real imagery of RSOs. The image recovery approach investigated involves first applying image deconvolution using an effective point spread function, followed by detail object extraction with a U-Net. Interestingly, using only U-Net for image reconstruction the best pose performance was attained, reducing the average Mean Squared Error in image recovery by 97.28% and the average angular error by 71.9%. The successful application of U-Net image restoration combined with the Resnet50 regression network for pose estimation of the International Space Station demonstrates the value of a diverse set of evaluation tools for effective solutions to real-world problems such as the analysis of distant objects in Earth's orbit.
Authors: Yuang Shi, Simone Gasparini, G\'eraldine Morin, Chenggang Yang, Wei Tsang Ooi
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising representation for photorealistic rendering of 3D scenes. However, its high storage requirements pose significant challenges for practical applications. We observe that Gaussians exhibit distinct roles and characteristics that are analogous to traditional artistic techniques -- Like how artists first sketch outlines before filling in broader areas with color, some Gaussians capture high-frequency features like edges and contours; While other Gaussians represent broader, smoother regions, that are analogous to broader brush strokes that add volume and depth to a painting. Based on this observation, we propose a novel hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which define scene boundaries, and (ii) Patch Gaussians, which cover smooth regions. Sketch Gaussians are efficiently encoded using parametric models, leveraging their geometric coherence, while Patch Gaussians undergo optimized pruning, retraining, and vector quantization to maintain volumetric consistency and storage efficiency. Our comprehensive evaluation across diverse indoor and outdoor scenes demonstrates that this structure-aware approach achieves up to 32.62% improvement in PSNR, 19.12% in SSIM, and 45.41% in LPIPS at equivalent model sizes, and correspondingly, for an indoor scene, our model maintains the visual quality with 2.3% of the original model size.
Authors: Mingshuo Xu, Hao Luan, Zhou Daniel Hao, Jigen Peng, Shigang Yue
Abstract: Recognizing motions of tiny targets - only few dozen pixels - in cluttered backgrounds remains a fundamental challenge when standard feature-based or deep learning methods fail under scarce visual cues. We propose STMDNet, a model-based computational framework to Recognize motions of tiny targets at variable velocities under low-sampling frequency scenarios. STMDNet designs a novel dual-dynamics-and-correlation mechanism, harnessing ipsilateral excitation to integrate target cues and leakage-enhancing-type contralateral inhibition to suppress large-object and background motion interference. Moreover, we develop the first collaborative directional encoding-decoding strategy that determines the motion direction from only one correlation per spatial location, cutting computational costs to one-eighth of prior methods. Further, simply substituting the backbone of a strong STMD model with STMDNet raises AUC by 24%, yielding an enhanced STMDNet-F. Evaluations on real-world low sampling frequency datasets show state-of-the-art results, surpassing the deep learning baseline. Across diverse speeds, STMDNet-F improves mF1 by 19%, 16%, and 8% at 240Hz, 120Hz, and 60Hz, respectively, while STMDNet achieves 87 FPS on a single CPU thread. These advances highlight STMDNet as a next-generation backbone for tiny target motion pattern recognition and underscore its broader potential to revitalize model-based visual approaches in motion detection.
Authors: Ali K. AlShami, Ryan Rabinowitz, Khang Lam, Yousra Shleibik, Melkamu Mersha, Terrance Boult, Jugal Kalita
Abstract: Human Action Recognition (HAR) is a challenging domain in computer vision, involving recognizing complex patterns by analyzing the spatiotemporal dynamics of individuals' movements in videos. These patterns arise in sequential data, such as video frames, which are often essential to accurately distinguish actions that would be ambiguous in a single image. HAR has garnered considerable interest due to its broad applicability, ranging from robotics and surveillance systems to sports motion analysis, healthcare, and the burgeoning field of autonomous vehicles. While several taxonomies have been proposed to categorize HAR approaches in surveys, they often overlook hybrid methodologies and fail to demonstrate how different models incorporate various architectures and modalities. In this comprehensive survey, we present the novel SMART-Vision taxonomy, which illustrates how innovations in deep learning for HAR complement one another, leading to hybrid approaches beyond traditional categories. Our survey provides a clear roadmap from foundational HAR works to current state-of-the-art systems, highlighting emerging research directions and addressing unresolved challenges in discussion sections for architectures within the HAR domain. We provide details of the research datasets that various approaches used to measure and compare goodness HAR approaches. We also explore the rapidly emerging field of Open-HAR systems, which challenges HAR systems by presenting samples from unknown, novel classes during test time.
Authors: Lianrui Zuo, Kaiwen Xu, Dingjie Su, Xin Yu, Aravind R. Krishnan, Yihao Liu, Shunxing Bao, Thomas Li, Kim L. Sandler, Fabien Maldonado, Bennett A. Landman
Abstract: The interconnection between the human lungs and other organs, such as the liver and kidneys, is crucial for understanding the underlying risks and effects of lung diseases and improving patient care. However, most research chest CT imaging is focused solely on the lungs due to considerations of cost and radiation dose. This restricted field of view (FOV) in the acquired images poses challenges to comprehensive analysis and hinders the ability to gain insights into the impact of lung diseases on other organs. To address this, we propose SCOPE (Spatial Coverage Optimization with Prior Encoding), a novel approach to capture the inter-organ relationships from CT images and extend the FOV of chest CT images. Our approach first trains a variational autoencoder (VAE) to encode 2D axial CT slices individually, then stacks the latent representations of the VAE to form a 3D context for training a latent diffusion model. Once trained, our approach extends the FOV of CT images in the z-direction by generating new axial slices in a zero-shot manner. We evaluated our approach on the National Lung Screening Trial (NLST) dataset, and results suggest that it effectively extends the FOV to include the liver and kidneys, which are not completely covered in the original NLST data acquisition. Quantitative results on a held-out whole-body dataset demonstrate that the generated slices exhibit high fidelity with acquired data, achieving an SSIM of 0.81.
Authors: Lianrui Zuo, Xin Yu, Dingjie Su, Kaiwen Xu, Aravind R. Krishnan, Yihao Liu, Shunxing Bao, Fabien Maldonado, Luigi Ferrucci, Bennett A. Landman
Abstract: Body composition analysis provides valuable insights into aging, disease progression, and overall health conditions. Due to concerns of radiation exposure, two-dimensional (2D) single-slice computed tomography (CT) imaging has been used repeatedly for body composition analysis. However, this approach introduces significant spatial variability that can impact the accuracy and robustness of the analysis. To mitigate this issue and facilitate body composition analysis, this paper presents a novel method to generate 3D CT volumes from limited number of 2D slices using a latent diffusion model (LDM). Our approach first maps 2D slices into a latent representation space using a variational autoencoder. An LDM is then trained to capture the 3D context of a stack of these latent representations. To accurately interpolate intermediateslices and construct a full 3D volume, we utilize body part regression to determine the spatial location and distance between the acquired slices. Experiments on both in-house and public 3D abdominal CT datasets demonstrate that the proposed method significantly enhances body composition analysis compared to traditional 2D-based analysis, with a reduced error rate from 23.3% to 15.2%.
Authors: Jos\'e Rodr\'iguez-Ortega, Siham Tabik
Abstract: Identifying anatomical landmarks in 3D dental models is crucial for orthodontic treatment. Manually placing these key points is complex, time-consuming, and requires expert knowledge. While some machine learning methods have been proposed for automatic tooth landmark detection in 3D Intraoral Scans (IOS), research remains limited, with no fully end-to-end approaches that avoid teeth segmentation. We propose CHaRNet (Conditioned Heatmap Regression Network), the first end-to-end deep learning method for tooth landmark detection in 3D IOS. Unlike traditional two-stage methods that segment teeth before detecting landmarks, CHaRNet directly detects landmarks on the input point cloud. It consists of four key modules: (1) a point cloud encoder, (2) a point cloud decoder with a heatmap regression head, (3) a teeth presence classification head, and (4) the innovative Conditioned Heatmap Regression (CHaR) module. The CHaR module refines landmark regression by leveraging teeth presence classification, enabling dynamic adaptation to cases with missing teeth and improving accuracy in complex dental models. We evaluate CHaRNet using five point cloud learning algorithms to validate the effectiveness of the CHaR module and test it on a clinical dataset of $1,214$ annotated 3D dental models. Both the dataset and code will be publicly released to address the lack of open datasets in orthodontics, promote benchmarking, and inspire new research. CHaRNet achieves a Mean Euclidean Distance Error (MEDE) of 1.28 mm and a Mean Success Ratio (MSR) of 82.40\%, demonstrating robust performance. Notably, it excels in handling irregular dental geometries, such as models with missing teeth. This end-to-end approach streamlines orthodontic workflows, improves 3D IOS analysis precision, and facilitates efficient computer-assisted treatment planning.
Authors: Akshay Krishnan, Xinchen Yan, Vincent Casser, Abhijit Kundu
Abstract: Diffusion models are state-of-the-art for image generation. Trained on large datasets, they capture expressive image priors that have been used for tasks like inpainting, depth, and (surface) normal prediction. However, these models are typically trained for one specific task, e.g., a separate model for each of color, depth, and normal prediction. Such models do not leverage the intrinsic correlation between appearance and geometry, often leading to inconsistent predictions. In this paper, we propose using a novel image diffusion prior that jointly encodes appearance and geometry. We introduce a diffusion model Orchid, comprising a Variational Autoencoder (VAE) to encode color, depth, and surface normals to a latent space, and a Latent Diffusion Model (LDM) for generating these joint latents. Orchid directly generates photo-realistic color images, relative depth, and surface normals from user-provided text, and can be used to create image-aligned partial 3D scenes seamlessly. It can also perform image-conditioned tasks like joint monocular depth and normal prediction and is competitive in accuracy to state-of-the-art methods designed for those tasks alone. Lastly, our model learns a joint prior that can be used zero-shot as a regularizer for many inverse problems that entangle appearance and geometry. For example, we demonstrate its effectiveness in color-depth-normal inpainting, showcasing its applicability to problems in 3D generation from sparse views.
Authors: Jiachen Lei, Julius Berner, Jiongxiao Wang, Zhongzhu Chen, Zhongjia Ba, Kui Ren, Jun Zhu, Anima Anandkumar
Abstract: Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently, diffusion models have been successfully employed for randomized smoothing to purify noise-perturbed samples before making predictions with a standard classifier. While these methods excel at small perturbation radii, they struggle with larger perturbations and incur a significant computational overhead during inference compared to classical methods. To address this, we reformulate the generative modeling task along the diffusion trajectories in pixel space as a discriminative task in the latent space. Specifically, we use instance discrimination to achieve consistent representations along the trajectories by aligning temporally adjacent points. After fine-tuning based on the learned representations, our model enables implicit denoising-then-classification via a single prediction, substantially reducing inference costs. We conduct extensive experiments on various datasets and achieve state-of-the-art performance with minimal computation budget during inference. For example, our method outperforms the certified accuracy of diffusion-based methods on ImageNet across all perturbation radii by 5.3% on average, with up to 11.6% at larger radii, while reducing inference costs by 85$\times$ on average. Codes are available at: https://github.com/jiachenlei/rRCM.
