Authors: Miguel Lopez-Duran, Julian Fierrez, Aythami Morales, Ruben Tolosana, Oscar Delgado-Mohatar, Alvaro Ortigosa
Abstract: The automatic analysis of document layouts in digital-born PDF documents remains a challenging problem due to the heterogeneous arrangement of textual and nontextual elements and the imprecision of the textual metadata in the Portable Document Format. In this work, we benchmark Graph Neural Network (GNN) architectures for the task of fine-grained layout classification of text blocks from digital native documents. We introduce two graph construction structures: a k-closest-neighbor graph and a fully connected graph, and generate node features via pre-trained text and vision models, thus avoiding manual feature engineering. Three experimental frameworks are evaluated: single-modality (text or visual), concatenated multimodal, and dual-branch multimodal. We evaluated four foundational GNN models and compared them with the baseline. Our experiments are specifically conducted on a rich dataset of public affairs documents that includes more than 20 sources (e.g., regional and national-level official gazettes), 37K PDF documents, with 441K pages in total. Our results demonstrate that GraphSAGE operating on the k-closest-neighbor graph in a dual-branch configuration achieves the highest per-class and overall accuracy, outperforming the baseline in some sources. These findings confirm the importance of local layout relationships and multimodal fusion exploited through GNNs for the analysis of native digital document layouts.
Authors: Xin Zhang, Ziruo Zhang, Jiawei Du, Zuozhu Liu, Joey Tianyi Zhou
Abstract: Multimodal Dataset Distillation (MDD) seeks to condense large-scale image-text datasets into compact surrogates while retaining their effectiveness for cross-modal learning. Despite recent progress, existing MDD approaches often suffer from \textit{\textbf{Modality Collapse}}, characterized by over-concentrated intra-modal representations and enlarged distributional gap across modalities. In this paper, at the first time, we identify this issue as stemming from a fundamental conflict between the over-compression behavior inherent in dataset distillation and the cross-modal supervision imposed by contrastive objectives. To alleviate modality collapse, we introduce \textbf{RepBlend}, a novel MDD framework that weakens overdominant cross-modal supervision via representation blending, thereby significantly enhancing intra-modal diversity. Additionally, we observe that current MDD methods impose asymmetric supervision across modalities, resulting in biased optimization. To address this, we propose symmetric projection trajectory matching, which synchronizes the optimization dynamics using modality-specific projection heads, thereby promoting balanced supervision and enhancing cross-modal alignment. Experiments on Flickr-30K and MS-COCO show that RepBlend consistently outperforms prior state-of-the-art MDD methods, achieving significant gains in retrieval performance (e.g., +9.4 IR@10, +6.3 TR@10 under the 100-pair setting) and offering up to 6.7$\times$ distillation speedup.
Authors: Georgiana Manolache, Gerard Schouten, Joaquin Vanschoren
Abstract: We present CrypticBio, the largest publicly available multimodal dataset of visually confusing species, specifically curated to support the development of AI models in the context of biodiversity applications. Visually confusing or cryptic species are groups of two or more taxa that are nearly indistinguishable based on visual characteristics alone. While much existing work addresses taxonomic identification in a broad sense, datasets that directly address the morphological confusion of cryptic species are small, manually curated, and target only a single taxon. Thus, the challenge of identifying such subtle differences in a wide range of taxa remains unaddressed. Curated from real-world trends in species misidentification among community annotators of iNaturalist, CrypticBio contains 52K unique cryptic groups spanning 67K species, represented in 166 million images. Rich research-grade image annotations--including scientific, multicultural, and multilingual species terminology, hierarchical taxonomy, spatiotemporal context, and associated cryptic groups--address multimodal AI in biodiversity research. For easy dataset curation, we provide an open-source pipeline CrypticBio-Curate. The multimodal nature of the dataset beyond vision-language arises from the integration of geographical and temporal data as complementary cues to identifying cryptic species. To highlight the importance of the dataset, we benchmark a suite of state-of-the-art foundation models across CrypticBio subsets of common, unseen, endangered, and invasive species, and demonstrate the substantial impact of geographical context on vision-language zero-shot learning for cryptic species. By introducing CrypticBio, we aim to catalyze progress toward real-world-ready biodiversity AI models capable of handling the nuanced challenges of species ambiguity.
Authors: Xuan Shen, Chenxia Han, Yufa Zhou, Yanyue Xie, Yifan Gong, Quanyi Wang, Yiwei Wang, Yanzhi Wang, Pu Zhao, Jiuxiang Gu
Abstract: Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over 80% of total latency, and generating just 8 seconds of 720p video takes tens of minutes-posing serious challenges to practical application and scalability. To address this, we propose the DraftAttention, a training-free framework for the acceleration of video diffusion transformers with dynamic sparse attention on GPUs. We apply down-sampling to each feature map across frames in the compressed latent space, enabling a higher-level receptive field over the latent composed of hundreds of thousands of tokens. The low-resolution draft attention map, derived from draft query and key, exposes redundancy both spatially within each feature map and temporally across frames. We reorder the query, key, and value based on the draft attention map to guide the sparse attention computation in full resolution, and subsequently restore their original order after the attention computation. This reordering enables structured sparsity that aligns with hardware-optimized execution. Our theoretical analysis demonstrates that the low-resolution draft attention closely approximates the full attention, providing reliable guidance for constructing accurate sparse attention. Experimental results show that our method outperforms existing sparse attention approaches in video generation quality and achieves up to 1.75x end-to-end speedup on GPUs. Code: https://github.com/shawnricecake/draft-attention
Authors: Xuan Shen, Weize Ma, Yufa Zhou, Enhao Tang, Yanyue Xie, Zhengang Li, Yifan Gong, Quanyi Wang, Henghui Ding, Yiwei Wang, Yanzhi Wang, Pu Zhao, Jun Lin, Jiuxiang Gu
Abstract: Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially larger number of tokens to produce coherent temporal frames, resulting in significant overhead during the decoding phase. Our key observations are: (i) MLP modules in the decode phase dominate the inference latency, and (ii) there exists high temporal redundancy in MLP outputs of adjacent frames. In this paper, we propose the \textbf{FastCar} framework to accelerate the decode phase for the AR video generation by exploring the temporal redundancy. The Temporal Attention Score (TAS) is proposed to determine whether to apply the replay strategy (\textit{i.e.}, reusing cached MLP outputs from the previous frame to reduce redundant computations) with detailed theoretical analysis and justification. Also, we develop a hardware accelerator on FPGA with Dynamic Resource Scheduling (DRS) based on TAS to enable better resource utilization and faster inference. Experimental results demonstrate the effectiveness of our method, which outperforms traditional sparse attention approaches with more than 2.1x decoding speedup and higher energy efficiency on the edge. Furthermore, by combining FastCar and sparse attention, FastCar can boost the performance of sparse attention with alleviated drifting, demonstrating our unique advantages for high-resolution and long-duration video generation. Code: https://github.com/shawnricecake/fast-car
Authors: Tuan-Vinh La, Minh-Hieu Nguyen, Minh-Son Dao
Abstract: Fake news detection remains a challenging problem due to the complex interplay between textual misinformation, manipulated images, and external knowledge reasoning. While existing approaches have achieved notable results in verifying veracity and cross-modal consistency, two key challenges persist: (1) Existing methods often consider only the global image context while neglecting local object-level details, and (2) they fail to incorporate external knowledge and entity relationships for deeper semantic understanding. To address these challenges, we propose a novel multi-modal fake news detection framework that integrates visual, textual, and knowledge-based representations. Our approach leverages bottom-up attention to capture fine-grained object details, CLIP for global image semantics, and RoBERTa for context-aware text encoding. We further enhance knowledge utilization by retrieving and adaptively selecting relevant entities from a knowledge graph. The fused multi-modal features are processed through a Transformer-based classifier to predict news veracity. Experimental results demonstrate that our model outperforms recent approaches, showcasing the effectiveness of neighbor selection mechanism and multi-modal fusion for fake news detection. Our proposal introduces a new paradigm: knowledge-grounded multimodal reasoning. By integrating explicit entity-level selection and NLI-guided filtering, we shift fake news detection from feature fusion to semantically grounded verification. For reproducibility and further research, the source code is publicly at \href{https://github.com/latuanvinh1998/KGAlign}{github.com/latuanvinh1998/KGAlign}.
Authors: Guoxuan Mao, Ting Cao, Ziyang Li, Yuan Dong
Abstract: Semantic segmentation stands as a pivotal research focus in computer vision. In the context of industrial image inspection, conventional semantic segmentation models fail to maintain the segmentation consistency of fixed components across varying contextual environments due to a lack of perception of object contours. Given the real-time constraints and limited computing capability of industrial image detection machines, it is also necessary to create efficient models to reduce computational complexity. In this work, a Shape-Aware Efficient Network (SPENet) is proposed, which focuses on the shapes of objects to achieve excellent segmentation consistency by separately supervising the extraction of boundary and body information from images. In SPENet, a novel method is introduced for describing fuzzy boundaries to better adapt to real-world scenarios named Variable Boundary Domain (VBD). Additionally, a new metric, Consistency Mean Square Error(CMSE), is proposed to measure segmentation consistency for fixed components. Our approach attains the best segmentation accuracy and competitive speed on our dataset, showcasing significant advantages in CMSE among numerous state-of-the-art real-time segmentation networks, achieving a reduction of over 50% compared to the previously top-performing models.
Authors: Wei Hua, Chenlin Zhou, Jibin Wu, Yansong Chua, Yangyang Shu
Abstract: The combination of Spiking Neural Networks(SNNs) with Vision Transformer architectures has attracted significant attention due to the great potential for energy-efficient and high-performance computing paradigms. However, a substantial performance gap still exists between SNN-based and ANN-based transformer architectures. While existing methods propose spiking self-attention mechanisms that are successfully combined with SNNs, the overall architectures proposed by these methods suffer from a bottleneck in effectively extracting features from different image scales. In this paper, we address this issue and propose MSVIT, a novel spike-driven Transformer architecture, which firstly uses multi-scale spiking attention (MSSA) to enrich the capability of spiking attention blocks. We validate our approach across various main data sets. The experimental results show that MSVIT outperforms existing SNN-based models, positioning itself as a state-of-the-art solution among SNN-transformer architectures. The codes are available at https://github.com/Nanhu-AI-Lab/MSViT.
Authors: Xiao Lin, Zhining Liu, Ze Yang, Gaotang Li, Ruizhong Qiu, Shuke Wang, Hui Liu, Haotian Li, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong
Abstract: Warning: This paper contains examples of harmful language and images. Reader discretion is advised. Recently, vision-language models have demonstrated increasing influence in morally sensitive domains such as autonomous driving and medical analysis, owing to their powerful multimodal reasoning capabilities. As these models are deployed in high-stakes real-world applications, it is of paramount importance to ensure that their outputs align with human moral values and remain within moral boundaries. However, existing work on moral alignment either focuses solely on textual modalities or relies heavily on AI-generated images, leading to distributional biases and reduced realism. To overcome these limitations, we introduce MORALISE, a comprehensive benchmark for evaluating the moral alignment of vision-language models (VLMs) using diverse, expert-verified real-world data. We begin by proposing a comprehensive taxonomy of 13 moral topics grounded in Turiel's Domain Theory, spanning the personal, interpersonal, and societal moral domains encountered in everyday life. Built on this framework, we manually curate 2,481 high-quality image-text pairs, each annotated with two fine-grained labels: (1) topic annotation, identifying the violated moral topic(s), and (2) modality annotation, indicating whether the violation arises from the image or the text. For evaluation, we encompass two tasks, \textit{moral judgment} and \textit{moral norm attribution}, to assess models' awareness of moral violations and their reasoning ability on morally salient content. Extensive experiments on 19 popular open- and closed-source VLMs show that MORALISE poses a significant challenge, revealing persistent moral limitations in current state-of-the-art models. The full benchmark is publicly available at https://huggingface.co/datasets/Ze1025/MORALISE.
Authors: Ram Mohan Rao Kadiyala, Siddhant Gupta, Jebish Purbey, Srishti Yadav, Alejandro Salamanca, Desmond Elliott
Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases exist. This work investigates the extent to which prominent VLMs exhibit cultural biases by evaluating their performance on an image-based country identification task at a country level. Utilizing the geographically diverse Country211 dataset, we probe several large vision language models (VLMs) under various prompting strategies: open-ended questions, multiple-choice questions (MCQs) including challenging setups like multilingual and adversarial settings. Our analysis aims to uncover disparities in model accuracy across different countries and question formats, providing insights into how training data distribution and evaluation methodologies might influence cultural biases in VLMs. The findings highlight significant variations in performance, suggesting that while VLMs possess considerable visual understanding, they inherit biases from their pre-training data and scale that impact their ability to generalize uniformly across diverse global contexts.
Authors: Yunha Yeo, Daeho Um
Abstract: This paper attempts to explore human identity by utilizing neural networks in an indirect manner. For this exploration, we adopt diffusion models, state-of-the-art AI generative models trained to create human face images. By relating the generated human face to human identity, we establish a correspondence between the face image generation process of the diffusion model and the process of human identity formation. Through experiments with the diffusion model, we observe that changes in its external input result in significant changes in the generated face image. Based on the correspondence, we indirectly confirm the dependence of human identity on external factors in the process of human identity formation. Furthermore, we introduce \textit{Fluidity of Human Identity}, a video artwork that expresses the fluid nature of human identity affected by varying external factors. The video is available at https://www.behance.net/gallery/219958453/Fluidity-of-Human-Identity?.
URLs: https://www.behance.net/gallery/219958453/Fluidity-of-Human-Identity?.
Authors: Daniya Najiha A. Kareem, Jean Lahoud, Mustansar Fiaz, Amandeep Kumar, Hisham Cholakkal
Abstract: Many practical medical imaging scenarios include categories that are under-represented but still crucial. The relevance of image recognition models to real-world applications lies in their ability to generalize to these rare classes as well as unseen classes. Real-world generalization requires taking into account the various complexities that can be encountered in the real-world. First, training data is highly imbalanced, which may lead to model exhibiting bias toward the more frequently represented classes. Moreover, real-world data may contain unseen classes that need to be identified, and model performance is affected by the data scarcity. While medical image recognition has been extensively addressed in the literature, current methods do not take into account all the intricacies in the real-world scenarios. To this end, we propose an open-set learning method for highly imbalanced medical datasets using a semi-supervised approach. Understanding the adverse impact of long-tail distribution at the inherent model characteristics, we implement a regularization strategy at the feature level complemented by a classifier normalization technique. We conduct extensive experiments on the publicly available datasets, ISIC2018, ISIC2019, and TissueMNIST with various numbers of labelled samples. Our analysis shows that addressing the impact of long-tail data in classification significantly improves the overall performance of the network in terms of closed-set and open-set accuracies on all datasets. Our code and trained models will be made publicly available at https://github.com/Daniyanaj/OpenLTR.
Authors: Rama Alyoubi, Taif Alharbi, Albatul Alghamdi, Yara Alshehri, Elham Alghamdi
Abstract: This study presents a robust framework that leverages advanced imaging techniques and machine learning for feature extraction and classification of key human attributes-namely skin tone, hair color, iris color, and vein-based undertones. The system employs a multi-stage pipeline involving face detection, region segmentation, and dominant color extraction to isolate and analyze these features. Techniques such as X-means clustering, alongside perceptually uniform distance metrics like Delta E (CIEDE2000), are applied within both LAB and HSV color spaces to enhance the accuracy of color differentiation. For classification, the dominant tones of the skin, hair, and iris are extracted and matched to a custom tone scale, while vein analysis from wrist images enables undertone classification into "Warm" or "Cool" based on LAB differences. Each module uses targeted segmentation and color space transformations to ensure perceptual precision. The system achieves up to 80% accuracy in tone classification using the Delta E-HSV method with Gaussian blur, demonstrating reliable performance across varied lighting and image conditions. This work highlights the potential of AI-powered color analysis and feature extraction for delivering inclusive, precise, and nuanced classification, supporting applications in beauty technology, digital personalization, and visual analytics.
Authors: Hao Tang, Kevin Ellis, Suhas Lohit, Michael J. Jones, Moitreya Chatterjee
Abstract: The task of estimating the world model describing the dynamics of a real world process assumes immense importance for anticipating and preparing for future outcomes. For applications such as video surveillance, robotics applications, autonomous driving, etc. this objective entails synthesizing plausible visual futures, given a few frames of a video to set the visual context. Towards this end, we propose ProgGen, which undertakes the task of video frame prediction by representing the dynamics of the video using a set of neuro-symbolic, human-interpretable set of states (one per frame) by leveraging the inductive biases of Large (Vision) Language Models (LLM/VLM). In particular, ProgGen utilizes LLM/VLM to synthesize programs: (i) to estimate the states of the video, given the visual context (i.e. the frames); (ii) to predict the states corresponding to future time steps by estimating the transition dynamics; (iii) to render the predicted states as visual RGB-frames. Empirical evaluations reveal that our proposed method outperforms competing techniques at the task of video frame prediction in two challenging environments: (i) PhyWorld (ii) Cart Pole. Additionally, ProgGen permits counter-factual reasoning and interpretable video generation attesting to its effectiveness and generalizability for video generation tasks.
Authors: Jose Sosa, Danila Rukhovich, Anis Kacem, Djamila Aouada
Abstract: Multi-modal data in Earth Observation (EO) presents a huge opportunity for improving transfer learning capabilities when pre-training deep learning models. Unlike prior work that often overlooks multi-modal EO data, recent methods have started to include it, resulting in more effective pre-training strategies. However, existing approaches commonly face challenges in effectively transferring learning to downstream tasks where the structure of available data differs from that used during pre-training. This paper addresses this limitation by exploring a more flexible multi-modal, multi-task pre-training strategy for EO data. Specifically, we adopt a Multi-modal Multi-task Masked Autoencoder (MultiMAE) that we pre-train by reconstructing diverse input modalities, including spectral, elevation, and segmentation data. The pre-trained model demonstrates robust transfer learning capabilities, outperforming state-of-the-art methods on various EO datasets for classification and segmentation tasks. Our approach exhibits significant flexibility, handling diverse input configurations without requiring modality-specific pre-trained models. Code will be available at: https://github.com/josesosajs/multimae-meets-eo.
Authors: Alessandro dos Santos Ferreira, Ana Paula Marques Ramos, Jos\'e Marcato Junior, Wesley Nunes Gon\c{c}alves
Abstract: Urban forests play a key role in enhancing environmental quality and supporting biodiversity in cities. Mapping and monitoring these green spaces are crucial for urban planning and conservation, yet accurately detecting trees is challenging due to complex landscapes and the variability in image resolution caused by different satellite sensors or UAV flight altitudes. While deep learning architectures have shown promise in addressing these challenges, their effectiveness remains strongly dependent on the availability of large and manually labeled datasets, which are often expensive and difficult to obtain in sufficient quantity. In this work, we propose a novel pipeline that integrates domain adaptation with GANs and Diffusion models to enhance the quality of low-resolution aerial images. Our proposed pipeline enhances low-resolution imagery while preserving semantic content, enabling effective tree segmentation without requiring large volumes of manually annotated data. Leveraging models such as pix2pix, Real-ESRGAN, Latent Diffusion, and Stable Diffusion, we generate realistic and structurally consistent synthetic samples that expand the training dataset and unify scale across domains. This approach not only improves the robustness of segmentation models across different acquisition conditions but also provides a scalable and replicable solution for remote sensing scenarios with scarce annotation resources. Experimental results demonstrated an improvement of over 50% in IoU for low-resolution images, highlighting the effectiveness of our method compared to traditional pipelines.
Authors: Ke Guo, Haochen Liu, Xiaojun Wu, Jia Pan, Chen Lv
Abstract: End-to-end (E2E) autonomous driving systems offer a promising alternative to traditional modular pipelines by reducing information loss and error accumulation, with significant potential to enhance both mobility and safety. However, most existing E2E approaches directly generate plans based on dense bird's-eye view (BEV) grid features, leading to inefficiency and limited planning awareness. To address these limitations, we propose iterative Proposal-centric autonomous driving (iPad), a novel framework that places proposals - a set of candidate future plans - at the center of feature extraction and auxiliary tasks. Central to iPad is ProFormer, a BEV encoder that iteratively refines proposals and their associated features through proposal-anchored attention, effectively fusing multi-view image data. Additionally, we introduce two lightweight, proposal-centric auxiliary tasks - mapping and prediction - that improve planning quality with minimal computational overhead. Extensive experiments on the NAVSIM and CARLA Bench2Drive benchmarks demonstrate that iPad achieves state-of-the-art performance while being significantly more efficient than prior leading methods.
Authors: Ta Duc Huy, Duy Anh Huynh, Yutong Xie, Yuankai Qi, Qi Chen, Phi Le Nguyen, Sen Kim Tran, Son Lam Phung, Anton van den Hengel, Zhibin Liao, Minh-Son To, Johan W. Verjans, Vu Minh Hieu Phan
Abstract: Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features corresponding to textual descriptions, improving model transparency and trustworthiness for wider adoption of deep learning models in clinical practice. Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations. In this paper, we empirically demonstrate two key observations. First, current VLMs assign high norms to background tokens, diverting the model's attention from regions of disease. Second, the global tokens used for cross-modal learning are not representative of local disease tokens. This hampers identifying correlations between the text and disease tokens. To address this, we introduce simple, yet effective Disease-Aware Prompting (DAP) process, which uses the explainability map of a VLM to identify the appropriate image features. This simple strategy amplifies disease-relevant regions while suppressing background interference. Without any additional pixel-level annotations, DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.
Authors: Haiduo Huang, Jiangcheng Song, Yadong Zhang, Pengju Ren
Abstract: Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separate task-oriented and distillation gradients, they overlook the inherent conflict between target-class and non-target-class knowledge flows. Furthermore, low-confidence dark knowledge in non-target classes introduces noisy signals that hinder effective knowledge transfer. To address these limitations, we propose DeepKD, a novel training framework that integrates dual-level decoupling with adaptive denoising. First, through theoretical analysis of gradient signal-to-noise ratio (GSNR) characteristics in task-oriented and non-task-oriented knowledge distillation, we design independent momentum updaters for each component to prevent mutual interference. We observe that the optimal momentum coefficients for task-oriented gradient (TOG), target-class gradient (TCG), and non-target-class gradient (NCG) should be positively related to their GSNR. Second, we introduce a dynamic top-k mask (DTM) mechanism that gradually increases K from a small initial value to incorporate more non-target classes as training progresses, following curriculum learning principles. The DTM jointly filters low-confidence logits from both teacher and student models, effectively purifying dark knowledge during early training. Extensive experiments on CIFAR-100, ImageNet, and MS-COCO demonstrate DeepKD's effectiveness. Our code is available at https://github.com/haiduo/DeepKD.
Authors: Seongmin Hwang, Daeyoung Han, Moongu Jeon
Abstract: Multispectral object detection aims to leverage complementary information from visible (RGB) and infrared (IR) modalities to enable robust performance under diverse environmental conditions. In this letter, we propose IC-Fusion, a multispectral object detector that effectively fuses visible and infrared features through a lightweight and modalityaware design. Motivated by wavelet analysis and empirical observations, we find that IR images contain structurally rich high-frequency information critical for object localization, while RGB images provide complementary semantic context. To exploit this, we adopt a compact RGB backbone and design a novel fusion module comprising a Multi-Scale Feature Distillation (MSFD) block to enhance RGB features and a three-stage fusion block with Cross-Modal Channel Shuffle Gate (CCSG) and Cross-Modal Large Kernel Gate (CLKG) to facilitate effective cross-modal interaction. Experiments on the FLIR and LLVIP benchmarks demonstrate the effectiveness and efficiency of our IR-centric fusion strategy. Our code is available at https://github.com/smin-hwang/IC-Fusion.
Authors: Badhan Mazumder, Lei Wu, Vince D. Calhoun, Dong Hye Ye
Abstract: Gaining insights into the structural and functional mechanisms of the brain has been a longstanding focus in neuroscience research, particularly in the context of understanding and treating neuropsychiatric disorders such as Schizophrenia (SZ). Nevertheless, most of the traditional multimodal deep learning approaches fail to fully leverage the complementary characteristics of structural and functional connectomics data to enhance diagnostic performance. To address this issue, we proposed ConneX, a multimodal fusion method that integrates cross-attention mechanism and multilayer perceptron (MLP)-Mixer for refined feature fusion. Modality-specific backbone graph neural networks (GNNs) were firstly employed to obtain feature representation for each modality. A unified cross-modal attention network was then introduced to fuse these embeddings by capturing intra- and inter-modal interactions, while MLP-Mixer layers refined global and local features, leveraging higher-order dependencies for end-to-end classification with a multi-head joint loss. Extensive evaluations demonstrated improved performance on two distinct clinical datasets, highlighting the robustness of our proposed framework.
Authors: Xinran Wang, Songyu Xu, Xiangxuan Shan, Yuxuan Zhang, Muxi Diao, Xueyan Duan, Yanhua Huang, Kongming Liang, Zhanyu Ma
Abstract: Cinematography is a cornerstone of film production and appreciation, shaping mood, emotion, and narrative through visual elements such as camera movement, shot composition, and lighting. Despite recent progress in multimodal large language models (MLLMs) and video generation models, the capacity of current models to grasp and reproduce cinematographic techniques remains largely uncharted, hindered by the scarcity of expert-annotated data. To bridge this gap, we present CineTechBench, a pioneering benchmark founded on precise, manual annotation by seasoned cinematography experts across key cinematography dimensions. Our benchmark covers seven essential aspects-shot scale, shot angle, composition, camera movement, lighting, color, and focal length-and includes over 600 annotated movie images and 120 movie clips with clear cinematographic techniques. For the understanding task, we design question answer pairs and annotated descriptions to assess MLLMs' ability to interpret and explain cinematographic techniques. For the generation task, we assess advanced video generation models on their capacity to reconstruct cinema-quality camera movements given conditions such as textual prompts or keyframes. We conduct a large-scale evaluation on 15+ MLLMs and 5+ video generation models. Our results offer insights into the limitations of current models and future directions for cinematography understanding and generation in automatically film production and appreciation. The code and benchmark can be accessed at https://github.com/PRIS-CV/CineTechBench.
Authors: Quanwei Liu, Tao Huang, Yanni Dong, Jiaqi Yang, Wei Xiang
Abstract: Remote sensing images (RSIs) capture both natural and human-induced changes on the Earth's surface, serving as essential data for environmental monitoring, urban planning, and resource management. Semantic segmentation (SS) of RSIs enables the fine-grained interpretation of surface features, making it a critical task in remote sensing analysis. With the increasing diversity and volume of RSIs collected by sensors on various platforms, traditional processing methods struggle to maintain efficiency and accuracy. In response, deep learning (DL) has emerged as a transformative approach, enabling substantial advances in remote sensing image semantic segmentation (RSISS) by automating feature extraction and improving segmentation accuracy across diverse modalities. This paper revisits the evolution of DL-based RSISS by categorizing existing approaches into four stages: the early pixel-based methods, the prevailing patch-based and tile-based techniques, and the emerging image-based strategies enabled by foundation models. We analyze these developments from the perspective of feature extraction and learning strategies, revealing the field's progression from pixel-level to tile-level and from unimodal to multimodal segmentation. Furthermore, we conduct a comprehensive evaluation of nearly 40 advanced techniques on a unified dataset to quantitatively characterize their performance and applicability. This review offers a holistic view of DL-based SS for RS, highlighting key advancements, comparative insights, and open challenges to guide future research.
Authors: Yunsheng Ma, Burhaneddin Yaman, Xin Ye, Mahmut Yurt, Jingru Luo, Abhirup Mallik, Ziran Wang, Liu Ren
Abstract: Recent advances have explored integrating large language models (LLMs) into end-to-end autonomous driving systems to enhance generalization and interpretability. However, most existing approaches are limited to either driving performance or vision-language reasoning, making it difficult to achieve both simultaneously. In this paper, we propose ALN-P3, a unified co-distillation framework that introduces cross-modal alignment between "fast" vision-based autonomous driving systems and "slow" language-driven reasoning modules. ALN-P3 incorporates three novel alignment mechanisms: Perception Alignment (P1A), Prediction Alignment (P2A), and Planning Alignment (P3A), which explicitly align visual tokens with corresponding linguistic outputs across the full perception, prediction, and planning stack. All alignment modules are applied only during training and incur no additional costs during inference. Extensive experiments on four challenging benchmarks-nuScenes, Nu-X, TOD3Cap, and nuScenes QA-demonstrate that ALN-P3 significantly improves both driving decisions and language reasoning, achieving state-of-the-art results.
Authors: Jaeyeon Lee, Dong-Wan Choi
Abstract: Although Vision Transformers (ViTs) have become the standard architecture in computer vision, their massive sizes lead to significant computational overhead. Token compression techniques have attracted considerable attention to address this issue, but they often suffer from severe information loss, requiring extensive additional training to achieve practical performance. In this paper, we propose Adaptive Token Merging (ATM), a novel method that ensures lossless token merging, eliminating the need for fine-tuning while maintaining competitive performance. ATM adaptively reduces tokens across layers and batches by carefully adjusting layer-specific similarity thresholds, thereby preventing the undesirable merging of less similar tokens with respect to each layer. Furthermore, ATM introduces a novel token matching technique that considers not only similarity but also merging sizes, particularly for the final layers, to minimize the information loss incurred from each merging operation. We empirically validate our method across a wide range of pretrained models, demonstrating that ATM not only outperforms all existing training-free methods but also surpasses most training-intensive approaches, even without additional training. Remarkably, training-free ATM achieves over a 30% reduction in FLOPs for the DeiT-T and DeiT-S models without any drop in their original accuracy.
Authors: Xinran Wang, Muxi Diao, Yuanzhi Liu, Chunyu Wang, Kongming Liang, Zhanyu Ma, Jun Guo
Abstract: Training text-to-image (T2I) models with detailed captions can significantly improve their generation quality. Existing methods often rely on simplistic metrics like caption length to represent the detailness of the caption in the T2I training set. In this paper, we propose a new metric to estimate caption detailness based on two aspects: image coverage rate (ICR), which evaluates whether the caption covers all regions/objects in the image, and average object detailness (AOD), which quantifies the detailness of each object's description. Through experiments on the COCO dataset using ShareGPT4V captions, we demonstrate that T2I models trained on high-ICR and -AOD captions achieve superior performance on DPG and other benchmarks. Notably, our metric enables more effective data selection-training on only 20% of full data surpasses both full-dataset training and length-based selection method, improving alignment and reconstruction ability. These findings highlight the critical role of detail-aware metrics over length-based heuristics in caption selection for T2I tasks.
Authors: Zhipei Xu, Xuanyu Zhang, Xing Zhou, Jian Zhang
Abstract: The rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, particularly in video generation, has led to unprecedented creative capabilities but also increased threats to information integrity, identity security, and public trust. Existing detection methods, while effective in general scenarios, lack robust solutions for human-centric videos, which pose greater risks due to their realism and potential for legal and ethical misuse. Moreover, current detection approaches often suffer from poor generalization, limited scalability, and reliance on labor-intensive supervised fine-tuning. To address these challenges, we propose AvatarShield, the first interpretable MLLM-based framework for detecting human-centric fake videos, enhanced via Group Relative Policy Optimization (GRPO). Through our carefully designed accuracy detection reward and temporal compensation reward, it effectively avoids the use of high-cost text annotation data, enabling precise temporal modeling and forgery detection. Meanwhile, we design a dual-encoder architecture, combining high-level semantic reasoning and low-level artifact amplification to guide MLLMs in effective forgery detection. We further collect FakeHumanVid, a large-scale human-centric video benchmark that includes synthesis methods guided by pose, audio, and text inputs, enabling rigorous evaluation of detection methods in real-world scenes. Extensive experiments show that AvatarShield significantly outperforms existing approaches in both in-domain and cross-domain detection, setting a new standard for human-centric video forensics.
Authors: Qian Zhou, Xianda Guo, Jilong Wang, Chuanfu Shen, Zhongyuan Wang, Hua Zou, Qin Zou, Chao Liang, Chen Long, Gang Wu
Abstract: Generalized gait recognition, which aims to achieve robust performance across diverse domains, remains a challenging problem due to severe domain shifts in viewpoints, appearances, and environments. While mixed-dataset training is widely used to enhance generalization, it introduces new obstacles including inter-dataset optimization conflicts and redundant or noisy samples, both of which hinder effective representation learning. To address these challenges, we propose a unified framework that systematically improves cross-domain gait recognition. First, we design a disentangled triplet loss that isolates supervision signals across datasets, mitigating gradient conflicts during optimization. Second, we introduce a targeted dataset distillation strategy that filters out the least informative 20\% of training samples based on feature redundancy and prediction uncertainty, enhancing data efficiency. Extensive experiments on CASIA-B, OU-MVLP, Gait3D, and GREW demonstrate that our method significantly improves cross-dataset recognition for both GaitBase and DeepGaitV2 backbones, without sacrificing source-domain accuracy. Code will be released at https://github.com/li1er3/Generalized_Gait.
Authors: Yangting Shi, Renjie He, Le Hui, Xiang Li, Jian Yang, Ming-Ming Cheng, Yimian Dai
Abstract: Omni-domain infrared small target detection (IRSTD) poses formidable challenges, as a single model must seamlessly adapt to diverse imaging systems, varying resolutions, and multiple spectral bands simultaneously. Current approaches predominantly rely on visual-only modeling paradigms that not only struggle with complex background interference and inherently scarce target features, but also exhibit limited generalization capabilities across complex omni-scene environments where significant domain shifts and appearance variations occur. In this work, we reveal a critical oversight in existing paradigms: the neglect of readily available auxiliary metadata describing imaging parameters and acquisition conditions, such as spectral bands, sensor platforms, resolution, and observation perspectives. To address this limitation, we propose the Auxiliary Metadata Driven Infrared Small Target Detector (AuxDet), a novel multi-modal framework that fundamentally reimagines the IRSTD paradigm by incorporating textual metadata for scene-aware optimization. Through a high-dimensional fusion module based on multi-layer perceptrons (MLPs), AuxDet dynamically integrates metadata semantics with visual features, guiding adaptive representation learning for each individual sample. Additionally, we design a lightweight prior-initialized enhancement module using 1D convolutional blocks to further refine fused features and recover fine-grained target cues. Extensive experiments on the challenging WideIRSTD-Full benchmark demonstrate that AuxDet consistently outperforms state-of-the-art methods, validating the critical role of auxiliary information in improving robustness and accuracy in omni-domain IRSTD tasks. Code is available at https://github.com/GrokCV/AuxDet.
Authors: Yifan Liu, Keyu Fan, Weihao Yu, Chenxin Li, Hao Lu, Yixuan Yuan
Abstract: Recent advances in generalizable 3D Gaussian Splatting have demonstrated promising results in real-time high-fidelity rendering without per-scene optimization, yet existing approaches still struggle to handle unfamiliar visual content during inference on novel scenes due to limited generalizability. To address this challenge, we introduce MonoSplat, a novel framework that leverages rich visual priors from pre-trained monocular depth foundation models for robust Gaussian reconstruction. Our approach consists of two key components: a Mono-Multi Feature Adapter that transforms monocular features into multi-view representations, coupled with an Integrated Gaussian Prediction module that effectively fuses both feature types for precise Gaussian generation. Through the Adapter's lightweight attention mechanism, features are seamlessly aligned and aggregated across views while preserving valuable monocular priors, enabling the Prediction module to generate Gaussian primitives with accurate geometry and appearance. Through extensive experiments on diverse real-world datasets, we convincingly demonstrate that MonoSplat achieves superior reconstruction quality and generalization capability compared to existing methods while maintaining computational efficiency with minimal trainable parameters. Codes are available at https://github.com/CUHK-AIM-Group/MonoSplat.
Authors: Hana Satou, Alan Mitkiy, F Monkey
Abstract: Transfer learning under domain shift remains a fundamental challenge due to the divergence between source and target data manifolds. In this paper, we propose MAADA (Manifold-Aware Adversarial Data Augmentation), a novel framework that decomposes adversarial perturbations into on-manifold and off-manifold components to simultaneously capture semantic variation and model brittleness. We theoretically demonstrate that enforcing on-manifold consistency reduces hypothesis complexity and improves generalization, while off-manifold regularization smooths decision boundaries in low-density regions. Moreover, we introduce a geometry-aware alignment loss that minimizes geodesic discrepancy between source and target manifolds. Experiments on DomainNet, VisDA, and Office-Home show that MAADA consistently outperforms existing adversarial and adaptation methods in both unsupervised and few-shot settings, demonstrating superior structural robustness and cross-domain generalization.
Authors: Fatemeh Ziaeetabar, Florentin W\"org\"otter
Abstract: Foundation models have ushered in a new era for multimodal video understanding by enabling the extraction of rich spatiotemporal and semantic representations. In this work, we introduce a novel graph-based framework that integrates a vision-language foundation, leveraging VideoMAE for dynamic visual encoding and BERT for contextual textual embedding, to address the challenge of recognizing fine-grained bimanual manipulation actions. Departing from conventional static graph architectures, our approach constructs an adaptive multimodal graph where nodes represent frames, objects, and textual annotations, and edges encode spatial, temporal, and semantic relationships. These graph structures evolve dynamically based on learned interactions, allowing for flexible and context-aware reasoning. A task-specific attention mechanism within a Graph Attention Network further enhances this reasoning by modulating edge importance based on action semantics. Through extensive evaluations on diverse benchmark datasets, we demonstrate that our method consistently outperforms state-of-the-art baselines, underscoring the strength of combining foundation models with dynamic graph-based reasoning for robust and generalizable action recognition.
Authors: Hana Satou, F Monkey
Abstract: Domain adaptation remains a challenge when there is significant manifold discrepancy between source and target domains. Although recent methods leverage manifold-aware adversarial perturbations to perform data augmentation, they often neglect precise manifold alignment and systematic exploration of structured perturbations. To address this, we propose GAMA (Geometry-Aware Manifold Alignment), a structured framework that achieves explicit manifold alignment via adversarial perturbation guided by geometric information. GAMA systematically employs tangent space exploration and manifold-constrained adversarial optimization, simultaneously enhancing semantic consistency, robustness to off-manifold deviations, and cross-domain alignment. Theoretical analysis shows that GAMA tightens the generalization bound via structured regularization and explicit alignment. Empirical results on DomainNet, VisDA, and Office-Home demonstrate that GAMA consistently outperforms existing adversarial and adaptation methods in both unsupervised and few-shot settings, exhibiting superior robustness, generalization, and manifold alignment capability.
Authors: Pinxin Liu, Haiyang Liu, Luchuan Song, Chenliang Xu
Abstract: When humans speak, gestures help convey communicative intentions, such as adding emphasis or describing concepts. However, current co-speech gesture generation methods rely solely on superficial linguistic cues (\textit{e.g.} speech audio or text transcripts), neglecting to understand and leverage the communicative intention that underpins human gestures. This results in outputs that are rhythmically synchronized with speech but are semantically shallow. To address this gap, we introduce \textbf{Intentional-Gesture}, a novel framework that casts gesture generation as an intention-reasoning task grounded in high-level communicative functions. % First, we curate the \textbf{InG} dataset by augmenting BEAT-2 with gesture-intention annotations (\textit{i.e.}, text sentences summarizing intentions), which are automatically annotated using large vision-language models. Next, we introduce the \textbf{Intentional Gesture Motion Tokenizer} to leverage these intention annotations. It injects high-level communicative functions (\textit{e.g.}, intentions) into tokenized motion representations to enable intention-aware gesture synthesis that are both temporally aligned and semantically meaningful, achieving new state-of-the-art performance on the BEAT-2 benchmark. Our framework offers a modular foundation for expressive gesture generation in digital humans and embodied AI. Project Page: https://andypinxinliu.github.io/Intentional-Gesture
Authors: Hyogun Lee, Haksub Kim, Ig-Jae Kim, Yonghun Choi
Abstract: Video Anomaly Detection (VAD) automatically identifies anomalous events from video, mitigating the need for human operators in large-scale surveillance deployments. However, three fundamental obstacles hinder real-world adoption: domain dependency and real-time constraints -- requiring near-instantaneous processing of incoming video. To this end, we propose Flashback, a zero-shot and real-time video anomaly detection paradigm. Inspired by the human cognitive mechanism of instantly judging anomalies and reasoning in current scenes based on past experience, Flashback operates in two stages: Recall and Respond. In the offline recall stage, an off-the-shelf LLM builds a pseudo-scene memory of both normal and anomalous captions without any reliance on real anomaly data. In the online respond stage, incoming video segments are embedded and matched against this memory via similarity search. By eliminating all LLM calls at inference time, Flashback delivers real-time VAD even on a consumer-grade GPU. On two large datasets from real-world surveillance scenarios, UCF-Crime and XD-Violence, we achieve 87.3 AUC (+7.0 pp) and 75.1 AP (+13.1 pp), respectively, outperforming prior zero-shot VAD methods by large margins.
Authors: Wenjie Liu, Zhongliang Liu, Junwei Shu, Changbo Wang, Yang Li
Abstract: Transferring 2D textures to 3D modalities is of great significance for improving the efficiency of multimedia content creation. Existing approaches have rarely focused on transferring image textures onto 3D representations. 3D style transfer methods are capable of transferring abstract artistic styles to 3D scenes. However, these methods often overlook the geometric information of the scene, which makes it challenging to achieve high-quality 3D texture transfer results. In this paper, we present GT^2-GS, a geometry-aware texture transfer framework for gaussian splitting. From the perspective of matching texture features with geometric information in rendered views, we identify the issue of insufficient texture features and propose a geometry-aware texture augmentation module to expand the texture feature set. Moreover, a geometry-consistent texture loss is proposed to optimize texture features into the scene representation. This loss function incorporates both camera pose and 3D geometric information of the scene, enabling controllable texture-oriented appearance editing. Finally, a geometry preservation strategy is introduced. By alternating between the texture transfer and geometry correction stages over multiple iterations, this strategy achieves a balance between learning texture features and preserving geometric integrity. Extensive experiments demonstrate the effectiveness and controllability of our method. Through geometric awareness, our approach achieves texture transfer results that better align with human visual perception. Our homepage is available at https://vpx-ecnu.github.io/GT2-GS-website.
Authors: Haotian Qin, Dongliang Chang, Yueying Gao, Bingyao Yu, Lei Chen, Zhanyu Ma
Abstract: Although existing CLIP-based methods for detecting AI-generated images have achieved promising results, they are still limited by severe feature redundancy, which hinders their generalization ability. To address this issue, incorporating an information bottleneck network into the task presents a straightforward solution. However, relying solely on image-corresponding prompts results in suboptimal performance due to the inherent diversity of prompts. In this paper, we propose a multimodal conditional bottleneck network to reduce feature redundancy while enhancing the discriminative power of features extracted by CLIP, thereby improving the model's generalization ability. We begin with a semantic analysis experiment, where we observe that arbitrary text features exhibit lower cosine similarity with real image features than with fake image features in the CLIP feature space, a phenomenon we refer to as "bias". Therefore, we introduce InfoFD, a text-guided AI-generated image detection framework. InfoFD consists of two key components: the Text-Guided Conditional Information Bottleneck (TGCIB) and Dynamic Text Orthogonalization (DTO). TGCIB improves the generalizability of learned representations by conditioning on both text and class modalities. DTO dynamically updates weighted text features, preserving semantic information while leveraging the global "bias". Our model achieves exceptional generalization performance on the GenImage dataset and latest generative models. Our code is available at https://github.com/Ant0ny44/InfoFD.
Authors: Yisi Luo, Xile Zhao, Deyu Meng
Abstract: Recently, continuous representation methods emerge as novel paradigms that characterize the intrinsic structures of real-world data through function representations that map positional coordinates to their corresponding values in the continuous space. As compared with the traditional discrete framework, the continuous framework demonstrates inherent superiority for data representation and reconstruction (e.g., image restoration, novel view synthesis, and waveform inversion) by offering inherent advantages including resolution flexibility, cross-modal adaptability, inherent smoothness, and parameter efficiency. In this review, we systematically examine recent advancements in continuous representation frameworks, focusing on three aspects: (i) Continuous representation method designs such as basis function representation, statistical modeling, tensor function decomposition, and implicit neural representation; (ii) Theoretical foundations of continuous representations such as approximation error analysis, convergence property, and implicit regularization; (iii) Real-world applications of continuous representations derived from computer vision, graphics, bioinformatics, and remote sensing. Furthermore, we outline future directions and perspectives to inspire exploration and deepen insights to facilitate continuous representation methods, theories, and applications. All referenced works are summarized in our open-source repository: https://github.com/YisiLuo/Continuous-Representation-Zoo.
URLs: https://github.com/YisiLuo/Continuous-Representation-Zoo.
Authors: Ting Huang, Zeyu Zhang, Ruicheng Zhang, Yang Zhao
Abstract: 3D scene understanding plays a fundamental role in vision applications such as robotics, autonomous driving, and augmented reality. However, advancing learning-based 3D scene understanding remains challenging due to two key limitations: (1) the large scale and complexity of 3D scenes lead to higher computational costs and slower training compared to 2D counterparts; and (2) high-quality annotated 3D datasets are significantly scarcer than those available for 2D vision. These challenges underscore the need for more efficient learning paradigms. In this work, we propose DC-Scene, a data-centric framework tailored for 3D scene understanding, which emphasizes enhancing data quality and training efficiency. Specifically, we introduce a CLIP-driven dual-indicator quality (DIQ) filter, combining vision-language alignment scores with caption-loss perplexity, along with a curriculum scheduler that progressively expands the training pool from the top 25% to 75% of scene-caption pairs. This strategy filters out noisy samples and significantly reduces dependence on large-scale labeled 3D data. Extensive experiments on ScanRefer and Nr3D demonstrate that DC-Scene achieves state-of-the-art performance (86.1 CIDEr with the top-75% subset vs. 85.4 with the full dataset) while reducing training cost by approximately two-thirds, confirming that a compact set of high-quality samples can outperform exhaustive training. Code will be available at https://github.com/AIGeeksGroup/DC-Scene.
Authors: Yuxuan Du, Zhendong Wang, Yuhao Luo, Caiyong Piao, Zhiyuan Yan, Hao Li, Li Yuan
Abstract: The rapid emergence of multimodal deepfakes (visual and auditory content are manipulated in concert) undermines the reliability of existing detectors that rely solely on modality-specific artifacts or cross-modal inconsistencies. In this work, we first demonstrate that modality-specific forensic traces (e.g., face-swap artifacts or spectral distortions) and modality-shared semantic misalignments (e.g., lip-speech asynchrony) offer complementary evidence, and that neglecting either aspect limits detection performance. Existing approaches either naively fuse modality-specific features without reconciling their conflicting characteristics or focus predominantly on semantic misalignment at the expense of modality-specific fine-grained artifact cues. To address these shortcomings, we propose a general multimodal framework for video deepfake detection via Cross-Modal Alignment and Distillation (CAD). CAD comprises two core components: 1) Cross-modal alignment that identifies inconsistencies in high-level semantic synchronization (e.g., lip-speech mismatches); 2) Cross-modal distillation that mitigates feature conflicts during fusion while preserving modality-specific forensic traces (e.g., spectral distortions in synthetic audio). Extensive experiments on both multimodal and unimodal (e.g., image-only/video-only)deepfake benchmarks demonstrate that CAD significantly outperforms previous methods, validating the necessity of harmonious integration of multimodal complementary information.
Authors: Kim Yun, Hana Satou, F Monkey
Abstract: Despite progress in geometry-aware domain adaptation, current methods such as GAMA still suffer from two unresolved issues: (1) insufficient disentanglement of task-relevant and task-irrelevant manifold dimensions, and (2) rigid perturbation schemes that ignore per-class alignment asymmetries. To address this, we propose GAMA++, a novel framework that introduces (i) latent space disentanglement to isolate label-consistent manifold directions from nuisance factors, and (ii) an adaptive contrastive perturbation strategy that tailors both on- and off-manifold exploration to class-specific manifold curvature and alignment discrepancy. We further propose a cross-domain contrastive consistency loss that encourages local semantic clusters to align while preserving intra-domain diversity. Our method achieves state-of-the-art results on DomainNet, Office-Home, and VisDA benchmarks under both standard and few-shot settings, with notable improvements in class-level alignment fidelity and boundary robustness. GAMA++ sets a new standard for semantic geometry alignment in transfer learning.