Authors: Wenhui Xiao, Remi Chierchia, Rodrigo Santa Cruz, Xuesong Li, David Ahmedt-Aristizabal, Olivier Salvado, Clinton Fookes, Leo Lebrat
Abstract: Neural Radiance Fields (NeRFs) have remodeled 3D scene representation since release. NeRFs can effectively reconstruct complex 3D scenes from 2D images, advancing different fields and applications such as scene understanding, 3D content generation, and robotics. Despite significant research progress, a thorough review of recent innovations, applications, and challenges is lacking. This survey compiles key theoretical advancements and alternative representations and investigates emerging challenges. It further explores applications on reconstruction, highlights NeRFs' impact on computer vision and robotics, and reviews essential datasets and toolkits. By identifying gaps in the literature, this survey discusses open challenges and offers directions for future research.
Authors: Boqiang Zhang, Kehan Li, Zesen Cheng, Zhiqiang Hu, Yuqian Yuan, Guanzheng Chen, Sicong Leng, Yuming Jiang, Hang Zhang, Xin Li, Peng Jin, Wenqi Zhang, Fan Wang, Lidong Bing, Deli Zhao
Abstract: In this paper, we propose VideoLLaMA3, a more advanced multimodal foundation model for image and video understanding. The core design philosophy of VideoLLaMA3 is vision-centric. The meaning of "vision-centric" is two-fold: the vision-centric training paradigm and vision-centric framework design. The key insight of our vision-centric training paradigm is that high-quality image-text data is crucial for both image and video understanding. Instead of preparing massive video-text datasets, we focus on constructing large-scale and high-quality image-text datasets. VideoLLaMA3 has four training stages: 1) vision-centric alignment stage, which warms up the vision encoder and projector; 2) vision-language pretraining stage, which jointly tunes the vision encoder, projector, and LLM with large-scale image-text data covering multiple types (including scene images, documents, charts) as well as text-only data. 3) multi-task fine-tuning stage, which incorporates image-text SFT data for downstream tasks and video-text data to establish a foundation for video understanding. 4) video-centric fine-tuning, which further improves the model's capability in video understanding. As for the framework design, to better capture fine-grained details in images, the pretrained vision encoder is adapted to encode images of varying sizes into vision tokens with corresponding numbers, rather than a fixed number of tokens. For video inputs, we reduce the number of vision tokens according to their similarity so that the representation of videos will be more precise and compact. Benefit from vision-centric designs, VideoLLaMA3 achieves compelling performances in both image and video understanding benchmarks.
Authors: Matthew Gwilliam, Han Cai, Di Wu, Abhinav Shrivastava, Zhiyu Cheng
Abstract: We propose Inner Loop Feedback (ILF), a novel approach to accelerate diffusion models' inference. ILF trains a lightweight module to predict future features in the denoising process by leveraging the outputs from a chosen diffusion backbone block at a given time step. This approach exploits two key intuitions; (1) the outputs of a given block at adjacent time steps are similar, and (2) performing partial computations for a step imposes a lower burden on the model than skipping the step entirely. Our method is highly flexible, since we find that the feedback module itself can simply be a block from the diffusion backbone, with all settings copied. Its influence on the diffusion forward can be tempered with a learnable scaling factor from zero initialization. We train this module using distillation losses; however, unlike some prior work where a full diffusion backbone serves as the student, our model freezes the backbone, training only the feedback module. While many efforts to optimize diffusion models focus on achieving acceptable image quality in extremely few steps (1-4 steps), our emphasis is on matching best case results (typically achieved in 20 steps) while significantly reducing runtime. ILF achieves this balance effectively, demonstrating strong performance for both class-to-image generation with diffusion transformer (DiT) and text-to-image generation with DiT-based PixArt-alpha and PixArt-sigma. The quality of ILF's 1.7x-1.8x speedups are confirmed by FID, CLIP score, CLIP Image Quality Assessment, ImageReward, and qualitative comparisons.
Authors: Feda Bolus Al Baqain, Omar Sultan Al-Kadi
Abstract: Histopathological image analysis is a reliable method for prostate cancer identification. In this paper, we present a comparative analysis of two approaches for segmenting glandular structures in prostate images to automate Gleason grading. The first approach utilizes a hand-crafted learning technique, combining Gray Level Co-Occurrence Matrix (GLCM) and Local Binary Pattern (LBP) texture descriptors to highlight spatial dependencies and minimize information loss at the pixel level. For machine driven feature extraction, we employ a U-Net convolutional neural network to perform semantic segmentation of prostate gland stroma tissue. Support vector machine-based learning of hand-crafted features achieves impressive classification accuracies of 99.0% and 95.1% for GLCM and LBP, respectively, while the U-Net-based machine-driven features attain 94% accuracy. Furthermore, a comparative analysis demonstrates superior segmentation quality for histopathological grades 1, 2, 3, and 4 using the U-Net approach, as assessed by Jaccard and Dice metrics. This work underscores the utility of machine-driven features in clinical applications that rely on automated pixel-level segmentation in prostate tissue images.
Authors: Eunjee Choi, Junhyun Ahn, XinYu Piao, Jong-Kook Kim
Abstract: Multimodal Fake News Detection has received increasing attention recently. Existing methods rely on independently encoded unimodal data and overlook the advantages of capturing intra-modality relationships and integrating inter-modal similarities using advanced techniques. To address these issues, Cross-Modal Tri-Transformer and Metric Learning for Multimodal Fake News Detection (CroMe) is proposed. CroMe utilizes Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (BLIP2) as encoders to capture detailed text, image and combined image-text representations. The metric learning module employs a proxy anchor method to capture intra-modality relationships while the feature fusion module uses a Cross-Modal and Tri-Transformer for effective integration. The final fake news detector processes the fused features through a classifier to predict the authenticity of the content. Experiments on datasets show that CroMe excels in multimodal fake news detection.
Authors: Fatih Aksu, Fabrizia Gelardi, Arturo Chiti, Paolo Soda
Abstract: Accurate classification of histological subtypes of non-small cell lung cancer (NSCLC) is essential in the era of precision medicine, yet current invasive techniques are not always feasible and may lead to clinical complications. This study presents a multi-stage intermediate fusion approach to classify NSCLC subtypes from CT and PET images. Our method integrates the two modalities at different stages of feature extraction, using voxel-wise fusion to exploit complementary information across varying abstraction levels while preserving spatial correlations. We compare our method against unimodal approaches using only CT or PET images to demonstrate the benefits of modality fusion, and further benchmark it against early and late fusion techniques to highlight the advantages of intermediate fusion during feature extraction. Additionally, we compare our model with the only existing intermediate fusion method for histological subtype classification using PET/CT images. Our results demonstrate that the proposed method outperforms all alternatives across key metrics, with an accuracy and AUC equal to 0.724 and 0.681, respectively. This non-invasive approach has the potential to significantly improve diagnostic accuracy, facilitate more informed treatment decisions, and advance personalized care in lung cancer management.
Authors: Guiqiu Liao, Matjaz Jogan, Marcel Hussing, Kenta Nakahashi, Kazuhiro Yasufuku, Amin Madani, Eric Eaton, Daniel A. Hashimoto
Abstract: Object-centric slot attention is a powerful framework for unsupervised learning of structured and explainable representations that can support reasoning about objects and actions, including in surgical videos. While conventional object-centric methods for videos leverage recurrent processing to achieve efficiency, they often struggle with maintaining long-range temporal coherence required for long videos in surgical applications. On the other hand, fully parallel processing of entire videos enhances temporal consistency but introduces significant computational overhead, making it impractical for implementation on hardware in medical facilities. We present Slot-BERT, a bidirectional long-range model that learns object-centric representations in a latent space while ensuring robust temporal coherence. Slot-BERT scales object discovery seamlessly to long videos of unconstrained lengths. A novel slot contrastive loss further reduces redundancy and improves the representation disentanglement by enhancing slot orthogonality. We evaluate Slot-BERT on real-world surgical video datasets from abdominal, cholecystectomy, and thoracic procedures. Our method surpasses state-of-the-art object-centric approaches under unsupervised training achieving superior performance across diverse domains. We also demonstrate efficient zero-shot domain adaptation to data from diverse surgical specialties and databases.
Authors: Fatima Haimour, Rizik Al-Sayyed, Waleed Mahafza, Omar S. Al-Kadi
Abstract: Brain imaging plays a crucial role in the diagnosis and treatment of various neurological disorders, providing valuable insights into the structure and function of the brain. Techniques such as magnetic resonance imaging (MRI) and computed tomography (CT) enable non-invasive visualization of the brain, aiding in the understanding of brain anatomy, abnormalities, and functional connectivity. However, cost and radiation dose may limit the acquisition of specific image modalities, so medical image synthesis can be used to generate required medical images without actual addition. In the medical domain, where obtaining labeled medical images is labor-intensive and expensive, addressing data scarcity is a major challenge. Recent studies propose using transfer learning to overcome this issue. This involves adapting pre-trained CycleGAN models, initially trained on non-medical data, to generate realistic medical images. In this work, transfer learning was applied to the task of MR-CT image translation and vice versa using 18 pre-trained non-medical models, and the models were fine-tuned to have the best result. The models' performance was evaluated using four widely used image quality metrics: Peak-signal-to-noise-ratio, Structural Similarity Index, Universal Quality Index, and Visual Information Fidelity. Quantitative evaluation and qualitative perceptual analysis by radiologists demonstrate the potential of transfer learning in medical imaging and the effectiveness of the generic pre-trained model. The results provide compelling evidence of the model's exceptional performance, which can be attributed to the high quality and similarity of the training images to actual human brain images. These results underscore the significance of carefully selecting appropriate and representative training images to optimize performance in brain image analysis tasks.
Authors: Jiaqi Guo, Yunnan Wu, Evangelos Kaimakamis, Georgios Petmezas, Vasileios E. Papageorgiou, Nicos Maglaveras, Aggelos K. Katsaggelos
Abstract: With the advent of the COVID-19 pandemic, ultrasound imaging has emerged as a promising technique for COVID-19 detection, due to its non-invasive nature, affordability, and portability. In response, researchers have focused on developing AI-based scoring systems to provide real-time diagnostic support. However, the limited size and lack of proper annotation in publicly available ultrasound datasets pose significant challenges for training a robust AI model. This paper proposes MeDiVLAD, a novel pipeline to address the above issue for multi-level lung-ultrasound (LUS) severity scoring. In particular, we leverage self-knowledge distillation to pretrain a vision transformer (ViT) without label and aggregate frame-level features via dual-level VLAD aggregation. We show that with minimal finetuning, MeDiVLAD outperforms conventional fully-supervised methods in both frame- and video-level scoring, while offering classification reasoning with exceptional quality. This superior performance enables key applications such as the automatic identification of critical lung pathology areas and provides a robust solution for broader medical video classification tasks.
Authors: Mirali Purohit, Gedeon Muhawenayo, Esther Rolf, Hannah Kerner
Abstract: Foundation models have made rapid advances in many domains including Earth observation, where Geospatial Foundation Models (GFMs) can help address global challenges such as climate change, agriculture, and disaster response. Previous work on GFMs focused on tailoring model architecture and pre-text tasks, and did not investigate the impact of pre-training data selection on model performance. However, recent works from other domains show that the pre-training data distribution is an important factor influencing the performance of the foundation models. With this motivation, our research explores how the geographic distribution of pre-training data affects the performance of GFMs. We evaluated several pre-training data distributions by sampling different compositions from a global data pool. Our experiments with two GFMs on downstream tasks indicate that balanced and globally representative data compositions often outperform region-specific sampling, highlighting the importance of diversity and global coverage in pre-training data. Our results suggest that the most appropriate data sampling technique may depend on the specific GFM architecture. These findings will support the development of robust GFMs by incorporating quality pre-training data distributions, ultimately improving machine learning solutions for Earth observation.