Authors: Andre Dourson, Kylie Taylor, Xiaoli Qiao, Michael Fitzke
Abstract: Self-supervised learning has emerged as a powerful paradigm for training deep neural networks, particularly in medical imaging where labeled data is scarce. While current approaches typically rely on synthetic augmentations of single images, we propose VET-DINO, a framework that leverages a unique characteristic of medical imaging: the availability of multiple standardized views from the same study. Using a series of clinical veterinary radiographs from the same patient study, we enable models to learn view-invariant anatomical structures and develop an implied 3D understanding from 2D projections. We demonstrate our approach on a dataset of 5 million veterinary radiographs from 668,000 canine studies. Through extensive experimentation, including view synthesis and downstream task performance, we show that learning from real multi-view pairs leads to superior anatomical understanding compared to purely synthetic augmentations. VET-DINO achieves state-of-the-art performance on various veterinary imaging tasks. Our work establishes a new paradigm for self-supervised learning in medical imaging that leverages domain-specific properties rather than merely adapting natural image techniques.
Authors: Tatyana Shmykova, Leila Khaertdinova, Ilya Pershin
Abstract: Accurate segmentation of anatomical structures in volumetric medical images is crucial for clinical applications, including disease monitoring and cancer treatment planning. Contemporary interactive segmentation models, such as Segment Anything Model 2 (SAM-2) and its medical variant (MedSAM-2), rely on manually provided prompts like bounding boxes and mouse clicks. In this study, we introduce eye gaze as a novel informational modality for interactive segmentation, marking the application of eye-tracking for 3D medical image segmentation. We evaluate the performance of using gaze-based prompts with SAM-2 and MedSAM-2 using both synthetic and real gaze data. Compared to bounding boxes, gaze-based prompts offer a time-efficient interaction approach with slightly lower segmentation quality. Our findings highlight the potential of using gaze as a complementary input modality for interactive 3D medical image segmentation.
Authors: Om Khangaonkar, Hamed Pirsiavash
Abstract: By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose perceptual organization? We finetune Stable Diffusion and MAE (encoder+decoder) for category-agnostic instance segmentation using our instance coloring loss exclusively on a narrow set of object types (indoor furnishings and cars). Surprisingly, our models exhibit strong zero-shot generalization, accurately segmenting objects of types and styles unseen in finetuning (and in many cases, MAE's ImageNet-1K pretraining too). Our best-performing models closely approach the heavily supervised SAM when evaluated on unseen object types and styles, and outperform it when segmenting fine structures and ambiguous boundaries. In contrast, existing promptable segmentation architectures or discriminatively pretrained models fail to generalize. This suggests that generative models learn an inherent grouping mechanism that transfers across categories and domains, even without internet-scale pretraining. Code, pretrained models, and demos are available on our website.
Authors: Zihao Pan, Yu Tong, Weibin Wu, Jingyi Wang, Lifeng Chen, Zhe Zhao, Jiajia Wei, Yitong Qiao, Zibin Zheng
Abstract: Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to fail?}'' However, this information is crucial for researchers to specifically improve model robustness. Recent research suggests that models may be particularly sensitive to certain semantics in visual inputs (such as ``wet,'' ``foggy''), making them prone to errors. Inspired by this, in this paper we conducted the first exploration on large vision-language models (LVLMs) and found that LVLMs indeed are susceptible to hallucinations and various errors when facing specific semantic concepts in images. To efficiently search for these sensitive concepts, we integrated large language models (LLMs) and text-to-image (T2I) models to propose a novel semantic evolution framework. Randomly initialized semantic concepts undergo LLM-based crossover and mutation operations to form image descriptions, which are then converted by T2I models into visual inputs for LVLMs. The task-specific performance of LVLMs on each input is quantified as fitness scores for the involved semantics and serves as reward signals to further guide LLMs in exploring concepts that induce LVLMs. Extensive experiments on seven mainstream LVLMs and two multimodal tasks demonstrate the effectiveness of our method. Additionally, we provide interesting findings about the sensitive semantics of LVLMs, aiming to inspire further in-depth research.
Authors: Wenmin Li, Shunsuke Sakai, Tatsuhito Hasegawa
Abstract: Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets. Current dataset distillation techniques, particularly Trajectory Matching methods, optimize synthetic data so that the model's training trajectory on synthetic samples mirrors that on real data. While demonstrating efficacy on medium-scale synthetic datasets, these methods fail to adequately preserve semantic richness under extreme sample scarcity. To address this limitation, we propose a novel dataset distillation method integrating contrastive learning during image synthesis. By explicitly maximizing instance-level feature discrimination, our approach produces more informative and diverse synthetic samples, even when dataset sizes are significantly constrained. Experimental results demonstrate that incorporating contrastive learning substantially enhances the performance of models trained on very small-scale synthetic datasets. This integration not only guides more effective feature representation but also significantly improves the visual fidelity of the synthesized images. Experimental results demonstrate that our method achieves notable performance improvements over existing distillation techniques, especially in scenarios with extremely limited synthetic data.
Authors: Zhenyu Ning, Guangda Liu, Qihao Jin, Wenchao Ding, Minyi Guo, Jieru Zhao
Abstract: Recent developments in Video Large Language Models (Video LLMs) have enabled models to process long video sequences and demonstrate remarkable performance. Nonetheless, studies predominantly focus on offline video question answering, neglecting memory usage and response speed that are essential in various real-world applications, such as Deepseek services, autonomous driving, and robotics. To mitigate these challenges, we propose $\textbf{LiveVLM}$, a training-free framework specifically designed for streaming, online video understanding and real-time interaction. Unlike existing works that process videos only after one question is posed, LiveVLM constructs an innovative streaming-oriented KV cache to process video streams in real-time, retain long-term video details and eliminate redundant KVs, ensuring prompt responses to user queries. For continuous video streams, LiveVLM generates and compresses video key-value tensors (video KVs) to reserve visual information while improving memory efficiency. Furthermore, when a new question is proposed, LiveVLM incorporates an online question-answering process that efficiently fetches both short-term and long-term visual information, while minimizing interference from redundant context. Extensive experiments demonstrate that LiveVLM enables the foundation LLaVA-OneVision model to process 44$\times$ number of frames on the same device, and achieves up to 5$\times$ speedup in response speed compared with SoTA online methods at an input of 256 frames, while maintaining the same or better model performance.
Authors: Eduarda Caldeira, Jan Niklas Kolf, Naser Damer, Fadi Boutros
Abstract: Face recognition models have made substantial progress due to advances in deep learning and the availability of large-scale datasets. However, reliance on massive annotated datasets introduces challenges related to training computational cost and data storage, as well as potential privacy concerns regarding managing large face datasets. This paper presents DiffProb, the first data pruning approach for the application of face recognition. DiffProb assesses the prediction probabilities of training samples within each identity and prunes the ones with identical or close prediction probability values, as they are likely reinforcing the same decision boundaries, and thus contribute minimally with new information. We further enhance this process with an auxiliary cleaning mechanism to eliminate mislabeled and label-flipped samples, boosting data quality with minimal loss. Extensive experiments on CASIA-WebFace with different pruning ratios and multiple benchmarks, including LFW, CFP-FP, and IJB-C, demonstrate that DiffProb can prune up to 50% of the dataset while maintaining or even, in some settings, improving the verification accuracies. Additionally, we demonstrate DiffProb's robustness across different architectures and loss functions. Our method significantly reduces training cost and data volume, enabling efficient face recognition training and reducing the reliance on massive datasets and their demanding management.
Authors: Yuchen Li, Chaoran Feng, Zhenyu Tang, Kaiyuan Deng, Wangbo Yu, Yonghong Tian, Li Yuan
Abstract: We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthesized from dense RGB videos, which typically lack viewpoint diversity and geometric consistency, or depend on expensive, difficult-to-scale hardware setups. GS2E overcomes these limitations by first reconstructing photorealistic static scenes using 3D Gaussian Splatting, and subsequently employing a novel, physically-informed event simulation pipeline. This pipeline generally integrates adaptive trajectory interpolation with physically-consistent event contrast threshold modeling. Such an approach yields temporally dense and geometrically consistent event streams under diverse motion and lighting conditions, while ensuring strong alignment with underlying scene structures. Experimental results on event-based 3D reconstruction demonstrate GS2E's superior generalization capabilities and its practical value as a benchmark for advancing event vision research.
Authors: Xu yan, Zhaohui Wang, Rong Wei, Jingbo Yu, Dong Li, Xiangde Liu
Abstract: We propose R3GS, a robust reconstruction and relocalization framework tailored for unconstrained datasets. Our method uses a hybrid representation during training. Each anchor combines a global feature from a convolutional neural network (CNN) with a local feature encoded by the multiresolution hash grids [2]. Subsequently, several shallow multi-layer perceptrons (MLPs) predict the attributes of each Gaussians, including color, opacity, and covariance. To mitigate the adverse effects of transient objects on the reconstruction process, we ffne-tune a lightweight human detection network. Once ffne-tuned, this network generates a visibility map that efffciently generalizes to other transient objects (such as posters, banners, and cars) with minimal need for further adaptation. Additionally, to address the challenges posed by sky regions in outdoor scenes, we propose an effective sky-handling technique that incorporates a depth prior as a constraint. This allows the inffnitely distant sky to be represented on the surface of a large-radius sky sphere, signiffcantly reducing ffoaters caused by errors in sky reconstruction. Furthermore, we introduce a novel relocalization method that remains robust to changes in lighting conditions while estimating the camera pose of a given image within the reconstructed 3DGS scene. As a result, R3GS significantly enhances rendering ffdelity, improves both training and rendering efffciency, and reduces storage requirements. Our method achieves state-of-the-art performance compared to baseline methods on in-the-wild datasets. The code will be made open-source following the acceptance of the paper.
Authors: Ji Guo, Xiaolei Wen, Wenbo Jiang, Cheng Huang, Jinjin Li, Hongwei Li
Abstract: With the widespread application of super-resolution (SR) in various fields, researchers have begun to investigate its security. Previous studies have demonstrated that SR models can also be subjected to backdoor attacks through data poisoning, affecting downstream tasks. A backdoor SR model generates an attacker-predefined target image when given a triggered image while producing a normal high-resolution (HR) output for clean images. However, prior backdoor attacks on SR models have primarily focused on the stealthiness of poisoned low-resolution (LR) images while ignoring the stealthiness of poisoned HR images, making it easy for users to detect anomalous data. To address this problem, we propose BadSR, which improves the stealthiness of poisoned HR images. The key idea of BadSR is to approximate the clean HR image and the pre-defined target image in the feature space while ensuring that modifications to the clean HR image remain within a constrained range. The poisoned HR images generated by BadSR can be integrated with existing triggers. To further improve the effectiveness of BadSR, we design an adversarially optimized trigger and a backdoor gradient-driven poisoned sample selection method based on a genetic algorithm. The experimental results show that BadSR achieves a high attack success rate in various models and data sets, significantly affecting downstream tasks.
Authors: Kazuaki Mishima, Antoni Bigata Casademunt, Stavros Petridis, Maja Pantic, Kenji Suzuki
Abstract: Human facial images encode a rich spectrum of information, encompassing both stable identity-related traits and mutable attributes such as pose, expression, and emotion. While recent advances in image generation have enabled high-quality identity-conditional face synthesis, precise control over non-identity attributes remains challenging, and disentangling identity from these mutable factors is particularly difficult. To address these limitations, we propose a novel identity-conditional diffusion model that introduces two lightweight control modules designed to independently manipulate facial pose, expression, and emotion without compromising identity preservation. These modules are embedded within the cross-attention layers of the base diffusion model, enabling precise attribute control with minimal parameter overhead. Furthermore, our tailored training strategy, which leverages cross-attention between the identity feature and each non-identity control feature, encourages identity features to remain orthogonal to control signals, enhancing controllability and diversity. Quantitative and qualitative evaluations, along with perceptual user studies, demonstrate that our method surpasses existing approaches in terms of control accuracy over pose, expression, and emotion, while also improving generative diversity under identity-only conditioning.
Authors: Qi'ao Xu, Yan Xing, Jiali Hu, Yunan Jia, Rui Huang
Abstract: Change detection, a critical task in remote sensing and computer vision, aims to identify pixel-level differences between image pairs captured at the same geographic area but different times. It faces numerous challenges such as illumination variation, seasonal changes, background interference, and shooting angles, especially with a large time gap between images. While current methods have advanced, they often overlook temporal dependencies and overemphasize prominent changes while ignoring subtle but equally important changes. To address these limitations, we introduce \textbf{CEBSNet}, a novel change-excited and background-suppressed network with temporal dependency modeling for change detection. During the feature extraction, we utilize a simple Channel Swap Module (CSM) to model temporal dependency, reducing differences and noise. The Feature Excitation and Suppression Module (FESM) is developed to capture both obvious and subtle changes, maintaining the integrity of change regions. Additionally, we design a Pyramid-Aware Spatial-Channel Attention module (PASCA) to enhance the ability to detect change regions at different sizes and focus on critical regions. We conduct extensive experiments on three common street view datasets and two remote sensing datasets, and our method achieves the state-of-the-art performance.
Authors: Mengqi Lei, Yihong Wu, Siqi Li, Xinhu Zheng, Juan Wang, Yue Gao, Shaoyi Du
Abstract: Visual recognition relies on understanding both the semantics of image tokens and the complex interactions among them. Mainstream self-attention methods, while effective at modeling global pair-wise relations, fail to capture high-order associations inherent in real-world scenes and often suffer from redundant computation. Hypergraphs extend conventional graphs by modeling high-order interactions and offer a promising framework for addressing these limitations. However, existing hypergraph neural networks typically rely on static and hard hyperedge assignments, leading to excessive and redundant hyperedges with hard binary vertex memberships that overlook the continuity of visual semantics. To overcome these issues, we present Soft Hypergraph Neural Networks (SoftHGNNs), which extend the methodology of hypergraph computation, to make it truly efficient and versatile in visual recognition tasks. Our framework introduces the concept of soft hyperedges, where each vertex is associated with hyperedges via continuous participation weights rather than hard binary assignments. This dynamic and differentiable association is achieved by using the learnable hyperedge prototype. Through similarity measurements between token features and the prototype, the model generates semantically rich soft hyperedges. SoftHGNN then aggregates messages over soft hyperedges to capture high-order semantics. To further enhance efficiency when scaling up the number of soft hyperedges, we incorporate a sparse hyperedge selection mechanism that activates only the top-k important hyperedges, along with a load-balancing regularizer to ensure balanced hyperedge utilization. Experimental results across three tasks on five datasets demonstrate that SoftHGNN efficiently captures high-order associations in visual scenes, achieving significant performance improvements.
Authors: Ria Shekhawat, Hailin Li, Raghavendra Ramachandra, Sushma Venkatesh
Abstract: Leveraging the power of multimodal large language models (LLMs) offers a promising approach to enhancing the accuracy and interpretability of morphing attack detection (MAD), especially in real-world biometric applications. This work introduces the use of LLMs for differential morphing attack detection (D-MAD). To the best of our knowledge, this is the first study to employ multimodal LLMs to D-MAD using real biometric data. To effectively utilize these models, we design Chain-of-Thought (CoT)-based prompts to reduce failure-to-answer rates and enhance the reasoning behind decisions. Our contributions include: (1) the first application of multimodal LLMs for D-MAD using real data subjects, (2) CoT-based prompt engineering to improve response reliability and explainability, (3) comprehensive qualitative and quantitative benchmarking of LLM performance using data from 54 individuals captured in passport enrollment scenarios, and (4) comparative analysis of two multimodal LLMs: ChatGPT-4o and Gemini providing insights into their morphing attack detection accuracy and decision transparency. Experimental results show that ChatGPT-4o outperforms Gemini in detection accuracy, especially against GAN-based morphs, though both models struggle under challenging conditions. While Gemini offers more consistent explanations, ChatGPT-4o is more resilient but prone to a higher failure-to-answer rate.
Authors: Bernardin Ligan, Khalide Jbilou, Fahd Kalloubi, Ahmed Ratnani
Abstract: Foundation models have achieved great success across diverse domains, including remote sensing (RS), thanks to their versatility and strong generalization abilities. However, most RS foundation models are designed for multispectral data, while hyperspectral imagery (HSI) - with its hundreds of spectral bands - remains less explored. Fine-tuning such models for downstream tasks is also challenging, often demanding considerable memory and storage. In this paper, we propose an efficient framework to fine-tune SpectralGPT, a multispectral foundation model, for hyperspectral image classification (HSIC). We explore several Parameter-Efficient Fine-Tuning (PEFT) methods, including Low-Rank Adaptation (LoRA), Kronecker-based adaptation (KronA), Low-Rank Kronecker (LoKr), and the recent LoRA+, which uses distinct learning rates for low-rank adapters scaled by a factor lambda. Inspired by LoRA+, we introduce KronA+, which applies a similar mechanism to the Kronecker matrices. We evaluate our approach on five datasets from different sensors, showing competitive performance with state-of-the-art HSI models. Our full fine-tuning (FFT) setup for SpectralGPT even outperforms a dedicated hyperspectral foundation model on some datasets while requiring only a quarter of the training epochs. Under the same number of epochs, KronA+ reaches similar performance with far fewer trainable parameters - just 0.056 percent - and adds only approximately 0.2 megabytes of storage, making it the most effective PEFT method tested.
Authors: Hon Ming Yam, Zhongliang Guo, Chun Pong Lau
Abstract: The proliferation of diffusion-based deepfake technologies poses significant risks for unauthorized and unethical facial image manipulation. While traditional countermeasures have primarily focused on passive detection methods, this paper introduces a novel proactive defense strategy through adversarial attacks that preemptively protect facial images from being exploited by diffusion-based deepfake systems. Existing adversarial protection methods predominantly target conventional generative architectures (GANs, AEs, VAEs) and fail to address the unique challenges presented by diffusion models, which have become the predominant framework for high-quality facial deepfakes. Current diffusion-specific adversarial approaches are limited by their reliance on specific model architectures and weights, rendering them ineffective against the diverse landscape of diffusion-based deepfake implementations. Additionally, they typically employ global perturbation strategies that inadequately address the region-specific nature of facial manipulation in deepfakes.
Authors: Angelique Mangubat, Shane Gilroy
Abstract: Road safety is a critical challenge, particularly for cyclists, who are among the most vulnerable road users. This study aims to enhance road safety by proposing a novel benchmark for bicycle occlusion level classification using advanced computer vision techniques. Utilizing a parts-based detection model, images are annotated and processed through a custom image detection pipeline. A novel method of bicycle occlusion level is proposed to objectively quantify the visibility and occlusion level of bicycle semantic parts. The findings indicate that the model robustly quantifies the visibility and occlusion level of bicycles, a significant improvement over the subjective methods used by the current state of the art. Widespread use of the proposed methodology will facilitate the accurate performance reporting of cyclist detection algorithms for occluded cyclists, informing the development of more robust vulnerable road user detection methods for autonomous vehicles.
Authors: Dasol Choi, Seunghyun Lee, Youngsook Song
Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities in understanding visual content, but their reliability in safety-critical contexts remains under-explored. We introduce VERI (Visual Emergency Recognition Dataset), a carefully designed diagnostic benchmark of 200 images (100 contrastive pairs). Each emergency scene is matched with a visually similar but safe counterpart through multi-stage human verification and iterative refinement. Using a two-stage protocol - risk identification and emergency response - we evaluate 14 VLMs (2B-124B parameters) across medical emergencies, accidents, and natural disasters. Our analysis reveals a systematic overreaction problem: models excel at identifying real emergencies (70-100 percent success rate) but suffer from an alarming rate of false alarms, misidentifying 31-96 percent of safe situations as dangerous, with 10 scenarios failed by all models regardless of scale. This "better-safe-than-sorry" bias manifests primarily through contextual overinterpretation (88-93 percent of errors), challenging VLMs' reliability for safety applications. These findings highlight persistent limitations that are not resolved by increasing model scale, motivating targeted approaches for improving contextual safety assessment in visually misleading scenarios.
Authors: Naman Patel, Prashanth Krishnamurthy, Farshad Khorrami
Abstract: Mapping and understanding complex 3D environments is fundamental to how autonomous systems perceive and interact with the physical world, requiring both precise geometric reconstruction and rich semantic comprehension. While existing 3D semantic mapping systems excel at reconstructing and identifying predefined object instances, they lack the flexibility to efficiently build semantic maps with open-vocabulary during online operation. Although recent vision-language models have enabled open-vocabulary object recognition in 2D images, they haven't yet bridged the gap to 3D spatial understanding. The critical challenge lies in developing a training-free unified system that can simultaneously construct accurate 3D maps while maintaining semantic consistency and supporting natural language interactions in real time. In this paper, we develop a zero-shot framework that seamlessly integrates GPU-accelerated geometric reconstruction with open-vocabulary vision-language models through online instance-level semantic embedding fusion, guided by hierarchical object association with spatial indexing. Our training-free system achieves superior performance through incremental processing and unified geometric-semantic updates, while robustly handling 2D segmentation inconsistencies. The proposed general-purpose 3D scene understanding framework can be used for various tasks including zero-shot 3D instance retrieval, segmentation, and object detection to reason about previously unseen objects and interpret natural language queries. The project page is available at https://razer-3d.github.io.
Authors: Raphael Sulzer, Liuyun Duan, Nicolas Girard, Florent Lafarge
Abstract: We present the P$^3$ dataset, a large-scale multimodal benchmark for building vectorization, constructed from aerial LiDAR point clouds, high-resolution aerial imagery, and vectorized 2D building outlines, collected across three continents. The dataset contains over 10 billion LiDAR points with decimeter-level accuracy and RGB images at a ground sampling distance of 25 centimeter. While many existing datasets primarily focus on the image modality, P$^3$ offers a complementary perspective by also incorporating dense 3D information. We demonstrate that LiDAR point clouds serve as a robust modality for predicting building polygons, both in hybrid and end-to-end learning frameworks. Moreover, fusing aerial LiDAR and imagery further improves accuracy and geometric quality of predicted polygons. The P$^3$ dataset is publicly available, along with code and pretrained weights of three state-of-the-art models for building polygon prediction at https://github.com/raphaelsulzer/PixelsPointsPolygons .
Authors: Hendrik Junkawitsch, Guoxing Sun, Heming Zhu, Christian Theobalt, Marc Habermann
Abstract: With recent advancements in neural rendering and motion capture algorithms, remarkable progress has been made in photorealistic human avatar modeling, unlocking immense potential for applications in virtual reality, augmented reality, remote communication, and industries such as gaming, film, and medicine. However, existing methods fail to provide complete, faithful, and expressive control over human avatars due to their entangled representation of facial expressions and body movements. In this work, we introduce Expressive Virtual Avatars (EVA), an actor-specific, fully controllable, and expressive human avatar framework that achieves high-fidelity, lifelike renderings in real time while enabling independent control of facial expressions, body movements, and hand gestures. Specifically, our approach designs the human avatar as a two-layer model: an expressive template geometry layer and a 3D Gaussian appearance layer. First, we present an expressive template tracking algorithm that leverages coarse-to-fine optimization to accurately recover body motions, facial expressions, and non-rigid deformation parameters from multi-view videos. Next, we propose a novel decoupled 3D Gaussian appearance model designed to effectively disentangle body and facial appearance. Unlike unified Gaussian estimation approaches, our method employs two specialized and independent modules to model the body and face separately. Experimental results demonstrate that EVA surpasses state-of-the-art methods in terms of rendering quality and expressiveness, validating its effectiveness in creating full-body avatars. This work represents a significant advancement towards fully drivable digital human models, enabling the creation of lifelike digital avatars that faithfully replicate human geometry and appearance.