Authors: Wang Pang, Zhihao Zhan, Xiang Zhu, Yechao Bai
Abstract: Most motion deblurring algorithms rely on spatial-domain convolution models, which struggle with the complex, non-linear blur arising from camera shake and object motion. In contrast, we propose a novel single-image deblurring approach that treats motion blur as a temporal averaging phenomenon. Our core innovation lies in leveraging a pre-trained video diffusion transformer model to capture diverse motion dynamics within a latent space. It sidesteps explicit kernel estimation and effectively accommodates diverse motion patterns. We implement the algorithm within a diffusion-based inverse problem framework. Empirical results on synthetic and real-world datasets demonstrate that our method outperforms existing techniques in deblurring complex motion blur scenarios. This work paves the way for utilizing powerful video diffusion models to address single-image deblurring challenges.
Authors: Haocheng Luo, Tuan Truong, Tung Pham, Mehrtash Harandi, Dinh Phung, Trung Le
Abstract: Sharpness-Aware Minimization (SAM) has attracted significant attention for its effectiveness in improving generalization across various tasks. However, its underlying principles remain poorly understood. In this work, we analyze SAM's training dynamics using the maximum eigenvalue of the Hessian as a measure of sharpness, and propose a third-order stochastic differential equation (SDE), which reveals that the dynamics are driven by a complex mixture of second- and third-order terms. We show that alignment between the perturbation vector and the top eigenvector is crucial for SAM's effectiveness in regularizing sharpness, but find that this alignment is often inadequate in practice, limiting SAM's efficiency. Building on these insights, we introduce Eigen-SAM, an algorithm that explicitly aims to regularize the top Hessian eigenvalue by aligning the perturbation vector with the leading eigenvector. We validate the effectiveness of our theory and the practical advantages of our proposed approach through comprehensive experiments. Code is available at https://github.com/RitianLuo/EigenSAM.
Authors: Mingyuan Fan, Zhanyi Hu, Fuyi Wang, Cen Chen
Abstract: Data heterogeneity and backdoor attacks rank among the most significant challenges facing federated learning (FL). For data heterogeneity, personalized federated learning (PFL) enables each client to maintain a private personalized model to cater to client-specific knowledge. Meanwhile, vanilla FL has proven vulnerable to backdoor attacks. However, recent advancements in PFL community have demonstrated a potential immunity against such attacks. This paper explores this intersection further, revealing that existing federated backdoor attacks fail in PFL because backdoors about manually designed triggers struggle to survive in personalized models. To tackle this, we design Bad-PFL, which employs features from natural data as our trigger. As long as the model is trained on natural data, it inevitably embeds the backdoor associated with our trigger, ensuring its longevity in personalized models. Moreover, our trigger undergoes mutual reinforcement training with the model, further solidifying the backdoor's durability and enhancing attack effectiveness. The large-scale experiments across three benchmark datasets demonstrate the superior performance of our attack against various PFL methods, even when equipped with state-of-the-art defense mechanisms.
Authors: Sushil Awale, Eric M\"uller-Budack, Ralph Ewerth
Abstract: Patent figure classification facilitates faceted search in patent retrieval systems, enabling efficient prior art search. Existing approaches have explored patent figure classification for only a single aspect and for aspects with a limited number of concepts. In recent years, large vision-language models (LVLMs) have shown tremendous performance across numerous computer vision downstream tasks, however, they remain unexplored for patent figure classification. Our work explores the efficacy of LVLMs in patent figure visual question answering (VQA) and classification, focusing on zero-shot and few-shot learning scenarios. For this purpose, we introduce new datasets, PatFigVQA and PatFigCLS, for fine-tuning and evaluation regarding multiple aspects of patent figures~(i.e., type, projection, patent class, and objects). For a computational-effective handling of a large number of classes using LVLM, we propose a novel tournament-style classification strategy that leverages a series of multiple-choice questions. Experimental results and comparisons of multiple classification approaches based on LVLMs and Convolutional Neural Networks (CNNs) in few-shot settings show the feasibility of the proposed approaches.
Authors: Ruicheng Zhang, Kanghui Tian, Zeyu Zhang, Qixiang Liu, Zhi Jin
Abstract: In this study, we reveal that the interaction between haze degradation and JPEG compression introduces complex joint loss effects, which significantly complicate image restoration. Existing dehazing models often neglect compression effects, which limits their effectiveness in practical applications. To address these challenges, we introduce three key contributions. First, we design FDG-Diff, a novel frequency-domain-guided dehazing framework that improves JPEG image restoration by leveraging frequency-domain information. Second, we introduce the High-Frequency Compensation Module (HFCM), which enhances spatial-domain detail restoration by incorporating frequency-domain augmentation techniques into a diffusion-based restoration framework. Lastly, the introduction of the Degradation-Aware Denoising Timestep Predictor (DADTP) module further enhances restoration quality by enabling adaptive region-specific restoration, effectively addressing regional degradation inconsistencies in compressed hazy images. Experimental results across multiple compressed dehazing datasets demonstrate that our method consistently outperforms the latest state-of-the-art approaches. Code be available at https://github.com/SYSUzrc/FDG-Diff.
Authors: Jingru Fu, Adrian V. Dalca, Bruce Fischl, Rodrigo Moreno, Malte Hoffmann
Abstract: Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registration across subjects, they have demonstrated limitations when applied to longitudinal (within-subject) registration, where achieving precise alignment is critical. Building on an existing framework for anatomy-aware, acquisition-agnostic affine registration, we propose a model optimized for longitudinal, rigid brain registration. By training the model with synthetic within-subject pairs augmented with rigid and subtle nonlinear transforms, the model estimates more accurate rigid transforms than previous cross-subject networks and performs robustly on longitudinal registration pairs within and across magnetic resonance imaging (MRI) contrasts.
Authors: David Lehavi, Brian Osserman
Abstract: We present a fast and accurate solution to the perspective n-points problem, by way of a new approach to the n=4 case. Our solution hinges on a novel separation of variables: given four 3D points and four corresponding 2D points on the camera canvas, we start by finding another set of 3D points, sitting on the rays connecting the camera to the 2D canvas points, so that the six pair-wise distances between these 3D points are as close as possible to the six distances between the original 3D points. This step reduces the perspective problem to an absolute orientation problem (which has a solution via explicit formula). To solve the first problem we set coordinates which are as orientation-free as possible: on the 3D points side our coordinates are the squared distances between the points. On the 2D canvas-points side our coordinates are the dot products of the points after rotating one of them to sit on the optical axis. We then derive the solution with the help of a computer algebra system.
Authors: Ioannis Sarridis, Christos Koutlis, Giorgos Kordopatis-Zilos, Ioannis Kompatsiaris, Symeon Papadopoulos
Abstract: In this paper, we introduce InDistill, a method that serves as a warmup stage for enhancing Knowledge Distillation (KD) effectiveness. InDistill focuses on transferring critical information flow paths from a heavyweight teacher to a lightweight student. This is achieved via a training scheme based on curriculum learning that considers the distillation difficulty of each layer and the critical learning periods when the information flow paths are established. This procedure can lead to a student model that is better prepared to learn from the teacher. To ensure the applicability of InDistill across a wide range of teacher-student pairs, we also incorporate a pruning operation when there is a discrepancy in the width of the teacher and student layers. This pruning operation reduces the width of the teacher's intermediate layers to match those of the student, allowing direct distillation without the need for an encoding stage. The proposed method is extensively evaluated using various pairs of teacher-student architectures on CIFAR-10, CIFAR-100, and ImageNet datasets demonstrating that preserving the information flow paths consistently increases the performance of the baseline KD approaches on both classification and retrieval settings. The code is available at https://github.com/gsarridis/InDistill.
Authors: Clement Tan, Chai Kiat Yeo, Cheston Tan, Basura Fernando
Abstract: Abductive reasoning aims to make the most likely inference for a given set of incomplete observations. In this paper, we introduce "Abductive Past Action Inference", a novel research task aimed at identifying the past actions performed by individuals within homes to reach specific states captured in a single image, using abductive inference. The research explores three key abductive inference problems: past action set prediction, past action sequence prediction, and abductive past action verification. We introduce several models tailored for abductive past action inference, including a relational graph neural network, a relational bilinear pooling model, and a relational transformer model. Notably, the newly proposed object-relational bilinear graph encoder-decoder (BiGED) model emerges as the most effective among all methods evaluated, demonstrating good proficiency in handling the intricacies of the Action Genome dataset. The contributions of this research significantly advance the ability of deep learning models to reason about current scene evidence and make highly plausible inferences about past human actions. This advancement enables a deeper understanding of events and behaviors, which can enhance decision-making and improve system capabilities across various real-world applications such as Human-Robot Interaction and Elderly Care and Health Monitoring. Code and data available at https://github.com/LUNAProject22/AAR
Authors: Hanlin Wang, Yilu Wu, Sheng Guo, Limin Wang
Abstract: In this paper, we study the problem of procedure planning in instructional videos, which aims to make a plan (i.e. a sequence of actions) given the current visual observation and the desired goal. Previous works cast this as a sequence modeling problem and leverage either intermediate visual observations or language instructions as supervision to make autoregressive planning, resulting in complex learning schemes and expensive annotation costs. To avoid intermediate supervision annotation and error accumulation caused by planning autoregressively, we propose a diffusion-based framework, coined as PDPP, to directly model the whole action sequence distribution with task label as supervision instead. Our core idea is to treat procedure planning as a distribution fitting problem under the given observations, thus transform the planning problem to a sampling process from this distribution during inference. The diffusion-based modeling approach also effectively addresses the uncertainty issue in procedure planning. Based on PDPP, we further apply joint training to our framework to generate plans with varying horizon lengths using a single model and reduce the number of training parameters required. We instantiate our PDPP with three popular diffusion models and investigate a series of condition-introducing methods in our framework, including condition embeddings, MoEs, two-stage prediction and Classifier-Free Guidance strategy. Finally, we apply our PDPP to the Visual Planners for human Assistance problem which requires the goal specified in natural language rather than visual observation. We conduct experiments on challenging datasets of different scales and our PDPP model achieves the state-of-the-art performance on multiple metrics, even compared with those strongly-supervised counterparts. These results further demonstrates the effectiveness and generalization ability of our model.
Authors: Christos Sakaridis, David Bruggemann, Fisher Yu, Luc Van Gool
Abstract: Adaptation of semantic segmentation networks to different visual conditions is vital for robust perception in autonomous cars and robots. However, previous work has shown that most feature-level adaptation methods, which employ adversarial training and are validated on synthetic-to-real adaptation, provide marginal gains in condition-level adaptation, being outperformed by simple pixel-level adaptation via stylization. Motivated by these findings, we propose to leverage stylization in performing feature-level adaptation by aligning the internal network features extracted by the encoder of the network from the original and the stylized view of each input image with a novel feature invariance loss. In this way, we encourage the encoder to extract features that are already invariant to the style of the input, allowing the decoder to focus on parsing these features and not on further abstracting from the specific style of the input. We implement our method, named Condition-Invariant Semantic Segmentation (CISS), on the current state-of-the-art domain adaptation architecture and achieve outstanding results on condition-level adaptation. In particular, CISS sets the new state of the art in the popular daytime-to-nighttime Cityscapes$\to$Dark Zurich benchmark. Furthermore, our method achieves the second-best performance on the normal-to-adverse Cityscapes$\to$ACDC benchmark. CISS is shown to generalize well to domains unseen during training, such as BDD100K-night and ACDC-night. Code is publicly available at https://github.com/SysCV/CISS .
Authors: Lorenzo Baraldi, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Andrea Pilzer, Rita Cucchiara
Abstract: The use of self-supervised pre-training has emerged as a promising approach to enhance the performance of many different visual tasks. In this context, recent approaches have employed the Masked Image Modeling paradigm, which pre-trains a backbone by reconstructing visual tokens associated with randomly masked image patches. This masking approach, however, introduces noise into the input data during pre-training, leading to discrepancies that can impair performance during the fine-tuning phase. Furthermore, input masking neglects the dependencies between corrupted patches, increasing the inconsistencies observed in downstream fine-tuning tasks. To overcome these issues, we propose a new self-supervised pre-training approach, named Masked and Permuted Vision Transformer (MaPeT), that employs autoregressive and permuted predictions to capture intra-patch dependencies. In addition, MaPeT employs auxiliary positional information to reduce the disparity between the pre-training and fine-tuning phases. In our experiments, we employ a fair setting to ensure reliable and meaningful comparisons and conduct investigations on multiple visual tokenizers, including our proposed $k$-CLIP which directly employs discretized CLIP features. Our results demonstrate that MaPeT achieves competitive performance on ImageNet, compared to baselines and competitors under the same model setting. We release an implementation of our code and models at https://github.com/aimagelab/MaPeT.
Authors: Jinsong Zhang, Minjie Zhu, Yuxiang Zhang, Yebin Liu, Kun Li
Abstract: This paper addresses the problem of generating whole-body motion from speech. Despite great successes, prior methods still struggle to produce reasonable and diverse whole-body motions from speech. This is due to their reliance on suboptimal representations and a lack of strategies for generating diverse results. To address these challenges, we present a novel hybrid point representation to achieve accurate and continuous motion generation, e.g., avoiding foot skating, and this representation can be transformed into an easy-to-use representation, i.e., SMPL-X body mesh, for many applications. To generate whole-body motion from speech, for facial motion, closely tied to the audio signal, we introduce an encoder-decoder architecture to achieve deterministic outcomes. However, for the body and hands, which have weaker connections to the audio signal, we aim to generate diverse yet reasonable motions. To boost diversity in motion generation, we propose a contrastive motion learning method to encourage the model to produce more distinctive representations. Specifically, we design a robust VQ-VAE to learn a quantized motion codebook using our hybrid representation. Then, we regress the motion representation from the audio signal by a translation model employing our contrastive motion learning method. Experimental results validate the superior performance and the correctness of our model. The project page is available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/SpeechAct.
URLs: http://cic.tju.edu.cn/faculty/likun/projects/SpeechAct.
Authors: Rixin Zhou, Ding Xia, Yi Zhang, Honglin Pang, Xi Yang, Chuntao Li
Abstract: In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods to match similar contour shapes or textures, which are always difficult to tune hyperparameters for extensive data and computationally time-consuming. Therefore, we propose a neural network that can effectively utilize neighbor textures with contour shape information to fundamentally improve performance. First, we employ a graph-based network to extract the local contour and texture features of fragments. Then, for the pair-searching task, we adopt a linear transformer-based module to integrate these local features and use contrastive loss to encode the global features of each fragment. For the pair-matching task, we design a weighted fusion module to dynamically fuse extracted local contour and texture features, and formulate a similarity matrix for each pair of fragments to calculate the matching score and infer the adjacent segment of contours. To faithfully evaluate our proposed network, we created a new image fragment dataset through an algorithm we designed that tears complete images into irregular fragments. The experimental results show that our proposed network achieves excellent pair-searching accuracy, reduces matching errors, and significantly reduces computational time. Details, sourcecode, and data are available in our supplementary material.
Authors: Jeonghwan Kim, Jisoo Kim, Jeonghyeon Na, Hanbyul Joo
Abstract: To enable machines to understand the way humans interact with the physical world in daily life, 3D interaction signals should be captured in natural settings, allowing people to engage with multiple objects in a range of sequential and casual manipulations. To achieve this goal, we introduce our ParaHome system designed to capture dynamic 3D movements of humans and objects within a common home environment. Our system features a multi-view setup with 70 synchronized RGB cameras, along with wearable motion capture devices including an IMU-based body suit and hand motion capture gloves. By leveraging the ParaHome system, we collect a new human-object interaction dataset, including 486 minutes of sequences across 207 captures with 38 participants, offering advancements with three key aspects: (1) capturing body motion and dexterous hand manipulation motion alongside multiple objects within a contextual home environment; (2) encompassing sequential and concurrent manipulations paired with text descriptions; and (3) including articulated objects with multiple parts represented by 3D parameterized models. We present detailed design justifications for our system, and perform key generative modeling experiments to demonstrate the potential of our dataset.
Authors: Bumsoo Kim, Wonseop Shin, Kyuchul Lee, Yonghoon Jung, Sanghyun Seo
Abstract: Leveraging large-scale Text-to-Image (TTI) models have become a common technique for generating exemplar or training dataset in the fields of image synthesis, video editing, 3D reconstruction. However, semantic structural visual hallucinations involving perceptually severe defects remain a concern, especially in the domain of non-photorealistic rendering (NPR) such as cartoons and pixelization-style character. To detect these hallucinations in NPR, We propose a novel semantic structural hallucination detection system using Vision-Language Model (VLM). Our approach is to leverage the emerging capability of large language model, in-context learning which denotes that VLM has seen some examples by user for specific downstream task, here hallucination detection. Based on in-context learning, we introduce pose-aware in-context visual learning (PA-ICVL) which improve the overall performance of VLM by further inputting visual data beyond prompts, RGB images and pose information. By incorporating pose guidance, we enable VLMs to make more accurate decisions. Experimental results demonstrate significant improvements in identifying visual hallucinations compared to baseline methods relying solely on RGB images. Within selected two VLMs, GPT-4v, Gemini pro vision, our proposed PA-ICVL improves the hallucination detection with 50% to 78%, 57% to 80%, respectively. This research advances a capability of TTI models toward real-world applications by mitigating visual hallucinations via in-context visual learning, expanding their potential in non-photorealistic domains. In addition, it showcase how users can boost the downstream-specialized capability of open VLM by harnessing additional conditions. We collect synthetic cartoon-hallucination dataset with TTI models, this dataset and final tuned VLM will be publicly available.
Authors: Yuxuan Wang, Xiaoyuan Liu
Abstract: Scene Graph Generation (SGG) provides basic language representation of visual scenes, requiring models to grasp complex and diverse semantics between objects. This complexity and diversity in SGG leads to underrepresentation, where parts of triplet labels are rare or even unseen during training, resulting in imprecise predictions. To tackle this, we propose integrating the pretrained Vision-language Models to enhance representation. However, due to the gap between pretraining and SGG, direct inference of pretrained VLMs on SGG leads to severe bias, which stems from the imbalanced predicates distribution in the pretraining language set. To alleviate the bias, we introduce a novel LM Estimation to approximate the unattainable predicates distribution. Finally, we ensemble the debiased VLMs with SGG models to enhance the representation, where we design a certainty-aware indicator to score each sample and dynamically adjust the ensemble weights. Our training-free method effectively addresses the predicates bias in pretrained VLMs, enhances SGG's representation, and significantly improve the performance.
Authors: Xixuan Hao, Wei Chen, Yibo Yan, Siru Zhong, Kun Wang, Qingsong Wen, Yuxuan Liang
Abstract: Urban socioeconomic indicator prediction aims to infer various metrics related to sustainable development in diverse urban landscapes using data-driven methods. However, prevalent pretrained models, particularly those reliant on satellite imagery, face dual challenges. Firstly, concentrating solely on macro-level patterns from satellite data may introduce bias, lacking nuanced details at micro levels, such as architectural details at a place. Secondly, the text generated by the precursor work UrbanCLIP, which fully utilizes the extensive knowledge of LLMs, frequently exhibits issues such as hallucination and homogenization, resulting in a lack of reliable quality. In response to these issues, we devise a novel framework entitled UrbanVLP based on Vision-Language Pretraining. Our UrbanVLP seamlessly integrates multi-granularity information from both macro (satellite) and micro (street-view) levels, overcoming the limitations of prior pretrained models. Moreover, it introduces automatic text generation and calibration, providing a robust guarantee for producing high-quality text descriptions of urban imagery. Rigorous experiments conducted across six socioeconomic indicator prediction tasks underscore its superior performance.
Authors: Yulin Pan, Chaojie Mao, Zeyinzi Jiang, Zhen Han, Jingfeng Zhang, Xiangteng He
Abstract: Prior studies have made significant progress in image inpainting guided by either text description or subject image. However, the research on inpainting with flexible guidance or control, i.e., text-only, image-only, and their combination, is still in the early stage. Therefore, in this paper, we introduce the multimodal promptable image inpainting project: a new task model, and data for taming customized image inpainting. We propose LAR-Gen, a novel approach for image inpainting that enables seamless inpainting of specific region in images corresponding to the mask prompt, incorporating both the text prompt and image prompt. Our LAR-Gen adopts a coarse-to-fine manner to ensure the context consistency of source image, subject identity consistency, local semantic consistency to the text description, and smoothness consistency. It consists of three mechanisms: (i) Locate mechanism: concatenating the noise with masked scene image to achieve precise regional editing, (ii) Assign mechanism: employing decoupled cross-attention mechanism to accommodate multi-modal guidance, and (iii) Refine mechanism: using a novel RefineNet to supplement subject details. Additionally, to address the issue of scarce training data, we introduce a novel data engine to automatically extract substantial pairs of data consisting of local text prompts and corresponding visual instances from a vast image data, leveraging publicly available pre-trained large models. Extensive experiments and various application scenarios demonstrate the superiority of LAR-Gen in terms of both identity preservation and text semantic consistency.
Authors: Chiara Plizzari, Shubham Goel, Toby Perrett, Jacob Chalk, Angjoo Kanazawa, Dima Damen
Abstract: As humans move around, performing their daily tasks, they are able to recall where they have positioned objects in their environment, even if these objects are currently out of their sight. In this paper, we aim to mimic this spatial cognition ability. We thus formulate the task of Out of Sight, Not Out of Mind - 3D tracking active objects using observations captured through an egocentric camera. We introduce a simple but effective approach to address this challenging problem, called Lift, Match, and Keep (LMK). LMK lifts partial 2D observations to 3D world coordinates, matches them over time using visual appearance, 3D location and interactions to form object tracks, and keeps these object tracks even when they go out-of-view of the camera. We benchmark LMK on 100 long videos from EPIC-KITCHENS. Our results demonstrate that spatial cognition is critical for correctly locating objects over short and long time scales. E.g., for one long egocentric video, we estimate the 3D location of 50 active objects. After 120 seconds, 57% of the objects are correctly localised by LMK, compared to just 33% by a recent 3D method for egocentric videos and 17% by a general 2D tracking method.