Authors: Huilin Zhu, Senyao Li, Jingling Yuan, Zhengwei Yang, Yu Guo, Wenxuan Liu, Xian Zhong, Shengfeng He
Abstract: Expanding pre-trained zero-shot counting models to handle unseen categories requires more than simply adding new prompts, as this approach does not achieve the necessary alignment between text and visual features for accurate counting. We introduce RichCount, the first framework to address these limitations, employing a two-stage training strategy that enhances text encoding and strengthens the model's association with objects in images. RichCount improves zero-shot counting for unseen categories through two key objectives: (1) enriching text features with a feed-forward network and adapter trained on text-image similarity, thereby creating robust, aligned representations; and (2) applying this refined encoder to counting tasks, enabling effective generalization across diverse prompts and complex images. In this manner, RichCount goes beyond simple prompt expansion to establish meaningful feature alignment that supports accurate counting across novel categories. Extensive experiments on three benchmark datasets demonstrate the effectiveness of RichCount, achieving state-of-the-art performance in zero-shot counting and significantly enhancing generalization to unseen categories in open-world scenarios.
Authors: Hichem Boussaid, Lucrezia Tosato, Flora Weissgerber, Camille Kurtz, Laurent Wendling, Sylvain Lobry
Abstract: The extraction of visual features is an essential step in Visual Question Answering (VQA). Building a good visual representation of the analyzed scene is indeed one of the essential keys for the system to be able to correctly understand the latter in order to answer complex questions. In many fields such as remote sensing, the visual feature extraction step could benefit significantly from leveraging different image modalities carrying complementary spectral, spatial and contextual information. In this work, we propose to add multiple image modalities to VQA in the particular context of remote sensing, leading to a novel task for the computer vision community. To this end, we introduce a new VQA dataset, named TAMMI (Text and Multi-Modal Imagery) with diverse questions on scenes described by three different modalities (very high resolution RGB, multi-spectral imaging data and synthetic aperture radar). Thanks to an automated pipeline, this dataset can be easily extended according to experimental needs. We also propose the MM-RSVQA (Multi-modal Multi-resolution Remote Sensing Visual Question Answering) model, based on VisualBERT, a vision-language transformer, to effectively combine the multiple image modalities and text through a trainable fusion process. A preliminary experimental study shows promising results of our methodology on this challenging dataset, with an accuracy of 65.56% on the targeted VQA task. This pioneering work paves the way for the community to a new multi-modal multi-resolution VQA task that can be applied in other imaging domains (such as medical imaging) where multi-modality can enrich the visual representation of a scene. The dataset and code are available at https://tammi.sylvainlobry.com/.
Authors: Patrik Reiske, Marcus N. Boon, Niek Andresen, Sole Traverso, Katharina Hohlbaum, Lars Lewejohann, Christa Th\"one-Reineke, Olaf Hellwich, Henning Sprekeler
Abstract: Machine learning and computer vision methods have a major impact on the study of natural animal behavior, as they enable the (semi-)automatic analysis of vast amounts of video data. Mice are the standard mammalian model system in most research fields, but the datasets available today to refine such methods focus either on simple or social behaviors. In this work, we present a video dataset of individual mice solving complex mechanical puzzles, so-called lockboxes. The more than 110 hours of total playtime show their behavior recorded from three different perspectives. As a benchmark for frame-level action classification methods, we provide human-annotated labels for all videos of two different mice, that equal 13% of our dataset. Our keypoint (pose) tracking-based action classification framework illustrates the challenges of automated labeling of fine-grained behaviors, such as the manipulation of objects. We hope that our work will help accelerate the advancement of automated action and behavior classification in the computational neuroscience community. Our dataset is publicly available at https://doi.org/10.14279/depositonce-23850
Authors: Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache
Abstract: Vision Transformers have emerged as the state-of-the-art models in various Computer Vision tasks, but their high computational and resource demands pose significant challenges. While Mixture-of-Experts (MoE) can make these models more efficient, they often require costly retraining or even training from scratch. Recent developments aim to reduce these computational costs by leveraging pretrained networks. These have been shown to produce sparse activation patterns in the Multi-Layer Perceptrons (MLPs) of the encoder blocks, allowing for conditional activation of only relevant subnetworks for each sample. Building on this idea, we propose a new method to construct MoE variants from pretrained models. Our approach extracts expert subnetworks from the model's MLP layers post-training in two phases. First, we cluster output activations to identify distinct activation patterns. In the second phase, we use these clusters to extract the corresponding subnetworks responsible for producing them. On ImageNet-1k recognition tasks, we demonstrate that these extracted experts can perform surprisingly well out of the box and require only minimal fine-tuning to regain 98% of the original performance, all while reducing MACs and model size, by up to 36% and 32% respectively.
Authors: Raza Imam, Rufael Marew, Mohammad Yaqub
Abstract: Medical Vision-Language Models (MVLMs) have achieved par excellence generalization in medical image analysis, yet their performance under noisy, corrupted conditions remains largely untested. Clinical imaging is inherently susceptible to acquisition artifacts and noise; however, existing evaluations predominantly assess generally clean datasets, overlooking robustness -- i.e., the model's ability to perform under real-world distortions. To address this gap, we first introduce MediMeta-C, a corruption benchmark that systematically applies several perturbations across multiple medical imaging datasets. Combined with MedMNIST-C, this establishes a comprehensive robustness evaluation framework for MVLMs. We further propose RobustMedCLIP, a visual encoder adaptation of a pretrained MVLM that incorporates few-shot tuning to enhance resilience against corruptions. Through extensive experiments, we benchmark 5 major MVLMs across 5 medical imaging modalities, revealing that existing models exhibit severe degradation under corruption and struggle with domain-modality tradeoffs. Our findings highlight the necessity of diverse training and robust adaptation strategies, demonstrating that efficient low-rank adaptation when paired with few-shot tuning, improves robustness while preserving generalization across modalities.
Authors: Zeqing Wang, Shiyuan Zhang, Chengpei Tang, Keze Wang
Abstract: Reasoning about temporal causality, particularly irreversible transformations of objects governed by real-world knowledge (e.g., fruit decay and human aging), is a fundamental aspect of human visual understanding. Unlike temporal perception based on simple event sequences, this form of reasoning requires a deeper comprehension of how object states change over time. Although the current powerful Vision-Language Models (VLMs) have demonstrated impressive performance on a wide range of downstream tasks, their capacity to reason about temporal causality remains underexplored. To address this gap, we introduce \textbf{TimeCausality}, a novel benchmark specifically designed to evaluate the causal reasoning ability of VLMs in the temporal dimension. Based on our TimeCausality, we find that while the current SOTA open-source VLMs have achieved performance levels comparable to closed-source models like GPT-4o on various standard visual question answering tasks, they fall significantly behind on our benchmark compared with their closed-source competitors. Furthermore, even GPT-4o exhibits a marked drop in performance on TimeCausality compared to its results on other tasks. These findings underscore the critical need to incorporate temporal causality into the evaluation and development of VLMs, and they highlight an important challenge for the open-source VLM community moving forward. Code and Data are available at \href{https://github.com/Zeqing-Wang/TimeCausality }{TimeCausality}.
Authors: Xintong Zhang, Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaowen Zhang, Yang Liu, Tao Yuan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li
Abstract: Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks. However, the multimodal reasoning capability has not been fully explored in existing models. In this paper, we propose a Chain-of-Focus (CoF) method that allows VLMs to perform adaptive focusing and zooming in on key image regions based on obtained visual cues and the given questions, achieving efficient multimodal reasoning. To enable this CoF capability, we present a two-stage training pipeline, including supervised fine-tuning (SFT) and reinforcement learning (RL). In the SFT stage, we construct the MM-CoF dataset, comprising 3K samples derived from a visual agent designed to adaptively identify key regions to solve visual tasks with different image resolutions and questions. We use MM-CoF to fine-tune the Qwen2.5-VL model for cold start. In the RL stage, we leverage the outcome accuracies and formats as rewards to update the Qwen2.5-VL model, enabling further refining the search and reasoning strategy of models without human priors. Our model achieves significant improvements on multiple benchmarks. On the V* benchmark that requires strong visual reasoning capability, our model outperforms existing VLMs by 5% among 8 image resolutions ranging from 224 to 4K, demonstrating the effectiveness of the proposed CoF method and facilitating the more efficient deployment of VLMs in practical applications.
Authors: Jianyuan Guo, Peike Li, Trevor Cohn
Abstract: Sign Language Translation (SLT) aims to map sign language videos to spoken language text. A common approach relies on gloss annotations as an intermediate representation, decomposing SLT into two sub-tasks: video-to-gloss recognition and gloss-to-text translation. While effective, this paradigm depends on expert-annotated gloss labels, which are costly and rarely available in existing datasets, limiting its scalability. To address this challenge, we propose a gloss-free pseudo gloss generation framework that eliminates the need for human-annotated glosses while preserving the structured intermediate representation. Specifically, we prompt a Large Language Model (LLM) with a few example text-gloss pairs using in-context learning to produce draft sign glosses from spoken language text. To enhance the correspondence between LLM-generated pseudo glosses and the sign sequences in video, we correct the ordering in the pseudo glosses for better alignment via a weakly supervised learning process. This reordering facilitates the incorporation of auxiliary alignment objectives, and allows for the use of efficient supervision via a Connectionist Temporal Classification (CTC) loss. We train our SLT mode, which consists of a vision encoder and a translator, through a three-stage pipeline, which progressively narrows the modality gap between sign language and spoken language. Despite its simplicity, our approach outperforms previous state-of-the-art gloss-free frameworks on two SLT benchmarks and achieves competitive results compared to gloss-based methods.
Authors: Ge Meng, Zhongnan Cai, Ruizhe Chen, Jingyan Tu, Yingying Wang, Yue Huang, Xinghao Ding
Abstract: Generating hyperspectral images (HSIs) from RGB images through spectral reconstruction can significantly reduce the cost of HSI acquisition. In this paper, we propose a Fractal-Based Recursive Spectral Reconstruction Network (FRN), which differs from existing paradigms that attempt to directly integrate the full-spectrum information from the R, G, and B channels in a one-shot manner. Instead, it treats spectral reconstruction as a progressive process, predicting from broad to narrow bands or employing a coarse-to-fine approach for predicting the next wavelength. Inspired by fractals in mathematics, FRN establishes a novel spectral reconstruction paradigm by recursively invoking an atomic reconstruction module. In each invocation, only the spectral information from neighboring bands is used to provide clues for the generation of the image at the next wavelength, which follows the low-rank property of spectral data. Moreover, we design a band-aware state space model that employs a pixel-differentiated scanning strategy at different stages of the generation process, further suppressing interference from low-correlation regions caused by reflectance differences. Through extensive experimentation across different datasets, FRN achieves superior reconstruction performance compared to state-of-the-art methods in both quantitative and qualitative evaluations.
Authors: David Nordstr\"om, Johan Edstedt, Fredrik Kahl, Georg B\"okman
Abstract: Recent efforts at scaling computer vision models have established Vision Transformers (ViTs) as the leading architecture. ViTs incorporate weight sharing over image patches as an important inductive bias. In this work, we show that ViTs benefit from incorporating equivariance under the octic group, i.e., reflections and 90-degree rotations, as a further inductive bias. We develop new architectures, octic ViTs, that use octic-equivariant layers and put them to the test on both supervised and self-supervised learning. Through extensive experiments on DeiT-III and DINOv2 training on ImageNet-1K, we show that octic ViTs yield more computationally efficient networks while also improving performance. In particular, we achieve approximately 40% reduction in FLOPs for ViT-H while simultaneously improving both classification and segmentation results.
Authors: Ziqiang Xu, Qi Dai, Tian Xie, Yifan Yang, Kai Qiu, DongDong Chen, Zuxuan Wu, Chong Luo
Abstract: Video understanding is inherently intention-driven-humans naturally focus on relevant frames based on their goals. Recent advancements in multimodal large language models (MLLMs) have enabled flexible query-driven reasoning; however, video-based frameworks like Video Chain-of-Thought lack direct training signals to effectively identify relevant frames. Current approaches often rely on heuristic methods or pseudo-label supervised annotations, which are both costly and limited in scalability across diverse scenarios. To overcome these challenges, we introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in intention-driven video understanding. An iterated amplification strategy is adopted to perform alternating cyclic training in the video CoT system, where each component undergoes iterative cycles of refinement to improve its capabilities. ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error, eliminating the need for expensive annotations while closely aligning with human-like learning processes. Comprehensive experiments across multiple benchmarks, including VideoMME, LVBench, and MLVU, demonstrate that ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks, highlighting its effectiveness and scalability. Notably, ViaRL achieves a nearly 15\% improvement on Needle QA, a subset of MLVU, which is required to search a specific needle within a long video and regarded as one of the most suitable benchmarks for evaluating temporal grounding.
Authors: Die Chen, Zhiwen Li, Cen Chen, Yuexiang Xie, Xiaodan Li, Jinyan Ye, Yingda Chen, Yaliang Li
Abstract: Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of diffusion models can inadvertently lead to the generation of not-safe-for-work (NSFW) content, posing significant risks to their safe deployment. While several concept erasure methods have been proposed to mitigate the issue associated with NSFW content, a comprehensive evaluation of their effectiveness across various scenarios remains absent. To bridge this gap, we introduce a full-pipeline toolkit specifically designed for concept erasure and conduct the first systematic study of NSFW concept erasure methods. By examining the interplay between the underlying mechanisms and empirical observations, we provide in-depth insights and practical guidance for the effective application of concept erasure methods in various real-world scenarios, with the aim of advancing the understanding of content safety in diffusion models and establishing a solid foundation for future research and development in this critical area.
Authors: Guotao Xu, Bowen Zhao, Yang Xiao, Yantao Zhong, Liang Zhai, Qingqi Pei
Abstract: Face recognition is an effective technology for identifying a target person by facial images. However, sensitive facial images raises privacy concerns. Although privacy-preserving face recognition is one of potential solutions, this solution neither fully addresses the privacy concerns nor is efficient enough. To this end, we propose an efficient privacy-preserving solution for face recognition, named Pura, which sufficiently protects facial privacy and supports face recognition over encrypted data efficiently. Specifically, we propose a privacy-preserving and non-interactive architecture for face recognition through the threshold Paillier cryptosystem. Additionally, we carefully design a suite of underlying secure computing protocols to enable efficient operations of face recognition over encrypted data directly. Furthermore, we introduce a parallel computing mechanism to enhance the performance of the proposed secure computing protocols. Privacy analysis demonstrates that Pura fully safeguards personal facial privacy. Experimental evaluations demonstrate that Pura achieves recognition speeds up to 16 times faster than the state-of-the-art.
Authors: Jiaying Wu, Fanxiao Li, Min-Yen Kan, Bryan Hooi
Abstract: The real-world impact of misinformation stems from the underlying misleading narratives that creators seek to convey. As such, interpreting misleading creator intent is essential for multimodal misinformation detection (MMD) systems aimed at effective information governance. In this paper, we introduce an automated framework that simulates real-world multimodal news creation by explicitly modeling creator intent through two components: the desired influence and the execution plan. Using this framework, we construct DeceptionDecoded, a large-scale benchmark comprising 12,000 image-caption pairs aligned with trustworthy reference articles. The dataset captures both misleading and non-misleading intents and spans manipulations across visual and textual modalities. We conduct a comprehensive evaluation of 14 state-of-the-art vision-language models (VLMs) on three intent-centric tasks: (1) misleading intent detection, (2) misleading source attribution, and (3) creator desire inference. Despite recent advances, we observe that current VLMs fall short in recognizing misleading intent, often relying on spurious cues such as superficial cross-modal consistency, stylistic signals, and heuristic authenticity hints. Our findings highlight the pressing need for intent-aware modeling in MMD and open new directions for developing systems capable of deeper reasoning about multimodal misinformation.
Authors: Ce Zhang, Zifu Wan, Simon Stepputtis, Katia Sycara, Yaqi Xie
Abstract: Semantic segmentation relying solely on RGB data often struggles in challenging conditions such as low illumination and obscured views, limiting its reliability in critical applications like autonomous driving. To address this, integrating additional thermal radiation data with RGB images demonstrates enhanced performance and robustness. However, how to effectively reconcile the modality discrepancies and fuse the RGB and thermal features remains a well-known challenge. In this work, we address this challenge from a novel spectral perspective. We observe that the multi-modal features can be categorized into two spectral components: low-frequency features that provide broad scene context, including color variations and smooth areas, and high-frequency features that capture modality-specific details such as edges and textures. Inspired by this, we propose the Spectral-aware Global Fusion Network (SGFNet) to effectively enhance and fuse the multi-modal features by explicitly modeling the interactions between the high-frequency, modality-specific features. Our experimental results demonstrate that SGFNet outperforms the state-of-the-art methods on the MFNet and PST900 datasets.
Authors: Conghao Xiong, Zhengrui Guo, Zhe Xu, Yifei Zhang, Raymond Kai-Yu Tong, Si Yong Yeo, Hao Chen, Joseph J. Y. Sung, Irwin King
Abstract: Deep learning has advanced computational pathology but expert annotations remain scarce. Few-shot learning mitigates annotation burdens yet suffers from overfitting and discriminative feature mischaracterization. In addition, the current few-shot multiple instance learning (MIL) approaches leverage pretrained vision-language models to alleviate these issues, but at the cost of complex preprocessing and high computational cost. We propose a Squeeze-and-Recalibrate (SR) block, a drop-in replacement for linear layers in MIL models to address these challenges. The SR block comprises two core components: a pair of low-rank trainable matrices (squeeze pathway, SP) that reduces parameter count and imposes a bottleneck to prevent spurious feature learning, and a frozen random recalibration matrix that preserves geometric structure, diversifies feature directions, and redefines the optimization objective for the SP. We provide theoretical guarantees that the SR block can approximate any linear mapping to arbitrary precision, thereby ensuring that the performance of a standard MIL model serves as a lower bound for its SR-enhanced counterpart. Extensive experiments demonstrate that our SR-MIL models consistently outperform prior methods while requiring significantly fewer parameters and no architectural changes.
Authors: Debarshi Brahma, Anuska Roy, Soma Biswas
Abstract: Recently, Vision-Language foundation models like CLIP and ALIGN, which are pre-trained on large-scale data have shown remarkable zero-shot generalization to diverse datasets with different classes and even domains. In this work, we take a step further and analyze whether these models can be adapted to target datasets having very different distributions and classes compared to what these models have been trained on, using only a few labeled examples from the target dataset. In such scenarios, finetuning large pretrained models is challenging due to problems of overfitting as well as loss of generalization, and has not been well explored in prior literature. Since, the pre-training data of such models are unavailable, it is difficult to comprehend the performance on various downstream datasets. First, we try to answer the question: Given a target dataset with a few labelled examples, can we estimate whether further fine-tuning can enhance the performance compared to zero-shot evaluation? by analyzing the common vision-language embedding space. Based on the analysis, we propose a novel prompt-tuning method, PromptMargin for adapting such large-scale VLMs directly on the few target samples. PromptMargin effectively tunes the text as well as visual prompts for this task, and has two main modules: 1) Firstly, we use a selective augmentation strategy to complement the few training samples in each task; 2) Additionally, to ensure robust training in the presence of unfamiliar class names, we increase the inter-class margin for improved class discrimination using a novel Multimodal Margin Regularizer. Extensive experiments and analysis across fifteen target benchmark datasets, with varying degrees of distribution shifts from natural images, shows the effectiveness of the proposed framework over the existing state-of-the-art approaches applied to this setting. github.com/debarshigit/PromptMargin.
Authors: Zihui Cheng, Qiguang Chen, Xiao Xu, Jiaqi Wang, Weiyun Wang, Hao Fei, Yidong Wang, Alex Jinpeng Wang, Zhi Chen, Wanxiang Che, Libo Qin
Abstract: Large Vision-Language Models (LVLMs) have achieved significant success in multimodal tasks, with multimodal chain-of-thought (MCoT) further enhancing performance and interpretability. Recent MCoT methods fall into two categories: (i) Textual-MCoT (T-MCoT), which takes multimodal input and produces textual output; and (ii) Interleaved-MCoT (I-MCoT), which generates interleaved image-text outputs. Despite advances in both approaches, the mechanisms driving these improvements are not fully understood. To fill this gap, we first reveal that MCoT boosts LVLMs by incorporating visual thoughts, which convey image information to the reasoning process regardless of the MCoT format, depending only on clarity and conciseness of expression. Furthermore, to explore visual thoughts systematically, we define four distinct forms of visual thought expressions and analyze them comprehensively. Our findings demonstrate that these forms differ in clarity and conciseness, yielding varying levels of MCoT improvement. Additionally, we explore the internal nature of visual thoughts, finding that visual thoughts serve as intermediaries between the input image and reasoning to deeper transformer layers, enabling more advanced visual information transmission. We hope that the visual thoughts can inspire further breakthroughs for future MCoT research.
Authors: Chang Liu
Abstract: To overcome the constraints of the underwater environment and improve the accuracy and robustness of underwater target detection models, this paper develops a specialized dataset for underwater target detection and proposes an efficient algorithm for underwater multi-target detection. A self-supervised learning based on the SimSiam structure is employed for the pre-training of underwater target detection network. To address the problems of low detection accuracy caused by low contrast, mutual occlusion and dense distribution of underwater targets in underwater object detection, a detection model suitable for underwater target detection is proposed by introducing deformable convolution and dilated convolution. The proposed detection model can obtain more effective information by increasing the receptive field. In addition, the regression loss function EIoU is introduced, which improves model performance by separately calculating the width and height losses of the predicted box. Experiment results show that the accuracy of the underwater target detection has been improved by the proposed detector.
Authors: Zane K J Hartley, Lewis A G Stuart, Andrew P French, Michael P Pound
Abstract: Recent years have seen substantial improvements in the ability to generate synthetic 3D objects using AI. However, generating complex 3D objects, such as plants, remains a considerable challenge. Current generative 3D models struggle with plant generation compared to general objects, limiting their usability in plant analysis tools, which require fine detail and accurate geometry. We introduce PlantDreamer, a novel approach to 3D synthetic plant generation, which can achieve greater levels of realism for complex plant geometry and textures than available text-to-3D models. To achieve this, our new generation pipeline leverages a depth ControlNet, fine-tuned Low-Rank Adaptation and an adaptable Gaussian culling algorithm, which directly improve textural realism and geometric integrity of generated 3D plant models. Additionally, PlantDreamer enables both purely synthetic plant generation, by leveraging L-System-generated meshes, and the enhancement of real-world plant point clouds by converting them into 3D Gaussian Splats. We evaluate our approach by comparing its outputs with state-of-the-art text-to-3D models, demonstrating that PlantDreamer outperforms existing methods in producing high-fidelity synthetic plants. Our results indicate that our approach not only advances synthetic plant generation, but also facilitates the upgrading of legacy point cloud datasets, making it a valuable tool for 3D phenotyping applications.
Authors: Lingyu Kong, Hongzhi Zhang, Jingyuan Zhang, Jianzhao Huang, Kunze Li, Qi Wang, Fuzheng Zhang
Abstract: Current vision-language models (VLMs) have demonstrated remarkable capabilities across diverse video understanding applications. Designing VLMs for video inputs requires effectively modeling the temporal dimension (i.e. capturing dependencies across frames) and balancing the processing of short and long videos. Specifically, short videos demand preservation of fine-grained details, whereas long videos require strategic compression of visual information to handle extensive temporal contexts efficiently. However, our empirical analysis reveals a critical limitation: most existing VLMs suffer severe performance degradation in long video understanding tasks when compressing visual tokens below a quarter of their original visual tokens. To enable more effective modeling of both short and long video inputs, we propose Clapper, a method that utilizes a slow-fast strategy for video representation and introduces a novel module named TimePerceiver for efficient temporal-spatial encoding within existing VLM backbones. By using our method, we achieves 13x compression of visual tokens per frame (averaging 61 tokens/frame) without compromising QA accuracy. In our experiments, Clapper achieves 62.0% on VideoMME, 69.8% on MLVU, and 67.4% on TempCompass, all with fewer than 6,000 visual tokens per video. The code will be publicly available on the homepage.
Authors: Chang Liu
Abstract: Computational Fluid Dynamics (CFD) is the main approach to analyzing flow field. However, the convergence and accuracy depend largely on mathematical models of flow, numerical methods, and time consumption. Deep learning-based analysis of flow filed provides an alternative. For the task of flow field prediction, an improved Convolutional Long Short-Term Memory (Con-vLSTM) Neural Network is proposed as the baseline network in consideration of the temporal and spatial characteristics of flow field. Combining dynamic mesh technology and User-Defined Function (UDF), numerical simulations of flow around a circular cylinder were conducted. Flow field snapshots were used to sample data from the cylinder's wake region at different time instants, constructing a flow field dataset with sufficient volume and rich flow state var-iations. Residual networks and attention mechanisms are combined with the standard ConvLSTM model. Compared with the standard ConvLSTM model, the results demonstrate that the improved ConvLSTM model can extract more temporal and spatial features while having fewer parameters and shorter train-ing time.
Authors: Andrew Caunes, Thierry Chateau, Vincent Fremont
Abstract: 3D semantic segmentation plays a pivotal role in autonomous driving and road infrastructure analysis, yet state-of-the-art 3D models are prone to severe domain shift when deployed across different datasets. We propose a novel multi-view projection framework that excels in both domain generalization (DG) and unsupervised domain adaptation (UDA). Our approach first aligns Lidar scans into coherent 3D scenes and renders them from multiple virtual camera poses to create a large-scale synthetic 2D dataset (PC2D). We then use it to train a 2D segmentation model in-domain. During inference, the model processes hundreds of views per scene; the resulting logits are back-projected to 3D with an occlusion-aware voting scheme to generate final point-wise labels. Our framework is modular and enables extensive exploration of key design parameters, such as view generation optimization (VGO), visualization modality optimization (MODO), and 2D model choice. We evaluate on the nuScenes and SemanticKITTI datasets under both the DG and UDA settings. We achieve state-of-the-art results in UDA and close to state-of-the-art in DG, with particularly large gains on large, static classes. Our code and dataset generation tools will be publicly available at https://github.com/andrewcaunes/ia4markings
Authors: Hossein Hassani, Soodeh Nikan, Abdallah Shami
Abstract: Vision Language Models (VLMs) employed for visual question-answering (VQA) in autonomous driving often require substantial computational resources that pose a challenge for their deployment in resource-constrained vehicles. To address this challenge, we introduce TinyDrive, a lightweight yet effective VLM for multi-view VQA in driving scenarios. Our model comprises two key components including a multiscale vision encoder and a dual-level prioritization mechanism for tokens and sequences. The multiscale encoder facilitates the processing of multi-view images at diverse resolutions through scale injection and cross-scale gating to generate enhanced visual representations. At the token level, we design a token routing mechanism that dynamically selects and process the most informative tokens based on learned importance scores. At the sequence level, we propose integrating normalized loss, uncertainty estimates, and a diversity metric to formulate sequence scores that rank and preserve samples within a sequence priority buffer. Samples with higher scores are more frequently selected for training. TinyDrive is first evaluated on our custom-curated VQA dataset, and it is subsequently tested on the public DriveLM benchmark, where it achieves state-of-the-art language understanding performance. Notably, it achieves relative improvements of 11.1% and 35.4% in BLEU-4 and METEOR scores, respectively, despite having a significantly smaller parameter count.
Authors: Xin Huang, Ruibin Li, Tong Jia, Wei Zheng, Ya Wang
Abstract: Vision-Language Models (VLMs) are essential for multimodal tasks, especially compositional reasoning (CR) tasks, which require distinguishing fine-grained semantic differences between visual and textual embeddings. However, existing methods primarily fine-tune the model by generating text-based hard negative samples, neglecting the importance of image-based negative samples, which results in insufficient training of the visual encoder and ultimately impacts the overall performance of the model. Moreover, negative samples are typically treated uniformly, without considering their difficulty levels, and the alignment of positive samples is insufficient, which leads to challenges in aligning difficult sample pairs. To address these issues, we propose Adaptive Hard Negative Perturbation Learning (AHNPL). AHNPL translates text-based hard negatives into the visual domain to generate semantically disturbed image-based negatives for training the model, thereby enhancing its overall performance. AHNPL also introduces a contrastive learning approach using a multimodal hard negative loss to improve the model's discrimination of hard negatives within each modality and a dynamic margin loss that adjusts the contrastive margin according to sample difficulty to enhance the distinction of challenging sample pairs. Experiments on three public datasets demonstrate that our method effectively boosts VLMs' performance on complex CR tasks. The source code is available at https://github.com/nynu-BDAI/AHNPL.
Authors: Hua Li, Shijie Lian, Zhiyuan Li, Runmin Cong, Sam Kwong
Abstract: With recent breakthroughs in large-scale modeling, the Segment Anything Model (SAM) has demonstrated significant potential in a variety of visual applications. However, due to the lack of underwater domain expertise, SAM and its variants face performance limitations in end-to-end underwater instance segmentation tasks, while their higher computational requirements further hinder their application in underwater scenarios. To address this challenge, we propose a large-scale underwater instance segmentation dataset, UIIS10K, which includes 10,048 images with pixel-level annotations for 10 categories. Then, we introduce UWSAM, an efficient model designed for automatic and accurate segmentation of underwater instances. UWSAM efficiently distills knowledge from the SAM ViT-Huge image encoder into the smaller ViT-Small image encoder via the Mask GAT-based Underwater Knowledge Distillation (MG-UKD) method for effective visual representation learning. Furthermore, we design an End-to-end Underwater Prompt Generator (EUPG) for UWSAM, which automatically generates underwater prompts instead of explicitly providing foreground points or boxes as prompts, thus enabling the network to locate underwater instances accurately for efficient segmentation. Comprehensive experimental results show that our model is effective, achieving significant performance improvements over state-of-the-art methods on multiple underwater instance datasets. Datasets and codes are available at https://github.com/LiamLian0727/UIIS10K.
Authors: Niccolo Avogaro, Thomas Frick, Yagmur G. Cinar, Daniel Caraballo, Cezary Skura, Filip M. Janicki, Piotr Kluska, Brown Ebouky, Nicola Farronato, Florian Scheidegger, Cristiano Malossi, Konrad Schindler, Andrea Bartezzaghi, Roy Assaf, Mattia Rigotti
Abstract: Large-scale pretrained vision backbones have transformed computer vision by providing powerful feature extractors that enable various downstream tasks, including training-free approaches like visual prompting for semantic segmentation. Despite their success in generic scenarios, these models often fall short when applied to specialized technical domains where the visual features differ significantly from their training distribution. To bridge this gap, we introduce VP Lab, a comprehensive iterative framework that enhances visual prompting for robust segmentation model development. At the core of VP Lab lies E-PEFT, a novel ensemble of parameter-efficient fine-tuning techniques specifically designed to adapt our visual prompting pipeline to specific domains in a manner that is both parameter- and data-efficient. Our approach not only surpasses the state-of-the-art in parameter-efficient fine-tuning for the Segment Anything Model (SAM), but also facilitates an interactive, near-real-time loop, allowing users to observe progressively improving results as they experiment within the framework. By integrating E-PEFT with visual prompting, we demonstrate a remarkable 50\% increase in semantic segmentation mIoU performance across various technical datasets using only 5 validated images, establishing a new paradigm for fast, efficient, and interactive model deployment in new, challenging domains. This work comes in the form of a demonstration.
Authors: Ruilin Yao, Bo Zhang, Jirui Huang, Xinwei Long, Yifang Zhang, Tianyu Zou, Yufei Wu, Shichao Su, Yifan Xu, Wenxi Zeng, Zhaoyu Yang, Guoyou Li, Shilan Zhang, Zichan Li, Yaxiong Chen, Shengwu Xiong, Peng Xu, Jiajun Zhang, Bowen Zhou, David Clifton, Luc Van Gool
Abstract: Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are usually constructed in the task-oriented manner without guarantee that different task samples come from the same data distribution, thus they often fall short in evaluating the synergistic effects of lower-level perceptual capabilities on higher-order reasoning. To lift this limitation, we contribute Lens, a multi-level benchmark with 3.4K contemporary images and 60K+ human-authored questions covering eight tasks and 12 daily scenarios, forming three progressive task tiers, i.e., perception, understanding, and reasoning. One feature is that each image is equipped with rich annotations for all tasks. Thus, this dataset intrinsically supports to evaluate MLLMs to handle image-invariable prompts, from basic perception to compositional reasoning. In addition, our images are manully collected from the social media, in which 53% were published later than Jan. 2025. We evaluate 15+ frontier MLLMs such as Qwen2.5-VL-72B, InternVL3-78B, GPT-4o and two reasoning models QVQ-72B-preview and Kimi-VL. These models are released later than Dec. 2024, and none of them achieve an accuracy greater than 60% in the reasoning tasks. Project page: https://github.com/Lens4MLLMs/lens. ICCV 2025 workshop page: https://lens4mllms.github.io/mars2-workshop-iccv2025/
URLs: https://github.com/Lens4MLLMs/lens., https://lens4mllms.github.io/mars2-workshop-iccv2025/
Authors: Iuliia Kotseruba, John K. Tsotsos
Abstract: Generalization of deep-learning-based (DL) computer vision algorithms to various image perturbations is hard to establish and remains an active area of research. The majority of past analyses focused on the images already captured, whereas effects of the image formation pipeline and environment are less studied. In this paper, we address this issue by analyzing the impact of capture conditions, such as camera parameters and lighting, on DL model performance on 3 vision tasks -- image classification, object detection, and visual question answering (VQA). To this end, we assess capture bias in common vision datasets and create a new benchmark, SNAP (for $\textbf{S}$hutter speed, ISO se$\textbf{N}$sitivity, and $\textbf{AP}$erture), consisting of images of objects taken under controlled lighting conditions and with densely sampled camera settings. We then evaluate a large number of DL vision models and show the effects of capture conditions on each selected vision task. Lastly, we conduct an experiment to establish a human baseline for the VQA task. Our results show that computer vision datasets are significantly biased, the models trained on this data do not reach human accuracy even on the well-exposed images, and are susceptible to both major exposure changes and minute variations of camera settings. Code and data can be found at https://github.com/ykotseruba/SNAP
Authors: Pujun Xue, Junyi Ge, Xiaotong Jiang, Siyang Song, Zijian Wu, Yupeng Huo, Weicheng Xie, Linlin Shen, Xiaoqin Zhou, Xiaofeng Liu, Min Gu
Abstract: Malocclusion is a major challenge in orthodontics, and its complex presentation and diverse clinical manifestations make accurate localization and diagnosis particularly important. Currently, one of the major shortcomings facing the field of dental image analysis is the lack of large-scale, accurately labeled datasets dedicated to malocclusion issues, which limits the development of automated diagnostics in the field of dentistry and leads to a lack of diagnostic accuracy and efficiency in clinical practice. Therefore, in this study, we propose the Oral and Maxillofacial Natural Images (OMNI) dataset, a novel and comprehensive dental image dataset aimed at advancing the study of analyzing dental images for issues of malocclusion. Specifically, the dataset contains 4166 multi-view images with 384 participants in data collection and annotated by professional dentists. In addition, we performed a comprehensive validation of the created OMNI dataset, including three CNN-based methods, two Transformer-based methods, and one GNN-based method, and conducted automated diagnostic experiments for malocclusion issues. The experimental results show that the OMNI dataset can facilitate the automated diagnosis research of malocclusion issues and provide a new benchmark for the research in this field. Our OMNI dataset and baseline code are publicly available at https://github.com/RoundFaceJ/OMNI.
Authors: Zhen Sun, Ziyi Zhang, Zeren Luo, Zeyang Sha, Tianshuo Cong, Zheng Li, Shiwen Cui, Weiqiang Wang, Jiaheng Wei, Xinlei He, Qi Li, Qian Wang
Abstract: Fine-grained edited image detection of localized edits in images is crucial for assessing content authenticity, especially given that modern diffusion models and image editing methods can produce highly realistic manipulations. However, this domain faces three challenges: (1) Binary classifiers yield only a global real-or-fake label without providing localization; (2) Traditional computer vision methods often rely on costly pixel-level annotations; and (3) No large-scale, high-quality dataset exists for modern image-editing detection techniques. To address these gaps, we develop an automated data-generation pipeline to create FragFake, the first dedicated benchmark dataset for edited image detection, which includes high-quality images from diverse editing models and a wide variety of edited objects. Based on FragFake, we utilize Vision Language Models (VLMs) for the first time in the task of edited image classification and edited region localization. Experimental results show that fine-tuned VLMs achieve higher average Object Precision across all datasets, significantly outperforming pretrained models. We further conduct ablation and transferability analyses to evaluate the detectors across various configurations and editing scenarios. To the best of our knowledge, this work is the first to reformulate localized image edit detection as a vision-language understanding task, establishing a new paradigm for the field. We anticipate that this work will establish a solid foundation to facilitate and inspire subsequent research endeavors in the domain of multimodal content authenticity.
Authors: Tianjiao Cao, Jiahao Lyu, Weichao Zeng, Weimin Mu, Yu Zhou
Abstract: Scene text detection has seen the emergence of high-performing methods that excel on academic benchmarks. However, these detectors often fail to replicate such success in real-world scenarios. We uncover two key factors contributing to this discrepancy through extensive experiments. First, a \textit{Fine-tuning Gap}, where models leverage \textit{Dataset-Specific Optimization} (DSO) paradigm for one domain at the cost of reduced effectiveness in others, leads to inflated performances on academic benchmarks. Second, the suboptimal performance in practical settings is primarily attributed to the long-tailed distribution of texts, where detectors struggle with rare and complex categories as artistic or overlapped text. Given that the DSO paradigm might undermine the generalization ability of models, we advocate for a \textit{Joint-Dataset Learning} (JDL) protocol to alleviate the Fine-tuning Gap. Additionally, an error analysis is conducted to identify three major categories and 13 subcategories of challenges in long-tailed scene text, upon which we propose a Long-Tailed Benchmark (LTB). LTB facilitates a comprehensive evaluation of ability to handle a diverse range of long-tailed challenges. We further introduce MAEDet, a self-supervised learning-based method, as a strong baseline for LTB. The code is available at https://github.com/pd162/LTB.
Authors: Hamzeh Asgharnezhad, Afshar Shamsi, Roohallah Alizadehsani, Arash Mohammadi, Hamid Alinejad-Rokny
Abstract: Knowing the uncertainty associated with the output of a deep neural network is of paramount importance in making trustworthy decisions, particularly in high-stakes fields like medical diagnosis and autonomous systems. Monte Carlo Dropout (MCD) is a widely used method for uncertainty quantification, as it can be easily integrated into various deep architectures. However, conventional MCD often struggles with providing well-calibrated uncertainty estimates. To address this, we introduce innovative frameworks that enhances MCD by integrating different search solutions namely Grey Wolf Optimizer (GWO), Bayesian Optimization (BO), and Particle Swarm Optimization (PSO) as well as an uncertainty-aware loss function, thereby improving the reliability of uncertainty quantification. We conduct comprehensive experiments using different backbones, namely DenseNet121, ResNet50, and VGG16, on various datasets, including Cats vs. Dogs, Myocarditis, Wisconsin, and a synthetic dataset (Circles). Our proposed algorithm outperforms the MCD baseline by 2-3% on average in terms of both conventional accuracy and uncertainty accuracy while achieving significantly better calibration. These results highlight the potential of our approach to enhance the trustworthiness of deep learning models in safety-critical applications.
Authors: Zhe Xu, Cheng Jin, Yihui Wang, Ziyi Liu, Hao Chen
Abstract: Multimodal pathological image understanding has garnered widespread interest due to its potential to improve diagnostic accuracy and enable personalized treatment through integrated visual and textual data. However, existing methods exhibit limited reasoning capabilities, which hamper their ability to handle complex diagnostic scenarios. Additionally, the enormous size of pathological images leads to severe computational burdens, further restricting their practical deployment. To address these limitations, we introduce a novel bilateral reinforcement learning framework comprising two synergistic branches. One reinforcement branch enhances the reasoning capability by enabling the model to learn task-specific decision processes, i.e., pathology rationales, directly from labels without explicit reasoning supervision. While the other branch dynamically allocates a tailored number of tokens to different images based on both their visual content and task context, thereby optimizing computational efficiency. We apply our method to various pathological tasks such as visual question answering, cancer subtyping, and lesion detection. Extensive experiments show an average +41.7 absolute performance improvement with 70.3% lower inference costs over the base models, achieving both reasoning accuracy and computational efficiency.
Authors: Xiaodong Mei, Sheng Wang, Jie Cheng, Yingbing Chen, Dan Xu
Abstract: Motion forecasting represents a critical challenge in autonomous driving systems, requiring accurate prediction of surrounding agents' future trajectories. While existing approaches predict future motion states with the extracted scene context feature from historical agent trajectories and road layouts, they suffer from the information degradation during the scene feature encoding. To address the limitation, we propose HAMF, a novel motion forecasting framework that learns future motion representations with the scene context encoding jointly, to coherently combine the scene understanding and future motion state prediction. We first embed the observed agent states and map information into 1D token sequences, together with the target multi-modal future motion features as a set of learnable tokens. Then we design a unified Attention-based encoder, which synergistically combines self-attention and cross-attention mechanisms to model the scene context information and aggregate future motion features jointly. Complementing the encoder, we implement the Mamba module in the decoding stage to further preserve the consistency and correlations among the learned future motion representations, to generate the accurate and diverse final trajectories. Extensive experiments on Argoverse 2 benchmark demonstrate that our hybrid Attention-Mamba model achieves state-of-the-art motion forecasting performance with the simple and lightweight architecture.
Authors: Zhuodong Jiang, Haoran Wang, Guoxi Huang, Brett Seymour, Nantheera Anantrasirichai
Abstract: Reconstructing high-fidelity underwater scenes remains a challenging task due to light absorption, scattering, and limited visibility inherent in aquatic environments. This paper presents an enhanced Gaussian Splatting-based framework that improves both the visual quality and geometric accuracy of deep underwater rendering. We propose decoupled learning for RGB channels, guided by the physics of underwater attenuation, to enable more accurate colour restoration. To address sparse-view limitations and improve view consistency, we introduce a frame interpolation strategy with a novel adaptive weighting scheme. Additionally, we introduce a new loss function aimed at reducing noise while preserving edges, which is essential for deep-sea content. We also release a newly collected dataset, Submerged3D, captured specifically in deep-sea environments. Experimental results demonstrate that our framework consistently outperforms state-of-the-art methods with PSNR gains up to 1.90dB, delivering superior perceptual quality and robustness, and offering promising directions for marine robotics and underwater visual analytics.
Authors: Weihao Xia, Cengiz Oztireli
Abstract: The intrication of brain signals drives research that leverages multimodal AI to align brain modalities with visual and textual data for explainable descriptions. However, most existing studies are limited to coarse interpretations, lacking essential details on object descriptions, locations, attributes, and their relationships. This leads to imprecise and ambiguous reconstructions when using such cues for visual decoding. To address this, we analyze different choices of vision feature spaces from pre-trained visual components within Multimodal Large Language Models (MLLMs) and introduce a zero-shot multimodal brain decoding method that interacts with these models to decode across multiple levels of granularities. % To assess a model's ability to decode fine details from brain signals, we propose the Multi-Granularity Brain Detail Understanding Benchmark (MG-BrainDub). This benchmark includes two key tasks: detailed descriptions and salient question-answering, with metrics highlighting key visual elements like objects, attributes, and relationships. Our approach enhances neural decoding precision and supports more accurate neuro-decoding applications. Code will be available at https://github.com/weihaox/VINDEX.
Authors: Kaizhi Zheng, Ruijian Zhang, Jing Gu, Jie Yang, Xin Eric Wang
Abstract: Acquiring detailed 3D scenes typically demands costly equipment, multi-view data, or labor-intensive modeling. Therefore, a lightweight alternative, generating complex 3D scenes from a single top-down image, plays an essential role in real-world applications. While recent 3D generative models have achieved remarkable results at the object level, their extension to full-scene generation often leads to inconsistent geometry, layout hallucinations, and low-quality meshes. In this work, we introduce 3DTown, a training-free framework designed to synthesize realistic and coherent 3D scenes from a single top-down view. Our method is grounded in two principles: region-based generation to improve image-to-3D alignment and resolution, and spatial-aware 3D inpainting to ensure global scene coherence and high-quality geometry generation. Specifically, we decompose the input image into overlapping regions and generate each using a pretrained 3D object generator, followed by a masked rectified flow inpainting process that fills in missing geometry while maintaining structural continuity. This modular design allows us to overcome resolution bottlenecks and preserve spatial structure without requiring 3D supervision or fine-tuning. Extensive experiments across diverse scenes show that 3DTown outperforms state-of-the-art baselines, including Trellis, Hunyuan3D-2, and TripoSG, in terms of geometry quality, spatial coherence, and texture fidelity. Our results demonstrate that high-quality 3D town generation is achievable from a single image using a principled, training-free approach.
Authors: Chuanhao Li, Jianwen Sun, Yukang Feng, Mingliang Zhai, Yifan Chang, Kaipeng Zhang
Abstract: Current text-to-image (T2I) generation models achieve promising results, but they fail on the scenarios where the knowledge implied in the text prompt is uncertain. For example, a T2I model released in February would struggle to generate a suitable poster for a movie premiering in April, because the character designs and styles are uncertain to the model. To solve this problem, we propose an Internet-Augmented text-to-image generation (IA-T2I) framework to compel T2I models clear about such uncertain knowledge by providing them with reference images. Specifically, an active retrieval module is designed to determine whether a reference image is needed based on the given text prompt; a hierarchical image selection module is introduced to find the most suitable image returned by an image search engine to enhance the T2I model; a self-reflection mechanism is presented to continuously evaluate and refine the generated image to ensure faithful alignment with the text prompt. To evaluate the proposed framework's performance, we collect a dataset named Img-Ref-T2I, where text prompts include three types of uncertain knowledge: (1) known but rare. (2) unknown. (3) ambiguous. Moreover, we carefully craft a complex prompt to guide GPT-4o in making preference evaluation, which has been shown to have an evaluation accuracy similar to that of human preference evaluation. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4o by about 30% in human evaluation.
Authors: Fengyuan Dai, Zifeng Zhuang, Yufei Huang, Siteng Huang, Bangyan Liao, Donglin Wang, Fajie Yuan
Abstract: Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. While reinforcement learning (RL) offers a promising solution,current methods struggle to simultaneously achieve stable, efficient fine-tuning and support non-differentiable rewards. Furthermore, their reliance on sparse rewards provides inadequate supervision during intermediate steps, often resulting in suboptimal generation quality. To address these limitations, dense and differentiable signals are required throughout the diffusion process. Hence, we propose VAlue-based Reinforced Diffusion (VARD): a novel approach that first learns a value function predicting expection of rewards from intermediate states, and subsequently uses this value function with KL regularization to provide dense supervision throughout the generation process. Our method maintains proximity to the pretrained model while enabling effective and stable training via backpropagation. Experimental results demonstrate that our approach facilitates better trajectory guidance, improves training efficiency and extends the applicability of RL to diffusion models optimized for complex, non-differentiable reward functions.
Authors: Ruizhi Shao, Yinghao Xu, Yujun Shen, Ceyuan Yang, Yang Zheng, Changan Chen, Yebin Liu, Gordon Wetzstein
Abstract: Generating photorealistic videos of digital humans in a controllable manner is crucial for a plethora of applications. Existing approaches either build on methods that employ template-based 3D representations or emerging video generation models but suffer from poor quality or limited consistency and identity preservation when generating individual or multiple digital humans. In this paper, we introduce a new interspatial attention (ISA) mechanism as a scalable building block for modern diffusion transformer (DiT)--based video generation models. ISA is a new type of cross attention that uses relative positional encodings tailored for the generation of human videos. Leveraging a custom-developed video variation autoencoder, we train a latent ISA-based diffusion model on a large corpus of video data. Our model achieves state-of-the-art performance for 4D human video synthesis, demonstrating remarkable motion consistency and identity preservation while providing precise control of the camera and body poses. Our code and model are publicly released at https://dsaurus.github.io/isa4d/.