Authors: Hongzhi You, Yijun Cao, Wei Yuan, Fanjun Wang, Ning Qiao, Yongjie Li
Abstract: From a perspective of feature matching, optical flow estimation for event cameras involves identifying event correspondences by comparing feature similarity across accompanying event frames. In this work, we introduces an effective and robust high-dimensional (HD) feature descriptor for event frames, utilizing Vector Symbolic Architectures (VSA). The topological similarity among neighboring variables within VSA contributes to the enhanced representation similarity of feature descriptors for flow-matching points, while its structured symbolic representation capacity facilitates feature fusion from both event polarities and multiple spatial scales. Based on this HD feature descriptor, we propose a novel feature matching framework for event-based optical flow, encompassing both model-based (VSA-Flow) and self-supervised learning (VSA-SM) methods. In VSA-Flow, accurate optical flow estimation validates the effectiveness of HD feature descriptors. In VSA-SM, a novel similarity maximization method based on the HD feature descriptor is proposed to learn optical flow in a self-supervised way from events alone, eliminating the need for auxiliary grayscale images. Evaluation results demonstrate that our VSA-based method achieves superior accuracy in comparison to both model-based and self-supervised learning methods on the DSEC benchmark, while remains competitive among both methods on the MVSEC benchmark. This contribution marks a significant advancement in event-based optical flow within the feature matching methodology.
Authors: Weijie Li, Wei Yang, Yuenan Hou, Li Liu, Yongxiang Liu, Xiang Li
Abstract: Despite the remarkable progress in synthetic aperture radar automatic target recognition (SAR ATR), recent efforts have concentrated on detecting and classifying a specific category, e.g., vehicles, ships, airplanes, or buildings. One of the fundamental limitations of the top-performing SAR ATR methods is that the learning paradigm is supervised, task-specific, limited-category, closed-world learning, which depends on massive amounts of accurately annotated samples that are expensively labeled by expert SAR analysts and have limited generalization capability and scalability. In this work, we make the first attempt towards building a foundation model for SAR ATR, termed SARATR-X. SARATR-X learns generalizable representations via self-supervised learning (SSL) and provides a cornerstone for label-efficient model adaptation to generic SAR target detection and classification tasks. Specifically, SARATR-X is trained on 0.18 M unlabelled SAR target samples, which are curated by combining contemporary benchmarks and constitute the largest publicly available dataset till now. Considering the characteristics of SAR images, a backbone tailored for SAR ATR is carefully designed, and a two-step SSL method endowed with multi-scale gradient features was applied to ensure the feature diversity and model scalability of SARATR-X. The capabilities of SARATR-X are evaluated on classification under few-shot and robustness settings and detection across various categories and scenes, and impressive performance is achieved, often competitive with or even superior to prior fully supervised, semi-supervised, or self-supervised algorithms. Our SARATR-X and the curated dataset are released at https://github.com/waterdisappear/SARATR-X to foster research into foundation models for SAR image interpretation.
Authors: Haoran Chen, Micah Goldblum, Zuxuan Wu, Yu-Gang Jiang
Abstract: Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias towards the most recent task. Traditionally, methods have relied on incorporating data from past tasks during training to mitigate this issue. However, the recent shift in continual learning to memory-free environments has rendered these approaches infeasible. In this study, we propose a solution focused on the testing phase. We first introduce a simple Out-of-Task Detection method, OTD, designed to accurately identify samples from past tasks during testing. Leveraging OTD, we then propose: (1) an Adaptive Retention mechanism for dynamically tuning the classifier layer on past task data; (2) an Adaptive Correction mechanism for revising predictions when the model classifies data from previous tasks into classes from the current task. We name our approach Adaptive Retention & Correction (ARC). While designed for memory-free environments, ARC also proves effective in memory-based settings. Extensive experiments show that our proposed method can be plugged in to virtually any existing continual learning approach without requiring any modifications to its training procedure. Specifically, when integrated with state-of-the-art approaches, ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets, respectively.
Authors: Zander W. Blasingame, Chen Liu
Abstract: The optimization of the latents and parameters of diffusion models with respect to some differentiable metric defined on the output of the model is a challenging and complex problem. The sampling for diffusion models is done by solving either the probability flow ODE or diffusion SDE wherein a neural network approximates the score function allowing a numerical ODE/SDE solver to be used. However, naive backpropagation techniques are memory intensive, requiring the storage of all intermediate states, and face additional complexity in handling the injected noise from the diffusion term of the diffusion SDE. We propose a novel family of bespoke ODE solvers to the continuous adjoint equations for diffusion models, which we call AdjointDEIS. We exploit the unique construction of diffusion SDEs to further simplify the formulation of the continuous adjoint equations using exponential integrators. Moreover, we provide convergence order guarantees for our bespoke solvers. Significantly, we show that continuous adjoint equations for diffusion SDEs actually simplify to a simple ODE. Lastly, we demonstrate the effectiveness of AdjointDEIS for guided generation with an adversarial attack in the form of the face morphing problem. Our code will be released at https: //github.com/zblasingame/AdjointDEIS.
Authors: Yongkun Du, Zhineng Chen, Caiyan Jia, Xieping Gao, Yu-Gang Jiang
Abstract: Scene Text Recognition (STR) methods have demonstrated robust performance in word-level text recognition. However, in real applications the text image is sometimes long due to detected with multiple horizontal words. It triggers the requirement to build long text recognition models from readily available short (i.e., word-level) text datasets, which has been less studied previously. In this paper, we term this task Out of Length (OOL) text recognition. We establish the first Long Text Benchmark (LTB) to facilitate the assessment of different methods in long text recognition. Meanwhile, we propose a novel method called OOL Text Recognition with sub-String Matching (SMTR). SMTR comprises two cross-attention-based modules: one encodes a sub-string containing multiple characters into next and previous queries, and the other employs the queries to attend to the image features, matching the sub-string and simultaneously recognizing its next and previous character. SMTR can recognize text of arbitrary length by iterating the process above. To avoid being trapped in recognizing highly similar sub-strings, we introduce a regularization training to compel SMTR to effectively discover subtle differences between similar sub-strings for precise matching. In addition, we propose an inference augmentation strategy to alleviate confusion caused by identical sub-strings in the same text and improve the overall recognition efficiency. Extensive experimental results reveal that SMTR, even when trained exclusively on short text, outperforms existing methods in public short text benchmarks and exhibits a clear advantage on LTB. Code: https://github.com/Topdu/OpenOCR.
Authors: Rabiul Awal, Saba Ahmadi, Le Zhang, Aishwarya Agrawal
Abstract: Fine-grained understanding of objects, attributes, and relationships between objects is crucial for visual-language models (VLMs). Existing benchmarks primarily focus on evaluating VLMs' capability to distinguish between two very similar captions given an image. In this paper, we introduce a new, challenging benchmark termed Visual Minimal-Change Understanding (VisMin), which requires models to predict the correct image-caption match given two images and two captions. The image pair and caption pair contain minimal changes, i.e., only one aspect changes at a time from among the following: object, attribute, count, and spatial relation. These changes test the models' understanding of objects, attributes (such as color, material, shape), counts, and spatial relationships between objects. We built an automatic framework using large language models and diffusion models, followed by a rigorous 4-step verification process by human annotators. Empirical experiments reveal that current VLMs exhibit notable deficiencies in understanding spatial relationships and counting abilities. We also generate a large-scale training dataset to finetune CLIP and Idefics2, showing significant improvements in fine-grained understanding across benchmarks and in CLIP's general image-text alignment. We release all resources, including the benchmark, training data, and finetuned model checkpoints, at https://vismin.net/.
URLs: https://vismin.net/.
Authors: Palak Handa, Amirreza Mahbod, Florian Schwarzhans, Ramona Woitek, Nidhi Goel, Manas Dhir, Deepti Chhabra, Shreshtha Jha, Pallavi Sharma, Vijay Thakur, Simarpreet Singh Chawla, Deepak Gunjan, Jagadeesh Kakarla, Balasubramanian Raman
Abstract: We present the Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy. It was virtually organized by the Research Center for Medical Image Analysis and Artificial Intelligence (MIAAI), Department of Medicine, Danube Private University, Krems, Austria in collaboration with the 9th International Conference on Computer Vision & Image Processing (CVIP 2024) being organized by the Indian Institute of Information Technology, Design and Manufacturing (IIITDM) Kancheepuram, Chennai, India. This document provides an overview of the challenge, including the registration process, rules, submission format, description of the datasets used, qualified team rankings, all team descriptions, and the benchmarking results reported by the organizers.
Authors: Utkarsh Nath, Rajeev Goel, Eun Som Jeon, Changhoon Kim, Kyle Min, Yezhou Yang, Yingzhen Yang, Pavan Turaga
Abstract: To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines. However, the diffusion models used in these techniques are prone to viewpoint bias and thus lead to geometric inconsistencies such as the Janus problem. To counter this, we introduce MT3D, a text-to-3D generative model that leverages a high-fidelity 3D object to overcome viewpoint bias and explicitly infuse geometric understanding into the generation pipeline. Firstly, we employ depth maps derived from a high-quality 3D model as control signals to guarantee that the generated 2D images preserve the fundamental shape and structure, thereby reducing the inherent viewpoint bias. Next, we utilize deep geometric moments to ensure geometric consistency in the 3D representation explicitly. By incorporating geometric details from a 3D asset, MT3D enables the creation of diverse and geometrically consistent objects, thereby improving the quality and usability of our 3D representations. Project page and code: https://moment-3d.github.io/
Authors: Yusuke Hirota, Min-Hung Chen, Chien-Yi Wang, Yuta Nakashima, Yu-Chiang Frank Wang, Ryo Hachiuma
Abstract: Large-scale vision-language models, such as CLIP, are known to contain societal bias regarding protected attributes (e.g., gender, age). This paper aims to address the problems of societal bias in CLIP. Although previous studies have proposed to debias societal bias through adversarial learning or test-time projecting, our comprehensive study of these works identifies two critical limitations: 1) loss of attribute information when it is explicitly disclosed in the input and 2) use of the attribute annotations during debiasing process. To mitigate societal bias in CLIP and overcome these limitations simultaneously, we introduce a simple-yet-effective debiasing method called SANER (societal attribute neutralizer) that eliminates attribute information from CLIP text features only of attribute-neutral descriptions. Experimental results show that SANER, which does not require attribute annotations and preserves original information for attribute-specific descriptions, demonstrates superior debiasing ability than the existing methods. Additionally, we observe that SANER does not require retraining CLIP from scratch with the original dataset. Moreover, the debiased model can be directly applied to the text-to-image generation model by simply replacing the text encoder.
Authors: Francesco Di Salvo, Sebastian Doerrich, Ines Rieger, Christian Ledig
Abstract: The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address label noise exhibit severe limitations due to computational complexity and application dependency. In this work, we propose WANN, a Weighted Adaptive Nearest Neighbor approach that builds on self-supervised feature representations obtained from foundation models. To guide the weighted voting scheme, we introduce a reliability score, which measures the likelihood of a data label being correct. WANN outperforms reference methods, including a linear layer trained with robust loss functions, on diverse datasets of varying size and under various noise types and severities. WANN also exhibits superior generalization on imbalanced data compared to both Adaptive-NNs (ANN) and fixed k-NNs. Furthermore, the proposed weighting scheme enhances supervised dimensionality reduction under noisy labels. This yields a significant boost in classification performance with 10x and 100x smaller image embeddings, minimizing latency and storage requirements. Our approach, emphasizing efficiency and explainability, emerges as a simple, robust solution to overcome inherent limitations of deep neural network training. The code is available at https://github.com/francescodisalvo05/wann-noisy-labels .
URLs: https://github.com/francescodisalvo05/wann-noisy-labels
Authors: Zhuoyan Luo, Fengyuan Shi, Yixiao Ge, Yujiu Yang, Limin Wang, Ying Shan
Abstract: We present Open-MAGVIT2, a family of auto-regressive image generation models ranging from 300M to 1.5B. The Open-MAGVIT2 project produces an open-source replication of Google's MAGVIT-v2 tokenizer, a tokenizer with a super-large codebook (i.e., $2^{18}$ codes), and achieves the state-of-the-art reconstruction performance (1.17 rFID) on ImageNet $256 \times 256$. Furthermore, we explore its application in plain auto-regressive models and validate scalability properties. To assist auto-regressive models in predicting with a super-large vocabulary, we factorize it into two sub-vocabulary of different sizes by asymmetric token factorization, and further introduce "next sub-token prediction" to enhance sub-token interaction for better generation quality. We release all models and codes to foster innovation and creativity in the field of auto-regressive visual generation.
Authors: David Tschirschwitz, Volker Rodehorst
Abstract: Annotation errors are a challenge not only during training of machine learning models, but also during their evaluation. Label variations and inaccuracies in datasets often manifest as contradictory examples that deviate from established labeling conventions. Such inconsistencies, when significant, prevent models from achieving optimal performance on metrics such as mean Average Precision (mAP). We introduce the notion of "label convergence" to describe the highest achievable performance under the constraint of contradictory test annotations, essentially defining an upper bound on model accuracy. Recognizing that noise is an inherent characteristic of all data, our study analyzes five real-world datasets, including the LVIS dataset, to investigate the phenomenon of label convergence. We approximate that label convergence is between 62.63-67.52 mAP@[0.5:0.95:0.05] for LVIS with 95% confidence, attributing these bounds to the presence of real annotation errors. With current state-of-the-art (SOTA) models at the upper end of the label convergence interval for the well-studied LVIS dataset, we conclude that model capacity is sufficient to solve current object detection problems. Therefore, future efforts should focus on three key aspects: (1) updating the problem specification and adjusting evaluation practices to account for unavoidable label noise, (2) creating cleaner data, especially test data, and (3) including multi-annotated data to investigate annotation variation and make these issues visible from the outset.
Authors: Ayca Takmaz, Alexandros Delitzas, Robert W. Sumner, Francis Engelmann, Johanna Wald, Federico Tombari
Abstract: Open-vocabulary 3D segmentation enables exploration of 3D spaces using free-form text descriptions. Existing methods for open-vocabulary 3D instance segmentation primarily focus on identifying object-level instances but struggle with finer-grained scene entities such as object parts, or regions described by generic attributes. In this work, we introduce Search3D, an approach to construct hierarchical open-vocabulary 3D scene representations, enabling 3D search at multiple levels of granularity: fine-grained object parts, entire objects, or regions described by attributes like materials. Unlike prior methods, Search3D shifts towards a more flexible open-vocabulary 3D search paradigm, moving beyond explicit object-centric queries. For systematic evaluation, we further contribute a scene-scale open-vocabulary 3D part segmentation benchmark based on MultiScan, along with a set of open-vocabulary fine-grained part annotations on ScanNet++. Search3D outperforms baselines in scene-scale open-vocabulary 3D part segmentation, while maintaining strong performance in segmenting 3D objects and materials. Our project page is http://search3d-segmentation.github.io.
Authors: Qian Zhang
Abstract: Prompt tuning for vision-language models such as CLIP involves optimizing the text prompts used to generate image-text pairs for specific downstream tasks. While hand-crafted or template-based prompts are generally applicable to a wider range of unseen classes, they tend to perform poorly in downstream tasks (i.e., seen classes). Learnable soft prompts, on the other hand, often perform well in downstream tasks but lack generalizability. Additionally, prior research has predominantly concentrated on the textual modality, with very few studies attempting to explore the prompt's generalization potential from the visual modality. Keeping these limitations in mind, we investigate how to prompt tuning to obtain both a competitive downstream performance and generalization. The study shows that by treating soft and hand-crafted prompts as dual views of the textual modality, and maximizing their mutual information, we can better ensemble task-specific and general semantic information. Moreover, to generate more expressive prompts, the study introduces a class-wise augmentation from the visual modality, resulting in significant robustness to a wider range of unseen classes. Extensive evaluations on several benchmarks report that the proposed approach achieves competitive results in terms of both task-specific performance and general abilities.
Authors: Joey Wilson, Ruihan Xu, Yile Sun, Parker Ewen, Minghan Zhu, Kira Barton, Maani Ghaffari
Abstract: This paper introduces a novel probabilistic mapping algorithm, LatentBKI, which enables open-vocabulary mapping with quantifiable uncertainty. Traditionally, semantic mapping algorithms focus on a fixed set of semantic categories which limits their applicability for complex robotic tasks. Vision-Language (VL) models have recently emerged as a technique to jointly model language and visual features in a latent space, enabling semantic recognition beyond a predefined, fixed set of semantic classes. LatentBKI recurrently incorporates neural embeddings from VL models into a voxel map with quantifiable uncertainty, leveraging the spatial correlations of nearby observations through Bayesian Kernel Inference (BKI). LatentBKI is evaluated against similar explicit semantic mapping and VL mapping frameworks on the popular Matterport3D and Semantic KITTI datasets, demonstrating that LatentBKI maintains the probabilistic benefits of continuous mapping with the additional benefit of open-dictionary queries. Real-world experiments demonstrate applicability to challenging indoor environments.
Authors: Ling-Hao Chen, Shunlin Lu, Wenxun Dai, Zhiyang Dou, Xuan Ju, Jingbo Wang, Taku Komura, Lei Zhang
Abstract: This research delves into the problem of interactive editing of human motion generation. Previous motion diffusion models lack explicit modeling of the word-level text-motion correspondence and good explainability, hence restricting their fine-grained editing ability. To address this issue, we propose an attention-based motion diffusion model, namely MotionCLR, with CLeaR modeling of attention mechanisms. Technically, MotionCLR models the in-modality and cross-modality interactions with self-attention and cross-attention, respectively. More specifically, the self-attention mechanism aims to measure the sequential similarity between frames and impacts the order of motion features. By contrast, the cross-attention mechanism works to find the fine-grained word-sequence correspondence and activate the corresponding timesteps in the motion sequence. Based on these key properties, we develop a versatile set of simple yet effective motion editing methods via manipulating attention maps, such as motion (de-)emphasizing, in-place motion replacement, and example-based motion generation, etc. For further verification of the explainability of the attention mechanism, we additionally explore the potential of action-counting and grounded motion generation ability via attention maps. Our experimental results show that our method enjoys good generation and editing ability with good explainability.
Authors: Xiufeng Song, Xiao Guo, Jiache Zhang, Qirui Li, Lei Bai, Xiaoming Liu, Guangtao Zhai, Xiaohong Liu
Abstract: Large numbers of synthesized videos from diffusion models pose threats to information security and authenticity, leading to an increasing demand for generated content detection. However, existing video-level detection algorithms primarily focus on detecting facial forgeries and often fail to identify diffusion-generated content with a diverse range of semantics. To advance the field of video forensics, we propose an innovative algorithm named Multi-Modal Detection(MM-Det) for detecting diffusion-generated videos. MM-Det utilizes the profound perceptual and comprehensive abilities of Large Multi-modal Models (LMMs) by generating a Multi-Modal Forgery Representation (MMFR) from LMM's multi-modal space, enhancing its ability to detect unseen forgery content. Besides, MM-Det leverages an In-and-Across Frame Attention (IAFA) mechanism for feature augmentation in the spatio-temporal domain. A dynamic fusion strategy helps refine forgery representations for the fusion. Moreover, we construct a comprehensive diffusion video dataset, called Diffusion Video Forensics (DVF), across a wide range of forgery videos. MM-Det achieves state-of-the-art performance in DVF, demonstrating the effectiveness of our algorithm. Both source code and DVF are available at https://github.com/SparkleXFantasy/MM-Det.
Authors: Mehmet Can Yavuz, Yang Yang
Abstract: In biomedical imaging analysis, the dichotomy between 2D and 3D data presents a significant challenge. While 3D volumes offer superior real-world applicability, they are less available for each modality and not easy to train in large scale, whereas 2D samples are abundant but less comprehensive. This paper introduces \texttt{Cross-D Conv} operation, a novel approach that bridges the dimensional gap by learning the phase shifting in the Fourier domain. Our method enables seamless weight transfer between 2D and 3D convolution operations, effectively facilitating cross-dimensional learning. The proposed architecture leverages the abundance of 2D training data to enhance 3D model performance, offering a practical solution to the multimodal data scarcity challenge in 3D medical model pretraining. Experimental validation on the RadImagenet (2D) and multimodal volumetric sets demonstrates that our approach achieves comparable or superior performance in feature quality assessment. The enhanced convolution operation presents new opportunities for developing efficient classification and segmentation models in medical imaging. This work represents an advancement in cross-dimensional and multimodal medical image analysis, offering a robust framework for utilizing 2D priors in 3D model pretraining while maintaining computational efficiency of 2D training.
Authors: Chinmay Talegaonkar, Yash Belhe, Ravi Ramamoorthi, Nicholas Antipa
Abstract: Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We show that splatting and its approximations are unnecessary, even within a rasterizer; we instead volumetrically integrate 3D Gaussians directly to compute the transmittance across them analytically. We use this analytic transmittance to derive more physically-accurate alpha values than 3DGS, which can directly be used within their framework. The result is a method that more closely follows the volume rendering equation (similar to ray-tracing) while enjoying the speed benefits of rasterization. Our method represents opaque surfaces with higher accuracy and fewer points than 3DGS. This enables it to outperform 3DGS for view synthesis (measured in SSIM and LPIPS). Being volumetrically consistent also enables our method to work out of the box for tomography. We match the state-of-the-art 3DGS-based tomography method with fewer points.
Authors: Jakob Nolte, Maureen M. J. Guichelaar, Donald E. Bouman, Stephanie M. van den Berg, Maryam Amir Haeri
Abstract: Longitudinal MRI analysis is crucial for predicting disease outcomes, particularly in chronic conditions like hepatocellular carcinoma (HCC), where early detection can significantly influence treatment strategies and patient prognosis. Yet, due to challenges like limited data availability, subtle parenchymal changes, and the irregular timing of medical screenings, current approaches have so far focused on cross-sectional imaging data. To address this, we propose HCCNet, a novel model architecture that integrates a 3D adaptation of the ConvNeXt CNN architecture with a Transformer encoder, capturing both the intricate spatial features of 3D MRIs and the complex temporal dependencies across different time points. HCCNet utilizes a two-stage pre-training process tailored for longitudinal MRI data. The CNN backbone is pre-trained using a self-supervised learning framework adapted for 3D MRIs, while the Transformer encoder is pre-trained with a sequence-order-prediction task to enhance its understanding of disease progression over time. We demonstrate the effectiveness of HCCNet by applying it to a cohort of liver cirrhosis patients undergoing regular MRI screenings for HCC surveillance. Our results show that HCCNet significantly improves predictive accuracy and reliability over baseline models, providing a robust tool for personalized HCC surveillance. The methodological approach presented in this paper is versatile and can be adapted to various longitudinal MRI screening applications. Its ability to handle varying patient record lengths and irregular screening intervals establishes it as an invaluable framework for monitoring chronic diseases, where timely and accurate disease prognosis is critical for effective treatment planning.