Authors: Zongzhao Li, Zongyang Ma, Mingze Li, Songyou Li, Yu Rong, Tingyang Xu, Ziqi Zhang, Deli Zhao, Wenbing Huang
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning. We investigate this gap through Transformation-Driven Visual Reasoning (TVR), a challenging task requiring identification of object transformations across images under varying viewpoints. While traditional Supervised Fine-Tuning (SFT) fails to generate coherent reasoning paths in cross-view settings, sparse-reward Reinforcement Learning (RL) suffers from inefficient exploration and slow convergence. To address these limitations, we propose STAR-R1, a novel framework that integrates a single-stage RL paradigm with a fine-grained reward mechanism tailored for TVR. Specifically, STAR-R1 rewards partial correctness while penalizing excessive enumeration and passive inaction, enabling efficient exploration and precise reasoning. Comprehensive evaluations demonstrate that STAR-R1 achieves state-of-the-art performance across all 11 metrics, outperforming SFT by 23% in cross-view scenarios. Further analysis reveals STAR-R1's anthropomorphic behavior and highlights its unique ability to compare all objects for improving spatial reasoning. Our work provides critical insights in advancing the research of MLLMs and reasoning models. The codes, model weights, and data will be publicly available at https://github.com/zongzhao23/STAR-R1.
Authors: Ling Yang, Ye Tian, Bowen Li, Xinchen Zhang, Ke Shen, Yunhai Tong, Mengdi Wang
Abstract: We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal understanding, and text-to-image generation. The approach is distinguished by three key innovations: (i) MMaDA adopts a unified diffusion architecture with a shared probabilistic formulation and a modality-agnostic design, eliminating the need for modality-specific components. This architecture ensures seamless integration and processing across different data types. (ii) We implement a mixed long chain-of-thought (CoT) fine-tuning strategy that curates a unified CoT format across modalities. By aligning reasoning processes between textual and visual domains, this strategy facilitates cold-start training for the final reinforcement learning (RL) stage, thereby enhancing the model's ability to handle complex tasks from the outset. (iii) We propose UniGRPO, a unified policy-gradient-based RL algorithm specifically tailored for diffusion foundation models. Utilizing diversified reward modeling, UniGRPO unifies post-training across both reasoning and generation tasks, ensuring consistent performance improvements. Experimental results demonstrate that MMaDA-8B exhibits strong generalization capabilities as a unified multimodal foundation model. It surpasses powerful models like LLaMA-3-7B and Qwen2-7B in textual reasoning, outperforms Show-o and SEED-X in multimodal understanding, and excels over SDXL and Janus in text-to-image generation. These achievements highlight MMaDA's effectiveness in bridging the gap between pretraining and post-training within unified diffusion architectures, providing a comprehensive framework for future research and development. We open-source our code and trained models at: https://github.com/Gen-Verse/MMaDA
Authors: Satoshi Kosugi
Abstract: Exemplar-based image colorization aims to colorize a grayscale image using a reference color image, ensuring that reference colors are applied to corresponding input regions based on their semantic similarity. To achieve accurate semantic matching between regions, we leverage the self-attention module of a pre-trained diffusion model, which is trained on a large dataset and exhibits powerful attention capabilities. To harness this power, we propose a novel, fine-tuning-free approach based on a pre-trained diffusion model, making two key contributions. First, we introduce dual attention-guided color transfer. We utilize the self-attention module to compute an attention map between the input and reference images, effectively capturing semantic correspondences. The color features from the reference image is then transferred to the semantically matching regions of the input image, guided by this attention map, and finally, the grayscale features are replaced with the corresponding color features. Notably, we utilize dual attention to calculate attention maps separately for the grayscale and color images, achieving more precise semantic alignment. Second, we propose classifier-free colorization guidance, which enhances the transferred colors by combining color-transferred and non-color-transferred outputs. This process improves the quality of colorization. Our experimental results demonstrate that our method outperforms existing techniques in terms of image quality and fidelity to the reference. Specifically, we use 335 input-reference pairs from previous research, achieving an FID of 95.27 (image quality) and an SI-FID of 5.51 (fidelity to the reference). Our source code is available at https://github.com/satoshi-kosugi/powerful-attention.
Authors: Federica Arrigoni
Abstract: Structure from Motion (SfM) refers to the problem of recovering both structure (i.e., 3D coordinates of points in the scene) and motion (i.e., camera matrices) starting from point correspondences in multiple images. It has attracted significant attention over the years, counting practical reconstruction pipelines as well as theoretical results. This paper is conceived as a conceptual review of SfM methods, which are grouped into three main categories, according to which part of the problem - between motion and structure - they focus on. The proposed taxonomy brings a new perspective on existing SfM approaches as well as insights into open problems and possible future research directions. Particular emphasis is given on identifying the theoretical conditions that make SfM well posed, which depend on the problem formulation that is being considered.
Authors: Penghao Wu, Lewei Lu, Ziwei Liu
Abstract: Large multimodal models excel in multimodal tasks but face significant computational challenges due to excessive computation on visual tokens. Unlike token reduction methods that focus on token-level redundancy, we identify and study the computation-level redundancy on vision tokens to ensure no information loss. Our key insight is that vision tokens from the pretrained vision encoder do not necessarily require all the heavy operations (e.g., self-attention, FFNs) in decoder-only LMMs and could be processed more lightly with proper designs. We designed a series of experiments to discover and progressively squeeze out the vision-related computation redundancy. Based on our findings, we propose ProxyV, a novel approach that utilizes proxy vision tokens to alleviate the computational burden on original vision tokens. ProxyV enhances efficiency without compromising performance and can even yield notable performance gains in scenarios with more moderate efficiency improvements. Furthermore, the flexibility of ProxyV is demonstrated through its combination with token reduction methods to boost efficiency further. The code will be made public at this https://github.com/penghao-wu/ProxyV URL.
Authors: Yijie Zheng, Weijie Wu, Qingyun Li, Xuehui Wang, Xu Zhou, Aiai Ren, Jun Shen, Long Zhao, Guoqing Li, Xue Yang
Abstract: Language-Guided object recognition in remote sensing imagery is crucial for large-scale mapping and automated data annotation. However, existing open-vocabulary and visual grounding methods rely on explicit category cues, limiting their ability to handle complex or implicit queries that require advanced reasoning. To address this issue, we introduce a new suite of tasks, including Instruction-Oriented Object Counting, Detection, and Segmentation (InstructCDS), covering open-vocabulary, open-ended, and open-subclass scenarios. We further present EarthInstruct, the first InstructCDS benchmark for earth observation. It is constructed from two diverse remote sensing datasets with varying spatial resolutions and annotation rules across 20 categories, necessitating models to interpret dataset-specific instructions. Given the scarcity of semantically rich labeled data in remote sensing, we propose InstructSAM, a training-free framework for instruction-driven object recognition. InstructSAM leverages large vision-language models to interpret user instructions and estimate object counts, employs SAM2 for mask proposal, and formulates mask-label assignment as a binary integer programming problem. By integrating semantic similarity with counting constraints, InstructSAM efficiently assigns categories to predicted masks without relying on confidence thresholds. Experiments demonstrate that InstructSAM matches or surpasses specialized baselines across multiple tasks while maintaining near-constant inference time regardless of object count, reducing output tokens by 89% and overall runtime by over 32% compared to direct generation approaches. We believe the contributions of the proposed tasks, benchmark, and effective approach will advance future research in developing versatile object recognition systems.
Authors: Muhammad Zubair, Muzammil Hussai, Mousa Ahmad Al-Bashrawi, Malika Bendechache, Muhammad Owais
Abstract: Multi-modal medical image fusion (MMIF) is increasingly recognized as an essential technique for enhancing diagnostic precision and facilitating effective clinical decision-making within computer-aided diagnosis systems. MMIF combines data from X-ray, MRI, CT, PET, SPECT, and ultrasound to create detailed, clinically useful images of patient anatomy and pathology. These integrated representations significantly advance diagnostic accuracy, lesion detection, and segmentation. This comprehensive review meticulously surveys the evolution, methodologies, algorithms, current advancements, and clinical applications of MMIF. We present a critical comparative analysis of traditional fusion approaches, including pixel-, feature-, and decision-level methods, and delves into recent advancements driven by deep learning, generative models, and transformer-based architectures. A critical comparative analysis is presented between these conventional methods and contemporary techniques, highlighting differences in robustness, computational efficiency, and interpretability. The article addresses extensive clinical applications across oncology, neurology, and cardiology, demonstrating MMIF's vital role in precision medicine through improved patient-specific therapeutic outcomes. Moreover, the review thoroughly investigates the persistent challenges affecting MMIF's broad adoption, including issues related to data privacy, heterogeneity, computational complexity, interpretability of AI-driven algorithms, and integration within clinical workflows. It also identifies significant future research avenues, such as the integration of explainable AI, adoption of privacy-preserving federated learning frameworks, development of real-time fusion systems, and standardization efforts for regulatory compliance.
Authors: Sahil Tomar, Rajeshwar Tripathi, Sandeep Kumar
Abstract: Bone fractures are a leading cause of morbidity and disability worldwide, imposing significant clinical and economic burdens on healthcare systems. Traditional X ray interpretation is time consuming and error prone, while existing machine learning and deep learning solutions often demand extensive feature engineering, large, annotated datasets, and high computational resources. To address these challenges, a distributed hybrid quantum classical pipeline is proposed that first applies Principal Component Analysis (PCA) for dimensionality reduction and then leverages a 4 qubit quantum amplitude encoding circuit for feature enrichment. By fusing eight PCA derived features with eight quantum enhanced features into a 16 dimensional vector and then classifying with different machine learning models achieving 99% accuracy using a public multi region X ray dataset on par with state of the art transfer learning models while reducing feature extraction time by 82%.
Authors: Xigui Li, Yuanye Zhou, Feiyang Xiao, Xin Guo, Chen Jiang, Tan Pan, Xingmeng Zhang, Cenyu Liu, Zeyun Miao, Jianchao Ge, Xiansheng Wang, Qimeng Wang, Yichi Zhang, Wenbo Zhang, Fengping Zhu, Limei Han, Yuan Qi, Chensen Lin, Yuan Cheng
Abstract: Intracranial aneurysms (IAs) are serious cerebrovascular lesions found in approximately 5\% of the general population. Their rupture may lead to high mortality. Current methods for assessing IA risk focus on morphological and patient-specific factors, but the hemodynamic influences on IA development and rupture remain unclear. While accurate for hemodynamic studies, conventional computational fluid dynamics (CFD) methods are computationally intensive, hindering their deployment in large-scale or real-time clinical applications. To address this challenge, we curated a large-scale, high-fidelity aneurysm CFD dataset to facilitate the development of efficient machine learning algorithms for such applications. Based on 427 real aneurysm geometries, we synthesized 10,660 3D shapes via controlled deformation to simulate aneurysm evolution. The authenticity of these synthetic shapes was confirmed by neurosurgeons. CFD computations were performed on each shape under eight steady-state mass flow conditions, generating a total of 85,280 blood flow dynamics data covering key parameters. Furthermore, the dataset includes segmentation masks, which can support tasks that use images, point clouds or other multimodal data as input. Additionally, we introduced a benchmark for estimating flow parameters to assess current modeling methods. This dataset aims to advance aneurysm research and promote data-driven approaches in biofluids, biomedical engineering, and clinical risk assessment. The code and dataset are available at: https://github.com/Xigui-Li/Aneumo.
Authors: Pierre-Marc Jodoin, Manon Edde, Gabriel Girard, F\'elix Dumais, Guillaume Theaud, Matthieu Dumont, Jean-Christophe Houde, Yoan David, Maxime Descoteaux
Abstract: Over the years, ComBAT has become the standard method for harmonizing MRI-derived measurements, with its ability to compensate for site-related additive and multiplicative biases while preserving biological variability. However, ComBAT relies on a set of assumptions that, when violated, can result in flawed harmonization. In this paper, we thoroughly review ComBAT's mathematical foundation, outlining these assumptions, and exploring their implications for the demographic composition necessary for optimal results. Through a series of experiments involving a slightly modified version of ComBAT called Pairwise-ComBAT tailored for normative modeling applications, we assess the impact of various population characteristics, including population size, age distribution, the absence of certain covariates, and the magnitude of additive and multiplicative factors. Based on these experiments, we present five essential recommendations that should be carefully considered to enhance consistency and supporting reproducibility, two essential factors for open science, collaborative research, and real-life clinical deployment.
Authors: Manshi Limbu, Diwita Banerjee
Abstract: Medical image captioning is a challenging task that requires generating clinically accurate and semantically meaningful descriptions of radiology images. While recent vision-language models (VLMs) such as BLIP, BLIP2, Gemini and ViT-GPT2 show strong performance on natural image datasets, they often produce generic or imprecise captions when applied to specialized medical domains. In this project, we explore the effectiveness of fine-tuning the BLIP model on the ROCO dataset for improved radiology captioning. We compare the fine-tuned BLIP against its zero-shot version, BLIP-2 base, BLIP-2 Instruct and a ViT-GPT2 transformer baseline. Our results demonstrate that domain-specific fine-tuning on BLIP significantly improves performance across both quantitative and qualitative evaluation metrics. We also visualize decoder cross-attention maps to assess interpretability and conduct an ablation study to evaluate the contributions of encoder-only and decoder-only fine-tuning. Our findings highlight the importance of targeted adaptation for medical applications and suggest that decoder-only fine-tuning (encoder-frozen) offers a strong performance baseline with 5% lower training time than full fine-tuning, while full model fine-tuning still yields the best results overall.
Authors: Hikmat Khan, Ziyu Su, Huina Zhang, Yihong Wang, Bohan Ning, Shi Wei, Hua Guo, Zaibo Li, Muhammad Khalid Khan Niazi
Abstract: Triple-negative breast cancer (TNBC) is an aggressive subtype defined by the lack of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) expression, resulting in limited targeted treatment options. Neoadjuvant chemotherapy (NACT) is the standard treatment for early-stage TNBC, with pathologic complete response (pCR) serving as a key prognostic marker; however, only 40-50% of patients with TNBC achieve pCR. Accurate prediction of NACT response is crucial to optimize therapy, avoid ineffective treatments, and improve patient outcomes. In this study, we developed a deep learning model to predict NACT response using pre-treatment hematoxylin and eosin (H&E)-stained biopsy images. Our model achieved promising results in five-fold cross-validation (accuracy: 82%, AUC: 0.86, F1-score: 0.84, sensitivity: 0.85, specificity: 0.81, precision: 0.80). Analysis of model attention maps in conjunction with multiplexed immunohistochemistry (mIHC) data revealed that regions of high predictive importance consistently colocalized with tumor areas showing elevated PD-L1 expression, CD8+ T-cell infiltration, and CD163+ macrophage density - all established biomarkers of treatment response. Our findings indicate that incorporating IHC-derived immune profiling data could substantially improve model interpretability and predictive performance. Furthermore, this approach may accelerate the discovery of novel histopathological biomarkers for NACT and advance the development of personalized treatment strategies for TNBC patients.
Authors: Fatemeh Chajaei, Hossein Bagheri
Abstract: Three-dimensional reconstruction of buildings, particularly at Level of Detail 1 (LOD1), plays a crucial role in various applications such as urban planning, urban environmental studies, and designing optimized transportation networks. This study focuses on assessing the potential of LiDAR data for accurate 3D building reconstruction at LOD1 and extracting morphological features from these models. Four deep semantic segmentation models, U-Net, Attention U-Net, U-Net3+, and DeepLabV3+, were used, applying transfer learning to extract building footprints from LiDAR data. The results showed that U-Net3+ and Attention U-Net outperformed the others, achieving IoU scores of 0.833 and 0.814, respectively. Various statistical measures, including maximum, range, mode, median, and the 90th percentile, were used to estimate building heights, resulting in the generation of 3D models at LOD1. As the main contribution of the research, the impact of segmentation accuracy on the quality of 3D building modeling and the accuracy of morphological features like building area and external wall surface area was investigated. The results showed that the accuracy of building identification (segmentation performance) significantly affects the 3D model quality and the estimation of morphological features, depending on the height calculation method. Overall, the UNet3+ method, utilizing the 90th percentile and median measures, leads to accurate height estimation of buildings and the extraction of morphological features.
Authors: Mengzhu Wang, Jiao Li, Shanshan Wang, Long Lan, Huibin Tan, Liang Yang, Guoli Yang
Abstract: Semi-supervised learning (SSL) has achieved significant progress in medical image segmentation (SSMIS) through effective utilization of limited labeled data. While current SSL methods for medical images predominantly rely on consistency regularization and pseudo-labeling, they often overlook transferable semantic relationships across different clinical domains and imaging modalities. To address this, we propose TransMedSeg, a novel transferable semantic framework for semi-supervised medical image segmentation. Our approach introduces a Transferable Semantic Augmentation (TSA) module, which implicitly enhances feature representations by aligning domain-invariant semantics through cross-domain distribution matching and intra-domain structural preservation. Specifically, TransMedSeg constructs a unified feature space where teacher network features are adaptively augmented towards student network semantics via a lightweight memory module, enabling implicit semantic transformation without explicit data generation. Interestingly, this augmentation is implicitly realized through an expected transferable cross-entropy loss computed over the augmented teacher distribution. An upper bound of the expected loss is theoretically derived and minimized during training, incurring negligible computational overhead. Extensive experiments on medical image datasets demonstrate that TransMedSeg outperforms existing semi-supervised methods, establishing a new direction for transferable representation learning in medical image analysis.
Authors: Andrey Alexandrov, Giovanni Acampora, Giovanni De Lellis, Antonia Di Crescenzo, Chiara Errico, Daria Morozova, Valeri Tioukov, Autilia Vittiello
Abstract: Accurately tracking particles and determining their position along the optical axis is a major challenge in optical microscopy, especially when extremely high precision is needed. In this study, we introduce a deep learning approach using convolutional neural networks (CNNs) that can determine axial positions from dual-focal plane images without relying on predefined models. Our method achieves an axial localization accuracy of 40 nanometers - six times better than traditional single-focal plane techniques. The model's simple design and strong performance make it suitable for a wide range of uses, including dark matter detection, proton therapy for cancer, and radiation protection in space. It also shows promise in fields like biological imaging, materials science, and environmental monitoring. This work highlights how machine learning can turn complex image data into reliable, precise information, offering a flexible and powerful tool for many scientific applications.
Authors: Nisarga Nilavadi, Andrey Rudenko, Timm Linder
Abstract: We introduce a unified approach to forecast the dynamics of human keypoints along with the motion trajectory based on a short sequence of input poses. While many studies address either full-body pose prediction or motion trajectory prediction, only a few attempt to merge them. We propose a motion transformation technique to simultaneously predict full-body pose and trajectory key-points in a global coordinate frame. We utilize an off-the-shelf 3D human pose estimation module, a graph attention network to encode the skeleton structure, and a compact, non-autoregressive transformer suitable for real-time motion prediction for human-robot interaction and human-aware navigation. We introduce a human navigation dataset ``DARKO'' with specific focus on navigational activities that are relevant for human-aware mobile robot navigation. We perform extensive evaluation on Human3.6M, CMU-Mocap, and our DARKO dataset. In comparison to prior work, we show that our approach is compact, real-time, and accurate in predicting human navigation motion across all datasets. Result animations, our dataset, and code will be available at https://nisarganc.github.io/UPTor-page/
Authors: Yaning Wang, Jinglun Yu, Wenhan Guo, Yu Sun, Jin U. Kang
Abstract: We propose an OCT super-resolution framework based on a plug-and-play diffusion model (PnP-DM) to reconstruct high-quality images from sparse measurements (OCT B-mode corneal images). Our method formulates reconstruction as an inverse problem, combining a diffusion prior with Markov chain Monte Carlo sampling for efficient posterior inference. We collect high-speed under-sampled B-mode corneal images and apply a deep learning-based up-sampling pipeline to build realistic training pairs. Evaluations on in vivo and ex vivo fish-eye corneal models show that PnP-DM outperforms conventional 2D-UNet baselines, producing sharper structures and better noise suppression. This approach advances high-fidelity OCT imaging in high-speed acquisition for clinical applications.
Authors: Mohammad R. Salmanpour, Seyed Mohammad Piri, Somayeh Sadat Mehrnia, Ahmad Shariftabrizi, Masume Allahmoradi, Venkata SK. Manem, Arman Rahmim, Ilker Hacihaliloglu
Abstract: Artificial intelligence (AI) holds strong potential for medical diagnostics, yet its clinical adoption is limited by a lack of interpretability and generalizability. This study introduces the Pathobiological Dictionary for Liver Cancer (LCP1.0), a practical framework designed to translate complex Pathomics and Radiomics Features (PF and RF) into clinically meaningful insights aligned with existing diagnostic workflows. QuPath and PyRadiomics, standardized according to IBSI guidelines, were used to extract 333 imaging features from hepatocellular carcinoma (HCC) tissue samples, including 240 PF-based-cell detection/intensity, 74 RF-based texture, and 19 RF-based first-order features. Expert-defined ROIs from the public dataset excluded artifact-prone areas, and features were aggregated at the case level. Their relevance to the WHO grading system was assessed using multiple classifiers linked with feature selectors. The resulting dictionary was validated by 8 experts in oncology and pathology. In collaboration with 10 domain experts, we developed a Pathobiological dictionary of imaging features such as PFs and RF. In our study, the Variable Threshold feature selection algorithm combined with the SVM model achieved the highest accuracy (0.80, P-value less than 0.05), selecting 20 key features, primarily clinical and pathomics traits such as Centroid, Cell Nucleus, and Cytoplasmic characteristics. These features, particularly nuclear and cytoplasmic, were strongly associated with tumor grading and prognosis, reflecting atypia indicators like pleomorphism, hyperchromasia, and cellular orientation.The LCP1.0 provides a clinically validated bridge between AI outputs and expert interpretation, enhancing model transparency and usability. Aligning AI-derived features with clinical semantics supports the development of interpretable, trustworthy diagnostic tools for liver cancer pathology.
Authors: Frederic Wang, Jonathan I. Tamir
Abstract: Magnetic Resonance Imaging (MRI) is highly susceptible to motion artifacts due to the extended acquisition times required for k-space sampling. These artifacts can compromise diagnostic utility, particularly for dynamic imaging. We propose a novel alternating minimization framework that leverages a bespoke diffusion model to jointly reconstruct and correct non-rigid motion-corrupted k-space data. The diffusion model uses a coarse-to-fine denoising strategy to capture large overall motion and reconstruct the lower frequencies of the image first, providing a better inductive bias for motion estimation than that of standard diffusion models. We demonstrate the performance of our approach on both real-world cine cardiac MRI datasets and complex simulated rigid and non-rigid deformations, even when each motion state is undersampled by a factor of 64x. Additionally, our method is agnostic to sampling patterns, anatomical variations, and MRI scanning protocols, as long as some low frequency components are sampled during each motion state.
Authors: Tianbao Zhang, Jian Zhao, Yuer Li, Zheng Zhu, Ping Hu, Zhaoxin Fan, Wenjun Wu, Xuelong Li
Abstract: Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans and enhancing the capabilities of interactive virtual agents, with wide-ranging applications in virtual reality, digital entertainment, and remote communication. Existing approaches often generate audio-driven facial expressions and gestures independently, which introduces a significant limitation: the lack of seamless coordination between facial and gestural elements, resulting in less natural and cohesive animations. To address this limitation, we propose AsynFusion, a novel framework that leverages diffusion transformers to achieve harmonious expression and gesture synthesis. The proposed method is built upon a dual-branch DiT architecture, which enables the parallel generation of facial expressions and gestures. Within the model, we introduce a Cooperative Synchronization Module to facilitate bidirectional feature interaction between the two modalities, and an Asynchronous LCM Sampling strategy to reduce computational overhead while maintaining high-quality outputs. Extensive experiments demonstrate that AsynFusion achieves state-of-the-art performance in generating real-time, synchronized whole-body animations, consistently outperforming existing methods in both quantitative and qualitative evaluations.