Authors: Zonglei Jing, Zonghao Ying, Le Wang, Siyuan Liang, Aishan Liu, Xianglong Liu, Dacheng Tao
Abstract: The development of text-to-image (T2I) generative models, that enable the creation of high-quality synthetic images from textual prompts, has opened new frontiers in creative design and content generation. However, this paper reveals a significant and previously unrecognized ethical risk inherent in this technology and introduces a novel method, termed the Cognitive Morphing Attack (CogMorph), which manipulates T2I models to generate images that retain the original core subjects but embeds toxic or harmful contextual elements. This nuanced manipulation exploits the cognitive principle that human perception of concepts is shaped by the entire visual scene and its context, producing images that amplify emotional harm far beyond attacks that merely preserve the original semantics. To address this, we first construct an imagery toxicity taxonomy spanning 10 major and 48 sub-categories, aligned with human cognitive-perceptual dimensions, and further build a toxicity risk matrix resulting in 1,176 high-quality T2I toxic prompts. Based on this, our CogMorph first introduces Cognitive Toxicity Augmentation, which develops a cognitive toxicity knowledge base with rich external toxic representations for humans (e.g., fine-grained visual features) that can be utilized to further guide the optimization of adversarial prompts. In addition, we present Contextual Hierarchical Morphing, which hierarchically extracts critical parts of the original prompt (e.g., scenes, subjects, and body parts), and then iteratively retrieves and fuses toxic features to inject harmful contexts. Extensive experiments on multiple open-sourced T2I models and black-box commercial APIs (e.g., DALLE-3) demonstrate the efficacy of CogMorph which significantly outperforms other baselines by large margins (+20.62% on average).
Authors: Longan Wang, Yuang Shi, Wei Tsang Ooi
Abstract: 3D Gaussian splats have emerged as a revolutionary, effective, learned representation for static 3D scenes. In this work, we explore using 2D Gaussian splats as a new primitive for representing videos. We propose GSVC, an approach to learning a set of 2D Gaussian splats that can effectively represent and compress video frames. GSVC incorporates the following techniques: (i) To exploit temporal redundancy among adjacent frames, which can speed up training and improve the compression efficiency, we predict the Gaussian splats of a frame based on its previous frame; (ii) To control the trade-offs between file size and quality, we remove Gaussian splats with low contribution to the video quality; (iii) To capture dynamics in videos, we randomly add Gaussian splats to fit content with large motion or newly-appeared objects; (iv) To handle significant changes in the scene, we detect key frames based on loss differences during the learning process. Experiment results show that GSVC achieves good rate-distortion trade-offs, comparable to state-of-the-art video codecs such as AV1 and VVC, and a rendering speed of 1500 fps for a 1920x1080 video.
Authors: Shixuan Song, Hao Chen, Shu Hu, Xin Wang, Jinrong Hu, Xi Wu
Abstract: Visual anomaly detection is a highly challenging task, often categorized as a one-class classification and segmentation problem. Recent studies have demonstrated that the student-teacher (S-T) framework effectively addresses this challenge. However, most S-T frameworks rely solely on pre-trained teacher networks to guide student networks in learning multi-scale similar features, overlooking the potential of the student networks to enhance learning through multi-scale feature fusion. In this study, we propose a novel model named PFADSeg, which integrates a pre-trained teacher network, a denoising student network with multi-scale feature fusion, and a guided anomaly segmentation network into a unified framework. By adopting a unique teacher-encoder and student-decoder denoising mode, the model improves the student network's ability to learn from teacher network features. Furthermore, an adaptive feature fusion mechanism is introduced to train a self-supervised segmentation network that synthesizes anomaly masks autonomously, significantly increasing detection performance. Evaluated on the MVTec AD dataset, PFADSeg achieves state-of-the-art results with an image-level AUC of 98.9%, a pixel-level mean precision of 76.4%, and an instance-level mean precision of 78.7%.
Authors: Zibo Zhao (refer to the report for detailed contributions), Zeqiang Lai (refer to the report for detailed contributions), Qingxiang Lin (refer to the report for detailed contributions), Yunfei Zhao (refer to the report for detailed contributions), Haolin Liu (refer to the report for detailed contributions), Shuhui Yang (refer to the report for detailed contributions), Yifei Feng (refer to the report for detailed contributions), Mingxin Yang (refer to the report for detailed contributions), Sheng Zhang (refer to the report for detailed contributions), Xianghui Yang (refer to the report for detailed contributions), Huiwen Shi (refer to the report for detailed contributions), Sicong Liu (refer to the report for detailed contributions), Junta Wu (refer to the report for detailed contributions), Yihang Lian (refer to the report for detailed contributions), Fan Yang (refer to the report for detailed contributions), Ruining Tang (refer to the report for detailed contributions), Zebin He (refer to the report for detailed contributions), Xinzhou Wang (refer to the report for detailed contributions), Jian Liu (refer to the report for detailed contributions), Xuhui Zuo (refer to the report for detailed contributions), Zhuo Chen (refer to the report for detailed contributions), Biwen Lei (refer to the report for detailed contributions), Haohan Weng (refer to the report for detailed contributions), Jing Xu (refer to the report for detailed contributions), Yiling Zhu (refer to the report for detailed contributions), Xinhai Liu (refer to the report for detailed contributions), Lixin Xu (refer to the report for detailed contributions), Changrong Hu (refer to the report for detailed contributions), Tianyu Huang (refer to the report for detailed contributions), Lifu Wang (refer to the report for detailed contributions), Jihong Zhang (refer to the report for detailed contributions), Meng Chen (refer to the report for detailed contributions), Liang Dong (refer to the report for detailed contributions), Yiwen Jia (refer to the report for detailed contributions), Yulin Cai (refer to the report for detailed contributions), Jiaao Yu (refer to the report for detailed contributions), Yixuan Tang (refer to the report for detailed contributions), Hao Zhang (refer to the report for detailed contributions), Zheng Ye (refer to the report for detailed contributions), Peng He (refer to the report for detailed contributions), Runzhou Wu (refer to the report for detailed contributions), Chao Zhang (refer to the report for detailed contributions), Yonghao Tan (refer to the report for detailed contributions), Jie Xiao (refer to the report for detailed contributions), Yangyu Tao (refer to the report for detailed contributions), Jianchen Zhu (refer to the report for detailed contributions), Jinbao Xue (refer to the report for detailed contributions), Kai Liu (refer to the report for detailed contributions), Chongqing Zhao (refer to the report for detailed contributions), Xinming Wu (refer to the report for detailed contributions), Zhichao Hu (refer to the report for detailed contributions), Lei Qin (refer to the report for detailed contributions), Jianbing Peng (refer to the report for detailed contributions), Zhan Li (refer to the report for detailed contributions), Minghui Chen (refer to the report for detailed contributions), Xipeng Zhang (refer to the report for detailed contributions), Lin Niu (refer to the report for detailed contributions), Paige Wang (refer to the report for detailed contributions), Yingkai Wang (refer to the report for detailed contributions), Haozhao Kuang (refer to the report for detailed contributions), Zhongyi Fan (refer to the report for detailed contributions), Xu Zheng (refer to the report for detailed contributions), Weihao Zhuang (refer to the report for detailed contributions), YingPing He (refer to the report for detailed contributions), Tian Liu (refer to the report for detailed contributions), Yong Yang (refer to the report for detailed contributions), Di Wang (refer to the report for detailed contributions), Yuhong Liu (refer to the report for detailed contributions), Jie Jiang (refer to the report for detailed contributions), Jingwei Huang (refer to the report for detailed contributions), Chunchao Guo (refer to the report for detailed contributions)
Abstract: We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio -- a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and etc. Hunyuan3D 2.0 is publicly released in order to fill the gaps in the open-source 3D community for large-scale foundation generative models. The code and pre-trained weights of our models are available at: https://github.com/Tencent/Hunyuan3D-2
Authors: Yihang Chen, Qianyi Wu, Weiyao Lin, Mehrtash Harandi, Jianfei Cai
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To achieve a compact size, we propose HAC++, which leverages the relationships between unorganized anchors and a structured hash grid, utilizing their mutual information for context modeling. Additionally, HAC++ captures intra-anchor contextual relationships to further enhance compression performance. To facilitate entropy coding, we utilize Gaussian distributions to precisely estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Moreover, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Overall, HAC++ achieves a remarkable size reduction of over 100X compared to vanilla 3DGS when averaged on all datasets, while simultaneously improving fidelity. It also delivers more than 20X size reduction compared to Scaffold-GS. Our code is available at https://github.com/YihangChen-ee/HAC-plus.
Authors: Sili Chen, Hengkai Guo, Shengnan Zhu, Feihu Zhang, Zilong Huang, Jiashi Feng, Bingyi Kang
Abstract: Depth Anything has achieved remarkable success in monocular depth estimation with strong generalization ability. However, it suffers from temporal inconsistency in videos, hindering its practical applications. Various methods have been proposed to alleviate this issue by leveraging video generation models or introducing priors from optical flow and camera poses. Nonetheless, these methods are only applicable to short videos (< 10 seconds) and require a trade-off between quality and computational efficiency. We propose Video Depth Anything for high-quality, consistent depth estimation in super-long videos (over several minutes) without sacrificing efficiency. We base our model on Depth Anything V2 and replace its head with an efficient spatial-temporal head. We design a straightforward yet effective temporal consistency loss by constraining the temporal depth gradient, eliminating the need for additional geometric priors. The model is trained on a joint dataset of video depth and unlabeled images, similar to Depth Anything V2. Moreover, a novel key-frame-based strategy is developed for long video inference. Experiments show that our model can be applied to arbitrarily long videos without compromising quality, consistency, or generalization ability. Comprehensive evaluations on multiple video benchmarks demonstrate that our approach sets a new state-of-the-art in zero-shot video depth estimation. We offer models of different scales to support a range of scenarios, with our smallest model capable of real-time performance at 30 FPS.
Authors: Yi Wang, Xinhao Li, Ziang Yan, Yinan He, Jiashuo Yu, Xiangyu Zeng, Chenting Wang, Changlian Ma, Haian Huang, Jianfei Gao, Min Dou, Kai Chen, Wenhai Wang, Yu Qiao, Yali Wang, Limin Wang
Abstract: This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of InternVideo2.5 with a focus on enhancing the original MLLMs' ability to perceive fine-grained details and capture long-form temporal structure in videos. Specifically, our approach incorporates dense vision task annotations into MLLMs using direct preference optimization and develops compact spatiotemporal representations through adaptive hierarchical token compression. Experimental results demonstrate this unique design of LRC greatly improves the results of video MLLM in mainstream video understanding benchmarks (short & long), enabling the MLLM to memorize significantly longer video inputs (at least 6x longer than the original), and master specialized vision capabilities like object tracking and segmentation. Our work highlights the importance of multimodal context richness (length and fineness) in empowering MLLM's innate abilites (focus and memory), providing new insights for future research on video MLLM. Code and models are available at https://github.com/OpenGVLab/InternVideo/tree/main/InternVideo2.5
URLs: https://github.com/OpenGVLab/InternVideo/tree/main/InternVideo2.5
Authors: Chao Feng, Ziyang Chen, Aleksander Holynski, Alexei A. Efros, Andrew Owens
Abstract: We show that the GPS tags contained in photo metadata provide a useful control signal for image generation. We train GPS-to-image models and use them for tasks that require a fine-grained understanding of how images vary within a city. In particular, we train a diffusion model to generate images conditioned on both GPS and text. The learned model generates images that capture the distinctive appearance of different neighborhoods, parks, and landmarks. We also extract 3D models from 2D GPS-to-image models through score distillation sampling, using GPS conditioning to constrain the appearance of the reconstruction from each viewpoint. Our evaluations suggest that our GPS-conditioned models successfully learn to generate images that vary based on location, and that GPS conditioning improves estimated 3D structure.