Authors: Hao Wang, Pinzhi Huang, Jihan Yang, Saining Xie, Daisuke Kawahara
Abstract: The rapid evolution of multimodal large language models (MLLMs) has significantly enhanced their real-world applications. However, achieving consistent performance across languages, especially when integrating cultural knowledge, remains a significant challenge. To better assess this issue, we introduce two new benchmarks: KnowRecall and VisRecall, which evaluate cross-lingual consistency in MLLMs. KnowRecall is a visual question answering benchmark designed to measure factual knowledge consistency in 15 languages, focusing on cultural and historical questions about global landmarks. VisRecall assesses visual memory consistency by asking models to describe landmark appearances in 9 languages without access to images. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, still struggle to achieve cross-lingual consistency. This underscores the need for more robust approaches that produce truly multilingual and culturally aware models.
Authors: Muniba Noreen (Faculty of Electrical,Electronics Engineering, University of Engineering,Technology Taxila, Pakistan), Furqan Shaukat (Faculty of Electrical,Electronics Engineering, University of Engineering,Technology Taxila, Pakistan)
Abstract: Lung cancer remains among the deadliest types of cancer in recent decades, and early lung nodule detection is crucial for improving patient outcomes. The limited availability of annotated medical imaging data remains a bottleneck in developing accurate computer-aided diagnosis (CAD) systems. Self-supervised learning can help leverage large amounts of unlabeled data to develop more robust CAD systems. With the recent advent of transformer-based architecture and their ability to generalize to unseen tasks, there has been an effort within the healthcare community to adapt them to various medical downstream tasks. Thus, we propose a novel "LungNodule-SSM" method, which utilizes selfsupervised learning with DINOv2 as a backbone to enhance lung nodule detection and classification without annotated data. Our methodology has two stages: firstly, the DINOv2 model is pre-trained on unlabeled CT scans to learn robust feature representations, then secondly, these features are fine-tuned using transformer-based architectures for lesionlevel detection and accurate lung nodule diagnosis. The proposed method has been evaluated on the challenging LUNA 16 dataset, consisting of 888 CT scans, and compared with SOTA methods. Our experimental results show the superiority of our proposed method with an accuracy of 98.37%, explaining its effectiveness in lung nodule detection. The source code, datasets, and pre-processed data can be accessed using the link:https://github.com/EMeRALDsNRPU/Lung-Nodule-SSM-Self-Supervised-Lung-Nodule-Detection-and-Classification/tree/main
Authors: Badhan Mazumder, Ayush Kanyal, Lei Wu, Vince D. Calhoun, Dong Hye Ye
Abstract: Clinical studies reveal disruptions in brain structural connectivity (SC) and functional connectivity (FC) in neuropsychiatric disorders such as schizophrenia (SZ). Traditional approaches might rely solely on SC due to limited functional data availability, hindering comprehension of cognitive and behavioral impairments in individuals with SZ by neglecting the intricate SC-FC interrelationship. To tackle the challenge, we propose a novel physics-guided deep learning framework that leverages a neural oscillation model to describe the dynamics of a collection of interconnected neural oscillators, which operate via nerve fibers dispersed across the brain's structure. Our proposed framework utilizes SC to simultaneously generate FC by learning SC-FC coupling from a system dynamics perspective. Additionally, it employs a novel multi-view graph neural network (GNN) with a joint loss to perform correlation-based SC-FC fusion and classification of individuals with SZ. Experiments conducted on a clinical dataset exhibited improved performance, demonstrating the robustness of our proposed approach.
Authors: Saqib Qamar, Mohd Fazil, Parvez Ahmad, Ghulam Muhammad
Abstract: Medical image segmentation plays an important role in various clinical applications, but existing models often struggle with the computational inefficiencies and challenges posed by complex medical data. State Space Sequence Models (SSMs) have demonstrated promise in modeling long-range dependencies with linear computational complexity, yet their application in medical image segmentation remains hindered by incompatibilities with image tokens and autoregressive assumptions. Moreover, it is difficult to achieve a balance in capturing both local fine-grained information and global semantic dependencies. To address these challenges, we introduce SAMA-UNet, a novel architecture for medical image segmentation. A key innovation is the Self-Adaptive Mamba-like Aggregated Attention (SAMA) block, which integrates contextual self-attention with dynamic weight modulation to prioritise the most relevant features based on local and global contexts. This approach reduces computational complexity and improves the representation of complex image features across multiple scales. We also suggest the Causal-Resonance Multi-Scale Module (CR-MSM), which enhances the flow of information between the encoder and decoder by using causal resonance learning. This mechanism allows the model to automatically adjust feature resolution and causal dependencies across scales, leading to better semantic alignment between the low-level and high-level features in U-shaped architectures. Experiments on MRI, CT, and endoscopy images show that SAMA-UNet performs better in segmentation accuracy than current methods using CNN, Transformer, and Mamba. The implementation is publicly available at GitHub.
Authors: Yifan Liu, Wuyang Li, Weihao Yu, Chenxin Li, Alexandre Alahi, Max Meng, Yixuan Yuan
Abstract: Computed Tomography serves as an indispensable tool in clinical workflows, providing non-invasive visualization of internal anatomical structures. Existing CT reconstruction works are limited to small-capacity model architecture, inflexible volume representation, and small-scale training data. In this paper, we present X-GRM (X-ray Gaussian Reconstruction Model), a large feedforward model for reconstructing 3D CT from sparse-view 2D X-ray projections. X-GRM employs a scalable transformer-based architecture to encode an arbitrary number of sparse X-ray inputs, where tokens from different views are integrated efficiently. Then, tokens are decoded into a new volume representation, named Voxel-based Gaussian Splatting (VoxGS), which enables efficient CT volume extraction and differentiable X-ray rendering. To support the training of X-GRM, we collect ReconX-15K, a large-scale CT reconstruction dataset containing around 15,000 CT/X-ray pairs across diverse organs, including the chest, abdomen, pelvis, and tooth etc. This combination of a high-capacity model, flexible volume representation, and large-scale training data empowers our model to produce high-quality reconstructions from various testing inputs, including in-domain and out-domain X-ray projections. Project Page: https://github.com/CUHK-AIM-Group/X-GRM.
Authors: Yerin Hwang, Dongryeol Lee, Kyungmin Min, Taegwan Kang, Yong-il Kim, Kyomin Jung
Abstract: Recently, large vision-language models (LVLMs) have emerged as the preferred tools for judging text-image alignment, yet their robustness along the visual modality remains underexplored. This work is the first study to address a key research question: Can adversarial visual manipulations systematically fool LVLM judges into assigning unfairly inflated scores? We define potential image induced biases within the context of T2I evaluation and examine how these biases affect the evaluations of LVLM judges. Moreover, we introduce a novel, fine-grained, multi-domain meta-evaluation benchmark named FRAME, which is deliberately constructed to exhibit diverse score distributions. By introducing the defined biases into the benchmark, we reveal that all tested LVLM judges exhibit vulnerability across all domains, consistently inflating scores for manipulated images. Further analysis reveals that combining multiple biases amplifies their effects, and pairwise evaluations are similarly susceptible. Moreover, we observe that visual biases persist under prompt-based mitigation strategies, highlighting the vulnerability of current LVLM evaluation systems and underscoring the urgent need for more robust LVLM judges.
Authors: Chenyu Zheng, Xinyu Zhang, Rongzhen Wang, Wei Huang, Zhi Tian, Weilin Huang, Jun Zhu, Chongxuan Li
Abstract: Diffusion Transformers have emerged as the foundation for vision generative models, but their scalability is limited by the high cost of hyperparameter (HP) tuning at large scales. Recently, Maximal Update Parametrization ($\mu$P) was proposed for vanilla Transformers, which enables stable HP transfer from small to large language models, and dramatically reduces tuning costs. However, it remains unclear whether $\mu$P of vanilla Transformers extends to diffusion Transformers, which differ architecturally and objectively. In this work, we generalize standard $\mu$P to diffusion Transformers and validate its effectiveness through large-scale experiments. First, we rigorously prove that $\mu$P of mainstream diffusion Transformers, including DiT, U-ViT, PixArt-$\alpha$, and MMDiT, aligns with that of the vanilla Transformer, enabling the direct application of existing $\mu$P methodologies. Leveraging this result, we systematically demonstrate that DiT-$\mu$P enjoys robust HP transferability. Notably, DiT-XL-2-$\mu$P with transferred learning rate achieves 2.9 times faster convergence than the original DiT-XL-2. Finally, we validate the effectiveness of $\mu$P on text-to-image generation by scaling PixArt-$\alpha$ from 0.04B to 0.61B and MMDiT from 0.18B to 18B. In both cases, models under $\mu$P outperform their respective baselines while requiring small tuning cost, only 5.5% of one training run for PixArt-$\alpha$ and 3% of consumption by human experts for MMDiT-18B. These results establish $\mu$P as a principled and efficient framework for scaling diffusion Transformers.
Authors: Yanzhi Tian, Zeming Liu, Zhengyang Liu, Yuhang Guo
Abstract: In-Image Machine Translation (IIMT) aims to translate texts within images from one language to another. Previous research on IIMT was primarily conducted on simplified scenarios such as images of one-line text with black font in white backgrounds, which is far from reality and impractical for applications in the real world. To make IIMT research practically valuable, it is essential to consider a complex scenario where the text backgrounds are derived from real-world images. To facilitate research of complex scenario IIMT, we design an IIMT dataset that includes subtitle text with real-world background. However previous IIMT models perform inadequately in complex scenarios. To address the issue, we propose the DebackX model, which separates the background and text-image from the source image, performs translation on text-image directly, and fuses the translated text-image with the background, to generate the target image. Experimental results show that our model achieves improvements in both translation quality and visual effect.
Authors: Kun Fang, Qinghua Tao, Mingzhen He, Kexin Lv, Runze Yang, Haibo Hu, Xiaolin Huang, Jie Yang, Longbin Cao
Abstract: Out-of-Distribution (OoD) detection is vital for the reliability of deep neural networks, the key of which lies in effectively characterizing the disparities between OoD and In-Distribution (InD) data. In this work, such disparities are exploited through a fresh perspective of non-linear feature subspace. That is, a discriminative non-linear subspace is learned from InD features to capture representative patterns of InD, while informative patterns of OoD features cannot be well captured in such a subspace due to their different distribution. Grounded on this perspective, we exploit the deviations of InD and OoD features in such a non-linear subspace for effective OoD detection. To be specific, we leverage the framework of Kernel Principal Component Analysis (KPCA) to attain the discriminative non-linear subspace and deploy the reconstruction error on such subspace to distinguish InD and OoD data. Two challenges emerge: (i) the learning of an effective non-linear subspace, i.e., the selection of kernel function in KPCA, and (ii) the computation of the kernel matrix with large-scale InD data. For the former, we reveal two vital non-linear patterns that closely relate to the InD-OoD disparity, leading to the establishment of a Cosine-Gaussian kernel for constructing the subspace. For the latter, we introduce two techniques to approximate the Cosine-Gaussian kernel with significantly cheap computations. In particular, our approximation is further tailored by incorporating the InD data confidence, which is demonstrated to promote the learning of discriminative subspaces for OoD data. Our study presents new insights into the non-linear feature subspace for OoD detection and contributes practical explorations on the associated kernel design and efficient computations, yielding a KPCA detection method with distinctively improved efficacy and efficiency.
Authors: Fengting Zhang, Boxu Liang, Qinghao Liu, Min Liu, Xiang Chen, Yaonan Wang
Abstract: Mesh reconstruction is a cornerstone process across various applications, including in-silico trials, digital twins, surgical planning, and navigation. Recent advancements in deep learning have notably enhanced mesh reconstruction speeds. Yet, traditional methods predominantly rely on deforming a standardised template mesh for individual subjects, which overlooks the unique anatomical variations between them, and may compromise the fidelity of the reconstructions. In this paper, we propose an adaptive-template-based mesh reconstruction network (ATMRN), which generates adaptive templates from the given images for the subsequent deformation, moving beyond the constraints of a singular, fixed template. Our approach, validated on cortical magnetic resonance (MR) images from the OASIS dataset, sets a new benchmark in voxel-to-cortex mesh reconstruction, achieving an average symmetric surface distance of 0.267mm across four cortical structures. Our proposed method is generic and can be easily transferred to other image modalities and anatomical structures.
Authors: Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang
Abstract: Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome this, we introduce \textbf{AgentThink}, a pioneering unified framework that, for the first time, integrates Chain-of-Thought (CoT) reasoning with dynamic, agent-style tool invocation for autonomous driving tasks. AgentThink's core innovations include: \textbf{(i) Structured Data Generation}, by establishing an autonomous driving tool library to automatically construct structured, self-verified reasoning data explicitly incorporating tool usage for diverse driving scenarios; \textbf{(ii) A Two-stage Training Pipeline}, employing Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO) to equip VLMs with the capability for autonomous tool invocation; and \textbf{(iii) Agent-style Tool-Usage Evaluation}, introducing a novel multi-tool assessment protocol to rigorously evaluate the model's tool invocation and utilization. Experiments on the DriveLMM-o1 benchmark demonstrate AgentThink significantly boosts overall reasoning scores by \textbf{53.91\%} and enhances answer accuracy by \textbf{33.54\%}, while markedly improving reasoning quality and consistency. Furthermore, ablation studies and robust zero-shot/few-shot generalization experiments across various benchmarks underscore its powerful capabilities. These findings highlight a promising trajectory for developing trustworthy and tool-aware autonomous driving models.
Authors: DongGeon Lee, Joonwon Jang, Jihae Jeong, Hwanjo Yu
Abstract: Rapid deployment of vision-language models (VLMs) magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate this question, we introduce MemeSafetyBench, a 50,430-instance benchmark pairing real meme images with both harmful and benign instructions. Using a comprehensive safety taxonomy and LLM-based instruction generation, we assess multiple VLMs across single and multi-turn interactions. We investigate how real-world memes influence harmful outputs, the mitigating effects of conversational context, and the relationship between model scale and safety metrics. Our findings demonstrate that VLMs show greater vulnerability to meme-based harmful prompts than to synthetic or typographic images. Memes significantly increase harmful responses and decrease refusals compared to text-only inputs. Though multi-turn interactions provide partial mitigation, elevated vulnerability persists. These results highlight the need for ecologically valid evaluations and stronger safety mechanisms.
Authors: Abdul Samad Shaik, Shashaank Mattur Aswatha, Rahul Jashvantbhai Pandya
Abstract: Cervical cancer, the fourth leading cause of cancer in women globally, requires early detection through Pap smear tests to identify precancerous changes and prevent disease progression. In this study, we performed a focused analysis by segmenting the cellular boundaries and drawing bounding boxes to isolate the cancer cells. A novel Deep Learning (DL) architecture, the ``Multi-Resolution Fusion Deep Convolutional Network", was proposed to effectively handle images with varying resolutions and aspect ratios, with its efficacy showcased using the SIPaKMeD dataset. The performance of this DL model was observed to be similar to the state-of-the-art models, with accuracy variations of a mere 2\% to 3\%, achieved using just 1.7 million learnable parameters, which is approximately 85 times less than the VGG-19 model. Furthermore, we introduced a multi-task learning technique that simultaneously performs segmentation and classification tasks and begets an Intersection over Union score of 0.83 and a classification accuracy of 90\%. The final stage of the workflow employs a probabilistic approach for risk assessment, extracting feature vectors to predict the likelihood of normal cells progressing to malignant states, which can be utilized for the prognosis of cervical cancer.
Authors: Mahesh Godavarti
Abstract: We introduce a new algebraic structure for multi-dimensional compositional embeddings, built on directional non-commutative monoidal operators. The core contribution of this work is this novel framework, which exhibits appealing theoretical properties (associativity along each dimension and an interchange law ensuring global consistency) while remaining compatible with modern machine learning architectures. Our construction defines a distinct composition operator circ_i for each axis i, ensuring associative combination along each axis without imposing global commutativity. Importantly, all axis-specific operators commute with one another, enforcing a global interchange law that enables consistent crossaxis compositions. This is, to our knowledge, the first approach that provides a common foundation that generalizes classical sequence-modeling paradigms (e.g., structured state-space models (SSMs) and transformer self-attention) to a unified multi-dimensional framework. For example, specific one-dimensional instances of our framework can recover the familiar affine transformation algebra, vanilla self-attention, and the SSM-style recurrence. The higher-dimensional generalizations naturally support recursive, structure-aware operations in embedding spaces. We outline several potential applications unlocked by this structure-including structured positional encodings in Transformers, directional image embeddings, and symbolic modeling of sequences or grids-indicating that it could inform future deep learning model designs. We formally establish the algebraic properties of our framework and discuss efficient implementations. Finally, as our focus is theoretical, we include no experiments here and defer empirical validation to future work, which we plan to undertake.
Authors: Christiaan Meijer, E. G. Patrick Bos
Abstract: While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance between two embedded data points by assigning attribution values through selective masking and distance-ranked mask filtering. We evaluate Distance Explainer on cross-modal embeddings (image-image and image-caption pairs) using established XAI metrics including Faithfulness, Sensitivity/Robustness, and Randomization. Experiments with ImageNet and CLIP models demonstrate that our method effectively identifies features contributing to similarity or dissimilarity between embedded data points while maintaining high robustness and consistency. We also explore how parameter tuning, particularly mask quantity and selection strategy, affects explanation quality. This work addresses a critical gap in XAI research and enhances transparency and trustworthiness in deep learning applications utilizing embedded spaces.
Authors: Yury Belousov, Brian Pulfer, Vitaliy Kinakh, Slava Voloshynovskiy
Abstract: While foundation models demonstrate impressive performance across various tasks, they remain vulnerable to adversarial inputs. Current research explores various approaches to enhance model robustness, with Diffusion Denoised Smoothing emerging as a particularly promising technique. This method employs a pretrained diffusion model to preprocess inputs before model inference. Yet, its effectiveness remains largely unexplored beyond classification. We aim to address this gap by analyzing three datasets with four distinct downstream tasks under three different adversarial attack algorithms. Our findings reveal that while foundation models maintain resilience against conventional transformations, applying high-noise diffusion denoising to clean images without any distortions significantly degrades performance by as high as 57%. Low-noise diffusion settings preserve performance but fail to provide adequate protection across all attack types. Moreover, we introduce a novel attack strategy specifically targeting the diffusion process itself, capable of circumventing defenses in the low-noise regime. Our results suggest that the trade-off between adversarial robustness and performance remains a challenge to be addressed.
Authors: S\'ebastien Pi\'erard, Adrien Deli\`ege, Ana\"is Halin, Marc Van Droogenbroeck
Abstract: Frequently, multiple entities (methods, algorithms, procedures, solutions, etc.) can be developed for a common task and applied across various domains that differ in the distribution of scenarios encountered. For example, in computer vision, the input data provided to image analysis methods depend on the type of sensor used, its location, and the scene content. However, a crucial difficulty remains: can we predict which entities will perform best in a new domain based on assessments on known domains, without having to carry out new and costly evaluations? This paper presents an original methodology to address this question, in a leave-one-domain-out fashion, for various application-specific preferences. We illustrate its use with 30 strategies to predict the rankings of 40 entities (unsupervised background subtraction methods) on 53 domains (videos).
Authors: Jiaming Zhou, Ke Ye, Jiayi Liu, Teli Ma, Zifang Wang, Ronghe Qiu, Kun-Yu Lin, Zhilin Zhao, Junwei Liang
Abstract: The generalization capabilities of vision-language-action (VLA) models to unseen tasks are crucial to achieving general-purpose robotic manipulation in open-world settings. However, the cross-task generalization capabilities of existing VLA models remain significantly underexplored. To address this gap, we introduce AGNOSTOS, a novel simulation benchmark designed to rigorously evaluate cross-task zero-shot generalization in manipulation. AGNOSTOS comprises 23 unseen manipulation tasks for testing, distinct from common training task distributions, and incorporates two levels of generalization difficulty to assess robustness. Our systematic evaluation reveals that current VLA models, despite being trained on diverse datasets, struggle to generalize effectively to these unseen tasks. To overcome this limitation, we propose Cross-Task In-Context Manipulation (X-ICM), a method that conditions large language models (LLMs) on in-context demonstrations from seen tasks to predict action sequences for unseen tasks. Additionally, we introduce a dynamics-guided sample selection strategy that identifies relevant demonstrations by capturing cross-task dynamics. On AGNOSTOS, X-ICM significantly improves cross-task zero-shot generalization performance over leading VLAs. We believe AGNOSTOS and X-ICM will serve as valuable tools for advancing general-purpose robotic manipulation.
Authors: Yuqi Zhou, Sunhao Dai, Shuai Wang, Kaiwen Zhou, Qinqlin Jia, Junxu
Abstract: Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object grounding and thereby achieving substantial performance gains. In this paper, we first conduct extensive analysis experiments of three key components of that training pipeline: input design, output evaluation, and policy update-each revealing distinct challenges arising from blindly applying general-purpose RL without adapting to GUI grounding tasks. Input design: Current templates encourage the model to generate chain-of-thought reasoning, but longer chains unexpectedly lead to worse grounding performance. Output evaluation: Reward functions based on hit signals or box area allow models to exploit box size, leading to reward hacking and poor localization quality. Policy update: Online RL tends to overfit easy examples due to biases in length and sample difficulty, leading to under-optimization on harder cases. To address these issues, we propose three targeted solutions. First, we adopt a Fast Thinking Template that encourages direct answer generation, reducing excessive reasoning during training. Second, we incorporate a box size constraint into the reward function to mitigate reward hacking. Third, we revise the RL objective by adjusting length normalization and adding a difficulty-aware scaling factor, enabling better optimization on hard samples. Our GUI-G1-3B, trained on 17K public samples with Qwen2.5-VL-3B-Instruct, achieves 90.3% accuracy on ScreenSpot and 37.1% on ScreenSpot-Pro. This surpasses all prior models of similar size and even outperforms the larger UI-TARS-7B, establishing a new state-of-the-art in GUI agent grounding. The project repository is available at https://github.com/Yuqi-Zhou/GUI-G1.
Authors: Xiawu Zheng, Yuexiao Ma, Teng Xi, Gang Zhang, Errui Ding, Yuchao Li, Jie Chen, Yonghong Tian, Rongrong Ji
Abstract: Despite superior performance on many computer vision tasks, deep convolution neural networks are well known to be compressed on devices that have resource constraints. Most existing network pruning methods require laborious human efforts and prohibitive computation resources, especially when the constraints are changed. This practically limits the application of model compression when the model needs to be deployed on a wide range of devices. Besides, existing methods are still challenged by the missing theoretical guidance. In this paper we propose an information theory-inspired strategy for automatic model compression. The principle behind our method is the information bottleneck theory, i.e., the hidden representation should compress information with each other. We thus introduce the normalized Hilbert-Schmidt Independence Criterion (nHSIC) on network activations as a stable and generalized indicator of layer importance. When a certain resource constraint is given, we integrate the HSIC indicator with the constraint to transform the architecture search problem into a linear programming problem with quadratic constraints. Such a problem is easily solved by a convex optimization method with a few seconds. We also provide a rigorous proof to reveal that optimizing the normalized HSIC simultaneously minimizes the mutual information between different layers. Without any search process, our method achieves better compression tradeoffs comparing to the state-of-the-art compression algorithms. For instance, with ResNet-50, we achieve a 45.3%-FLOPs reduction, with a 75.75 top-1 accuracy on ImageNet. Codes are avaliable at https://github.com/MAC-AutoML/ITPruner/tree/master.