Authors: Qinghui Liu, Elies Fuster-Garcia, Ivar Thokle Hovden, Bradley J MacIntosh, Edvard Gr{\o}dem, Petter Brandal, Carles Lopez-Mateu, Donatas Sederevicius, Karoline Skogen, Till Schellhorn, Atle Bj{\o}rnerud, Kyrre Eeg Emblem
Abstract: Diffuse gliomas are malignant brain tumors that grow widespread through the brain. The complex interactions between neoplastic cells and normal tissue, as well as the treatment-induced changes often encountered, make glioma tumor growth modeling challenging. In this paper, we present a novel end-to-end network capable of future predictions of tumor masks and multi-parametric magnetic resonance images (MRI) of how the tumor will look at any future time points for different treatment plans. Our approach is based on cutting-edge diffusion probabilistic models and deep-segmentation neural networks. We included sequential multi-parametric MRI and treatment information as conditioning inputs to guide the generative diffusion process as well as a joint segmentation process. This allows for tumor growth estimates and realistic MRI generation at any given treatment and time point. We trained the model using real-world postoperative longitudinal MRI data with glioma tumor growth trajectories represented as tumor segmentation maps over time. The model demonstrates promising performance across various tasks, including generating high-quality multi-parametric MRI with tumor masks, performing time-series tumor segmentations, and providing uncertainty estimates. Combined with the treatment-aware generated MRI, the tumor growth predictions with uncertainty estimates can provide useful information for clinical decision-making.
Authors: Linjie Fu, Xia Li, Xiuding Cai, Yingkai Wang, Xueyao Wang, Yali Shen, Yu Yao
Abstract: Radiation therapy is crucial in cancer treatment. Experienced experts typically iteratively generate high-quality dose distribution maps, forming the basis for excellent radiation therapy plans. Therefore, automated prediction of dose distribution maps is significant in expediting the treatment process and providing a better starting point for developing radiation therapy plans. With the remarkable results of diffusion models in predicting high-frequency regions of dose distribution maps, dose prediction methods based on diffusion models have been extensively studied. However, existing methods mainly utilize CNNs or Transformers as denoising networks. CNNs lack the capture of global receptive fields, resulting in suboptimal prediction performance. Transformers excel in global modeling but face quadratic complexity with image size, resulting in significant computational overhead. To tackle these challenges, we introduce a novel diffusion model, MD-Dose, based on the Mamba architecture for predicting radiation therapy dose distribution in thoracic cancer patients. In the forward process, MD-Dose adds Gaussian noise to dose distribution maps to obtain pure noise images. In the backward process, MD-Dose utilizes a noise predictor based on the Mamba to predict the noise, ultimately outputting the dose distribution maps. Furthermore, We develop a Mamba encoder to extract structural information and integrate it into the noise predictor for localizing dose regions in the planning target volume (PTV) and organs at risk (OARs). Through extensive experiments on a dataset of 300 thoracic tumor patients, we showcase the superiority of MD-Dose in various metrics and time consumption.
Authors: Mohammad Shahab Sepehri, Zalan Fabian, Mahdi Soltanolkotabi
Abstract: The landscape of computational building blocks of efficient image restoration architectures is dominated by a combination of convolutional processing and various attention mechanisms. However, convolutional filters, while efficient, are inherently local and therefore struggle with modeling long-range dependencies in images. In contrast, attention excels at capturing global interactions between arbitrary image regions, but suffers from a quadratic cost in image dimension. In this work, we propose Serpent, an efficient architecture for high-resolution image restoration that combines recent advances in state space models (SSMs) with multi-scale signal processing in its core computational block. SSMs, originally introduced for sequence modeling, can maintain a global receptive field with a favorable linear scaling in input size. We propose a novel hierarchical architecture inspired by traditional signal processing principles, that converts the input image into a collection of sequences and processes them in a multi-scale fashion. Our experimental results demonstrate that Serpent can achieve reconstruction quality on par with state-of-the-art techniques, while requiring orders of magnitude less compute (up to $150$ fold reduction in FLOPS) and a factor of up to $5\times$ less GPU memory while maintaining a compact model size. The efficiency gains achieved by Serpent are especially notable at high image resolutions.
Authors: Chris Lin, Mingyu Lu, Chanwoo Kim, Su-In Lee
Abstract: As diffusion models are deployed in real-world settings, and their performance is driven by training data, appraising the contribution of data contributors is crucial to creating incentives for sharing quality data and to implementing policies for data compensation. Depending on the use case, model performance corresponds to various global properties of the distribution learned by a diffusion model (e.g., overall aesthetic quality). Hence, here we address the problem of attributing global properties of diffusion models to data contributors. The Shapley value provides a principled approach to valuation by uniquely satisfying game-theoretic axioms of fairness. However, estimating Shapley values for diffusion models is computationally impractical because it requires retraining on many training data subsets corresponding to different contributors and rerunning inference. We introduce a method to efficiently retrain and rerun inference for Shapley value estimation, by leveraging model pruning and fine-tuning. We evaluate the utility of our method with three use cases: (i) image quality for a DDPM trained on a CIFAR dataset, (ii) demographic diversity for an LDM trained on CelebA-HQ, and (iii) aesthetic quality for a Stable Diffusion model LoRA-finetuned on Post-Impressionist artworks. Our results empirically demonstrate that our framework can identify important data contributors across models' global properties, outperforming existing attribution methods for diffusion models.
Authors: Hasan Md Tusfiqur Alam, Devansh Srivastav, Md Abdul Kadir, Daniel Sonntag
Abstract: Deep learning has advanced medical image classification, but interpretability challenges hinder its clinical adoption. This study enhances interpretability in Chest X-ray (CXR) classification by using concept bottleneck models (CBMs) and a multi-agent Retrieval-Augmented Generation (RAG) system for report generation. By modeling relationships between visual features and clinical concepts, we create interpretable concept vectors that guide a multi-agent RAG system to generate radiology reports, enhancing clinical relevance, explainability, and transparency. Evaluation of the generated reports using an LLM-as-a-judge confirmed the interpretability and clinical utility of our model's outputs. On the COVID-QU dataset, our model achieved 81% classification accuracy and demonstrated robust report generation performance, with five key metrics ranging between 84% and 90%. This interpretable multi-agent framework bridges the gap between high-performance AI and the explainability required for reliable AI-driven CXR analysis in clinical settings. Our code is available at https://github.com/tifat58/IRR-with-CBM-RAG.git.
Authors: Shao-Hao Lu, Ren Wang, Ching-Chun Huang, Wei-Chen Chiu
Abstract: Recently, diffusion-based blind super-resolution (SR) methods have shown great ability to generate high-resolution images with abundant high-frequency detail, but the detail is often achieved at the expense of fidelity. Meanwhile, another line of research focusing on rectifying the reverse process of diffusion models (i.e., diffusion guidance), has demonstrated the power to generate high-fidelity results for non-blind SR. However, these methods rely on known degradation kernels, making them difficult to apply to blind SR. To address these issues, we present DADiff in this paper. DADiff incorporates degradation-aware models into the diffusion guidance framework, eliminating the need to know degradation kernels. Additionally, we propose two novel techniques -- input perturbation and guidance scalar -- to further improve our performance. Extensive experimental results show that our proposed method has superior performance over state-of-the-art methods on blind SR benchmarks.
Authors: Haichao Zhang, Haonan Yu, Le Zhao, Andrew Choi, Qinxun Bai, Break Yang, Wei Xu
Abstract: We present a low-cost legged mobile manipulation system that solves long-horizon real-world tasks, trained by reinforcement learning purely in simulation. This system is made possible by 1) a hierarchical design of a high-level policy for visual-mobile manipulation following instructions and a low-level policy for quadruped movement and limb control, 2) a progressive exploration and learning approach that leverages privileged task decomposition information to train the teacher policy for long-horizon tasks, which will guide an imitation-based student policy for efficient training of the high-level visuomotor policy, and 3) a suite of techniques for minimizing sim-to-real gaps. In contrast to previous approaches that use high-end equipment, our system demonstrates effective performance with more accessible hardware - specifically, a Unitree Go1 quadruped, a WidowX250S arm, and a single wrist-mounted RGB camera - despite the increased challenges of sim-to-real transfer. When fully trained in simulation, a single policy autonomously solves long-horizon tasks such as search, move, grasp, and drop-into, achieving nearly 80% success. This performance is comparable to that of expert human teleoperation on the same tasks but operates in a more efficient way, at 1.5 times the speed of human expert. The sim-to-real transfer is fluid across diverse indoor and outdoor scenes under varying lighting conditions. Finally, we discuss the key techniques that enable the entire pipeline, including efficient RL training and sim-to-real, to work effectively for legged mobile manipulation, and present their ablation results.
Authors: Yuecheng Liu, Dafeng Chi, Shiguang Wu, Zhanguang Zhang, Yaochen Hu, Lingfeng Zhang, Yingxue Zhang, Shuang Wu, Tongtong Cao, Guowei Huang, Helong Huang, Guangjian Tian, Weichao Qiu, Xingyue Quan, Jianye Hao, Yuzheng Zhuang
Abstract: Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks, largely due to their dependence on language-based outputs. While some approaches have introduced a point-based action space to mitigate this issue, they fall short in managing more intricate tasks within complex environments. This deficiency arises from their failure to fully exploit the inherent thinking and reasoning capabilities that are fundamental strengths of Vision-Language Models (VLMs). To address these limitations, we propose a novel approach named SpatialCoT, specifically designed to bolster the spatial reasoning capabilities of VLMs. Our approach comprises two stages: spatial coordinate bi-directional alignment, which aligns vision-language inputs with spatial coordinates, and chain-of-thought spatial grounding, which harnesses the reasoning capabilities of language models for advanced spatial reasoning. We evaluate SpatialCoT on challenging navigation and manipulation tasks, both in simulation and real-world settings. Experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches in both tasks.
Authors: Junshi Xia, Hongruixuan Chen, Clifford Broni-Bediako, Yimin Wei, Jian Song, Naoto Yokoya
Abstract: High-resolution land cover mapping plays a crucial role in addressing a wide range of global challenges, including urban planning, environmental monitoring, disaster response, and sustainable development. However, creating accurate, large-scale land cover datasets remains a significant challenge due to the inherent complexities of geospatial data, such as diverse terrain, varying sensor modalities, and atmospheric conditions. Synthetic Aperture Radar (SAR) imagery, with its ability to penetrate clouds and capture data in all-weather, day-and-night conditions, offers unique advantages for land cover mapping. Despite these strengths, the lack of benchmark datasets tailored for SAR imagery has limited the development of robust models specifically designed for this data modality. To bridge this gap and facilitate advancements in SAR-based geospatial analysis, we introduce OpenEarthMap-SAR, a benchmark SAR dataset, for global high-resolution land cover mapping. OpenEarthMap-SAR consists of 1.5 million segments of 5033 aerial and satellite images with the size of 1024$\times$1024 pixels, covering 35 regions from Japan, France, and the USA, with partially manually annotated and fully pseudo 8-class land cover labels at a ground sampling distance of 0.15--0.5 m. We evaluated the performance of state-of-the-art methods for semantic segmentation and present challenging problem settings suitable for further technical development. The dataset also serves the official dataset for IEEE GRSS Data Fusion Contest Track I. The dataset has been made publicly available at https://zenodo.org/records/14622048.