Authors: Yi Sun, Xin Xu, Jian Li, Xiaochang Hu, Yifei Shi, Ling-Li Zeng
Abstract: Multi-output deep neural networks(MONs) contain multiple task branches, and these tasks usually share partial network filters that lead to the entanglement of different task inference routes. Due to the inconsistent optimization objectives, the task gradients used for training MONs will interfere with each other on the shared routes, which will decrease the overall model performance. To address this issue, we propose a novel gradient de-conflict algorithm named DR-MGF(Dynamic Routes and Meta-weighted Gradient Fusion) in this work. Different from existing de-conflict methods, DR-MGF achieves gradient de-conflict in MONs by learning task-preferred inference routes. The proposed method is motivated by our experimental findings: the shared filters are not equally important to different tasks. By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks. Through making the dominances of tasks over filters be proportional to the task-specific importance of filters, DR-MGF can effectively reduce the inter-task interference. The task-specific importance variables ultimately determine task-preferred inference routes at the end of training iterations. Extensive experimental results on CIFAR, ImageNet, and NYUv2 illustrate that DR-MGF outperforms the existing de-conflict methods both in prediction accuracy and convergence speed of MONs. Furthermore, DR-MGF can be extended to general MONs without modifying the overall network structures.
Authors: Veronika Cheplygina, Cathrine Damgaard, Trine Naja Eriksen, Dovile Juodelyte, Amelia Jim\'enez-S\'anchez
Abstract: The advancement of machine learning algorithms in medical image analysis requires the expansion of training datasets. A popular and cost-effective approach is automated annotation extraction from free-text medical reports, primarily due to the high costs associated with expert clinicians annotating medical images, such as chest X-rays. However, it has been shown that the resulting datasets are susceptible to biases and shortcuts. Another strategy to increase the size of a dataset is crowdsourcing, a widely adopted practice in general computer vision with some success in medical image analysis. In a similar vein to crowdsourcing, we enhance two publicly available chest X-ray datasets by incorporating non-expert annotations. However, instead of using diagnostic labels, we annotate shortcuts in the form of tubes. We collect 3.5k chest drain annotations for NIH-CXR14, and 1k annotations for four different tube types in PadChest, and create the Non-Expert Annotations of Tubes in X-rays (NEATX) dataset. We train a chest drain detector with the non-expert annotations that generalizes well to expert labels. Moreover, we compare our annotations to those provided by experts and show "moderate" to "almost perfect" agreement. Finally, we present a pathology agreement study to raise awareness about the quality of ground truth annotations. We make our dataset available on Zenodo at https://zenodo.org/records/14944064 and our code available at https://github.com/purrlab/chestxr-label-reliability.
URLs: https://zenodo.org/records/14944064, https://github.com/purrlab/chestxr-label-reliability.
Authors: Zhilin Zhang, Fangyu Wu
Abstract: Visual Question Answering (VQA) has emerged as a highly engaging field in recent years, with increasing research focused on enhancing VQA accuracy through advanced models such as Transformers. Despite this growing interest, limited work has examined the comparative effectiveness of textual encoders in VQA, particularly considering model complexity and computational efficiency. In this work, we conduct a comprehensive comparison between complex textual models that leverage long-range dependencies and simpler models focusing on local textual features within a well-established VQA framework. Our findings reveal that employing complex textual encoders is not always the optimal approach for the VQA-v2 dataset. Motivated by this insight, we propose ConvGRU, a model that incorporates convolutional layers to improve text feature representation without substantially increasing model complexity. Tested on the VQA-v2 dataset, ConvGRU demonstrates a modest yet consistent improvement over baselines for question types such as Number and Count, which highlights the potential of lightweight architectures for VQA tasks, especially when computational resources are limited.
Authors: Zhihang Song, Dingyi Yao, Ruibo MIng, Lihui Peng, Jianming Hu, Danya Yao, Yi Zhang
Abstract: Multi-modal object detection in autonomous driving has achieved great breakthroughs due to the usage of fusing complementary information from different sensors. The calibration in fusion between sensors such as LiDAR and camera is always supposed to be precise in previous work. However, in reality, calibration matrices are fixed when the vehicles leave the factory, but vibration, bumps, and data lags may cause calibration bias. As the research on the calibration influence on fusion detection performance is relatively few, flexible calibration dependency multi-sensor detection method has always been attractive. In this paper, we conducted experiments on SOTA detection method EPNet++ and proved slight bias on calibration can reduce the performance seriously. We also proposed a re-calibration model based on semantic segmentation which can be combined with a detection algorithm to improve the performance and robustness of multi-modal calibration bias.
Authors: Yongting Zhang, Lu Chen, Guodong Zheng, Yifeng Gao, Rui Zheng, Jinlan Fu, Zhenfei Yin, Senjie Jin, Yu Qiao, Xuanjing Huang, Feng Zhao, Tao Gui, Jing Shao
Abstract: The emergence of Vision Language Models (VLMs) has brought unprecedented advances in understanding multimodal information. The combination of textual and visual semantics in VLMs is highly complex and diverse, making the safety alignment of these models challenging. Furthermore, due to the limited study on the safety alignment of VLMs, there is a lack of large-scale, high-quality datasets. To address these limitations, we propose a Safety Preference Alignment dataset for Vision Language Models named SPA-VL. In terms of breadth, SPA-VL covers 6 harmfulness domains, 13 categories, and 53 subcategories, and contains 100,788 samples of the quadruple (question, image, chosen response, rejected response). In terms of depth, the responses are collected from 12 open-source (e.g., QwenVL) and closed-source (e.g., Gemini) VLMs to ensure diversity. The construction of preference data is fully automated, and the experimental results indicate that models trained with alignment techniques on the SPA-VL dataset exhibit substantial improvements in harmlessness and helpfulness while maintaining core capabilities. SPA-VL, as a large-scale, high-quality, and diverse dataset, represents a significant milestone in ensuring that VLMs achieve both harmlessness and helpfulness.
Authors: Zhaowei Wu, Binyi Su, Qichuan Geng, Hua Zhang, Zhong Zhou
Abstract: Few-shot Open-set Object Detection (FOOD) poses a challenge in many open-world scenarios. It aims to train an open-set detector to detect known objects while rejecting unknowns with scarce training samples. Existing FOOD methods are subject to limited visual information, and often exhibit an ambiguous decision boundary between known and unknown classes. To address these limitations, we propose the first prompt-based few-shot open-set object detection framework, which exploits additional textual information and delves into constructing a robust decision boundary for unknown rejection. Specifically, as no available training data for unknown classes, we select pseudo-unknown samples with Attribution-Gradient based Pseudo-unknown Mining (AGPM), which leverages the discrepancy in attribution gradients to quantify uncertainty. Subsequently, we propose Conditional Evidence Decoupling (CED) to decouple and extract distinct knowledge from selected pseudo-unknown samples by eliminating opposing evidence. This optimization process can enhance the discrimination between known and unknown classes. To further regularize the model and form a robust decision boundary for unknown rejection, we introduce Abnormal Distribution Calibration (ADC) to calibrate the output probability distribution of local abnormal features in pseudo-unknown samples. Our method achieves superior performance over previous state-of-the-art approaches, improving the average recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. Our source code is available at https://gitee.com/VR_NAVE/ced-food.
Authors: Qiushi Guo
Abstract: Data augmentation remains a widely utilized technique in deep learning, particularly in tasks such as image classification, semantic segmentation, and object detection. Among them, Copy-Paste is a simple yet effective method and gain great attention recently. However, existing Copy-Paste often overlook contextual relevance between source and target images, resulting in inconsistencies in generated outputs. To address this challenge, we propose a context-aware approach that integrates Bidirectional Latent Information Propagation (BLIP) for content extraction from source images. By matching extracted content information with category information, our method ensures cohesive integration of target objects using Segment Anything Model (SAM) and You Only Look Once (YOLO). This approach eliminates the need for manual annotation, offering an automated and user-friendly solution. Experimental evaluations across diverse datasets demonstrate the effectiveness of our method in enhancing data diversity and generating high-quality pseudo-images across various computer vision tasks.
Authors: Jackson Hamel, Ming-Jun Lai, Zhaiming Shen, Ye Tian
Abstract: In this work, we propose to use a local clustering approach based on the sparse solution technique to study the medical image, especially the lung cancer image classification task. We view images as the vertices in a weighted graph and the similarity between a pair of images as the edges in the graph. The vertices within the same cluster can be assumed to share similar features and properties, thus making the applications of graph clustering techniques very useful for image classification. Recently, the approach based on the sparse solutions of linear systems for graph clustering has been found to identify clusters more efficiently than traditional clustering methods such as spectral clustering. We propose to use the two newly developed local clustering methods based on sparse solution of linear system for image classification. In addition, we employ a box spline-based tight-wavelet-framelet method to clean these images and help build a better adjacency matrix before clustering. The performance of our methods is shown to be very effective in classifying images. Our approach is significantly more efficient and either favorable or equally effective compared with other state-of-the-art approaches. Finally, we shall make a remark by pointing out two image deformation methods to build up more artificial image data to increase the number of labeled images.
Authors: Xuechao Chen, Ying Chen, Jialin Li, Qiang Nie, Hanqiu Deng, Yong Liu, Qixing Huang, Yang Li
Abstract: 3D pre-training is crucial to 3D perception tasks. Nevertheless, limited by the difficulties in collecting clean and complete 3D data, 3D pre-training has persistently faced data scaling challenges. In this work, we introduce a novel self-supervised pre-training framework that incorporates millions of images into 3D pre-training corpora by leveraging a large depth estimation model. New pre-training corpora encounter new challenges in representation ability and embedding efficiency of models. Previous pre-training methods rely on farthest point sampling and k-nearest neighbors to embed a fixed number of 3D tokens. However, these approaches prove inadequate when it comes to embedding millions of samples that feature a diverse range of point numbers, spanning from 1,000 to 100,000. In contrast, we propose a tokenizer with linear-time complexity, which enables the efficient embedding of a flexible number of tokens. Accordingly, a new 3D reconstruction target is proposed to cooperate with our 3D tokenizer. Our method achieves state-of-the-art performance in 3D classification, few-shot learning, and 3D segmentation. Code is available at https://github.com/XuechaoChen/P3P-MAE.
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.
Authors: Zehao Wang, Han Zhou, Matthew B. Blaschko, Tinne Tuytelaars, Minye Wu
Abstract: Novel view synthesis of indoor scenes can be achieved by capturing a monocular video sequence of the environment. However, redundant information caused by artificial movements in the input video data reduces the efficiency of scene modeling. To address this, we formulate the problem as a combinatorial optimization task for view subset selection. In this work, we propose a novel subset selection framework that integrates a comprehensive diversity-based measurement with well-designed utility functions. We provide a theoretical analysis of these utility functions and validate their effectiveness through extensive experiments. Furthermore, we introduce IndoorTraj, a novel dataset designed for indoor novel view synthesis, featuring complex and extended trajectories that simulate intricate human behaviors. Experiments on IndoorTraj show that our framework consistently outperforms baseline strategies while using only 5-20% of the data, highlighting its remarkable efficiency and effectiveness. The code is available at: https://github.com/zehao-wang/IndoorTraj
Authors: Enming Zhang, Xingyuan Dai, Min Huang, Yisheng Lv, Qinghai Miao
Abstract: Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving, performing subtasks such as prediction, planning, and perception through question-and-answer interactions. However, most existing methods rely on computationally expensive visual encoders and large language models (LLMs), making them difficult to deploy in real-world scenarios and real-time applications. Meanwhile, most existing VLMs lack the ability to process multiple images, making it difficult to adapt to multi-camera perception in autonomous driving. To address these issues, we propose a novel framework called MiniDrive, which incorporates our proposed Feature Engineering Mixture of Experts (FE-MoE) module and Dynamic Instruction Adapter (DI-Adapter). The FE-MoE effectively maps 2D features into visual token embeddings before being input into the language model. The DI-Adapter enables the visual token embeddings to dynamically change with the instruction text embeddings, resolving the issue of static visual token embeddings for the same image in previous approaches. Compared to previous works, MiniDrive achieves state-of-the-art performance in terms of parameter size, floating point operations, and response efficiency, with the smallest version containing only 83M parameters.
Authors: Vincenzo Polizzi, Marco Cannici, Davide Scaramuzza, Jonathan Kelly
Abstract: Camera relocalization methods range from dense image alignment to direct camera pose regression from a query image. Among these, sparse feature matching stands out as an efficient, versatile, and generally lightweight approach with numerous applications. However, feature-based methods often struggle with significant viewpoint and appearance changes, leading to matching failures and inaccurate pose estimates. To overcome this limitation, we propose a novel approach that leverages a globally sparse yet locally dense 3D representation of 2D features. By tracking and triangulating landmarks over a sequence of frames, we construct a sparse voxel map optimized to render image patch descriptors observed during tracking. Given an initial pose estimate, we first synthesize descriptors from the voxels using volumetric rendering and then perform feature matching to estimate the camera pose. This methodology enables the generation of descriptors for unseen views, enhancing robustness to view changes. We extensively evaluate our method on the 7-Scenes and Cambridge Landmarks datasets. Our results show that our method significantly outperforms existing state-of-the-art feature representation techniques in indoor environments, achieving up to a 39% improvement in median translation error. Additionally, our approach yields comparable results to other methods for outdoor scenarios while maintaining lower memory and computational costs.
Authors: Xiangning Zhang, Qingwei Zhang, Jinnan Chen, Chengfeng Zhou, Yaqi Wang, Zhengjie Zhang, Xiaobo Li, Dahong Qian
Abstract: Endoscopic Submucosal Dissection (ESD) is a minimally invasive procedure initially developed for early gastric cancer treatment and has expanded to address diverse gastrointestinal lesions. While computer-assisted surgery (CAS) systems enhance ESD precision and safety, their efficacy hinges on accurate real-time surgical phase recognition, a task complicated by ESD's inherent complexity, including heterogeneous lesion characteristics and dynamic tissue interactions. Existing video-based phase recognition algorithms, constrained by inefficient temporal context modeling, exhibit limited performance in capturing fine-grained phase transitions and long-range dependencies. To overcome these limitations, we propose SPRMamba, a novel framework integrating a Mamba-based architecture with a Scaled Residual TranMamba (SRTM) block to synergize long-term temporal modeling and localized detail extraction. SPRMamba further introduces the Hierarchical Sampling Strategy to optimize computational efficiency, enabling real-time processing critical for clinical deployment. Evaluated on the ESD385 dataset and the cholecystectomy benchmark Cholec80, SPRMamba achieves state-of-the-art performance (87.64% accuracy on ESD385, +1.0% over prior methods), demonstrating robust generalizability across surgical workflows. This advancement bridges the gap between computational efficiency and temporal sensitivity, offering a transformative tool for intraoperative guidance and skill assessment in ESD surgery. The code is accessible at https://github.com/Zxnyyyyy/SPRMamba.
Authors: Mohammad Shahab Sepehri, Zalan Fabian, Maryam Soltanolkotabi, Mahdi Soltanolkotabi
Abstract: Multimodal Large Language Models (MLLMs) have tremendous potential to improve the accuracy, availability, and cost-effectiveness of healthcare by providing automated solutions or serving as aids to medical professionals. Despite promising first steps in developing medical MLLMs in the past few years, their capabilities and limitations are not well-understood. Recently, many benchmark datasets have been proposed that test the general medical knowledge of such models across a variety of medical areas. However, the systematic failure modes and vulnerabilities of such models are severely underexplored with most medical benchmarks failing to expose the shortcomings of existing models in this safety-critical domain. In this paper, we introduce MediConfusion, a challenging medical Visual Question Answering (VQA) benchmark dataset, that probes the failure modes of medical MLLMs from a vision perspective. We reveal that state-of-the-art models are easily confused by image pairs that are otherwise visually dissimilar and clearly distinct for medical experts. Strikingly, all available models (open-source or proprietary) achieve performance below random guessing on MediConfusion, raising serious concerns about the reliability of existing medical MLLMs for healthcare deployment. We also extract common patterns of model failure that may help the design of a new generation of more trustworthy and reliable MLLMs in healthcare.
Authors: Christopher Scarvelis, David Benhaim, Paul Zhang
Abstract: Orientation estimation is a fundamental task in 3D shape analysis which consists of estimating a shape's orientation axes: its side-, up-, and front-axes. Using this data, one can rotate a shape into canonical orientation, where its orientation axes are aligned with the coordinate axes. Developing an orientation algorithm that reliably estimates complete orientations of general shapes remains an open problem. We introduce a two-stage orientation pipeline that achieves state of the art performance on up-axis estimation and further demonstrate its efficacy on full-orientation estimation, where one seeks all three orientation axes. Unlike previous work, we train and evaluate our method on all of Shapenet rather than a subset of classes. We motivate our engineering contributions by theory describing fundamental obstacles to orientation estimation for rotationally-symmetric shapes, and show how our method avoids these obstacles.
Authors: Xiao Cai, Pengpeng Zeng, Lianli Gao, Sitong Su, Heng Tao Shen, Jingkuan Song
Abstract: General Text-to-3D (GT23D) generation is crucial for creating diverse 3D content across objects and scenes, yet it faces two key challenges: 1) ensuring semantic consistency between input text and generated 3D models, and 2) maintaining multi-view consistency across different perspectives within 3D. Existing approaches typically address only one of these challenges, often leading to suboptimal results in semantic fidelity and structural coherence. To overcome these limitations, we propose SeMv-3D, a novel framework that jointly enhances semantic alignment and multi-view consistency in GT23D generation. At its core, we introduce Triplane Prior Learning (TPL), which effectively learns triplane priors by capturing spatial correspondences across three orthogonal planes using a dedicated Orthogonal Attention mechanism, thereby ensuring geometric consistency across viewpoints. Additionally, we present Prior-based Semantic Aligning in Triplanes (SAT), which enables consistent any-view synthesis by leveraging attention-based feature alignment to reinforce the correspondence between textual semantics and triplane representations. Extensive experiments demonstrate that our method sets a new state-of-the-art in multi-view consistency, while maintaining competitive performance in semantic consistency compared to methods focused solely on semantic alignment. These results emphasize the remarkable ability of our approach to effectively balance and excel in both dimensions, establishing a new benchmark in the field.
Authors: Xiang Liu, Yijun Song, Xia Li, Yifei Sun, Huiying Lan, Zemin Liu, Linshan Jiang, Jialin Li
Abstract: Deep learning models are increasingly utilized on resource-constrained edge devices for real-time data analytics. Recently, Vision Transformer and their variants have shown exceptional performance in various computer vision tasks. However, their substantial computational requirements and low inference latency create significant challenges for deploying such models on resource-constrained edge devices. To address this issue, we propose a novel framework, ED-ViT, which is designed to efficiently split and execute complex Vision Transformers across multiple edge devices. Our approach involves partitioning Vision Transformer models into several sub-models, while each dedicated to handling a specific subset of data classes. To further reduce computational overhead and inference latency, we introduce a class-wise pruning technique that decreases the size of each sub-model. Through extensive experiments conducted on five datasets using three model architectures and actual implementation on edge devices, we demonstrate that our method significantly cuts down inference latency on edge devices and achieves a reduction in model size by up to 28.9 times and 34.1 times, respectively, while maintaining test accuracy comparable to the original Vision Transformer. Additionally, we compare ED-ViT with two state-of-the-art methods that deploy CNN and SNN models on edge devices, evaluating metrics such as accuracy, inference time, and overall model size. Our comprehensive evaluation underscores the effectiveness of the proposed ED-ViT framework.
Authors: Donghao Zhou, Jiancheng Huang, Jinbin Bai, Jiaze Wang, Hao Chen, Guangyong Chen, Xiaowei Hu, Pheng-Ann Heng
Abstract: Text-to-image diffusion models can generate high-quality images but lack fine-grained control of visual concepts, limiting their creativity. Thus, we introduce component-controllable personalization, a new task that enables users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesired elements disrupt the target concept, and semantic imbalance, which causes disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adaptively perturb unwanted visual semantics and Dual-Stream Balancing for more balanced learning of desired visual semantics. The experimental results show that MagicTailor achieves superior performance in this task and enables more personalized and creative image generation.
Authors: Yeong-Joon Ju, Ho-Joong Kim, Seong-Whan Lee
Abstract: Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the alignment to understand multimodal queries. However, existing methods often overlook crucial visual information due to a text-dominant issue, which overly depends on text-driven signals. In this paper, we introduce MIRe, a retrieval framework that achieves modality interaction without fusing textual features during the alignment. Our method allows the textual query to attend to visual embeddings while not feeding text-driven signals back into the visual representations. Additionally, we construct a pre-training dataset for multimodal query retrieval by transforming concise question-answer pairs into extended passages. Our experiments demonstrate that our pre-training strategy significantly enhances the understanding of multimodal queries, resulting in strong performance across four multimodal retrieval benchmarks under zero-shot settings. Moreover, our ablation studies and analyses explicitly verify the effectiveness of our framework in mitigating the text-dominant issue. Our code is publicly available: https://github.com/yeongjoonJu/MIRe
Authors: Fabian Immel, Richard Fehler, Frank Bieder, Jan-Hendrik Pauls, Christoph Stiller
Abstract: Autonomous vehicles rely on HD maps for their operation, but offline HD maps eventually become outdated. For this reason, online HD map construction methods use live sensor data to infer map information instead. Research on real map changes shows that oftentimes entire parts of an HD map remain unchanged and can be used as a prior. We therefore introduce M3TR (Multi-Masking Map Transformer), a generalist approach for HD map completion both with and without offline HD map priors. As a necessary foundation, we address shortcomings in ground truth labels for Argoverse 2 and nuScenes and propose the first comprehensive benchmark for HD map completion. Unlike existing models that specialize in a single kind of map change, which is unrealistic for deployment, our Generalist model handles all kinds of changes, matching the effectiveness of Expert models. With our map masking as augmentation regime, we can even achieve a +1.4 mAP improvement without a prior. Finally, by fully utilizing prior HD map elements and optimizing query designs, M3TR outperforms existing methods by +4.3 mAP while being the first real-world deployable model for offline HD map priors. Code is available at https://github.com/immel-f/m3tr
Authors: Kaifeng Gao, Jiaxin Shi, Hanwang Zhang, Chunping Wang, Jun Xiao, Long Chen
Abstract: With the advance of diffusion models, today's video generation has achieved impressive quality. To extend the generation length and facilitate real-world applications, a majority of video diffusion models (VDMs) generate videos in an autoregressive manner, i.e., generating subsequent clips conditioned on the last frame(s) of the previous clip. However, existing autoregressive VDMs are highly inefficient and redundant: The model must re-compute all the conditional frames that are overlapped between adjacent clips. This issue is exacerbated when the conditional frames are extended autoregressively to provide the model with long-term context. In such cases, the computational demands increase significantly (i.e., with a quadratic complexity w.r.t. the autoregression step). In this paper, we propose Ca2-VDM, an efficient autoregressive VDM with Causal generation and Cache sharing. For causal generation, it introduces unidirectional feature computation, which ensures that the cache of conditional frames can be precomputed in previous autoregression steps and reused in every subsequent step, eliminating redundant computations. For cache sharing, it shares the cache across all denoising steps to avoid the huge cache storage cost. Extensive experiments demonstrated that our Ca2-VDM achieves state-of-the-art quantitative and qualitative video generation results and significantly improves the generation speed. Code is available: https://github.com/Dawn-LX/CausalCache-VDM
Authors: Hui Ren, Joanna Materzynska, Rohit Gandikota, David Bau, Antonio Torralba
Abstract: We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investigate this, we train a text-to-image model exclusively on photographs, without access to any painting-related content. We show that it is possible to adapt a model that is trained without paintings to an artistic style, given only few examples. User studies and automatic evaluations confirm that our model (post-adaptation) performs on par with state-of-the-art models trained on massive datasets that contain artistic content like paintings, drawings or illustrations. Finally, using data attribution techniques, we analyze how both artistic and non-artistic datasets contribute to generating artistic-style images. Surprisingly, our findings suggest that high-quality artistic outputs can be achieved without prior exposure to artistic data, indicating that artistic style generation can occur in a controlled, opt-in manner using only a limited, carefully selected set of training examples.
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 the core approximations in splatting 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. Our code is publicly available at: https://github.com/chinmay0301ucsd/Vol3DGS
Authors: Kangyu Zhu, Peng Xia, Yun Li, Hongtu Zhu, Sheng Wang, Huaxiu Yao
Abstract: The advancement of Large Vision-Language Models (LVLMs) has propelled their application in the medical field. However, Medical LVLMs (Med-LVLMs) encounter factuality challenges due to modality misalignment, where the models prioritize textual knowledge over visual input, leading to hallucinations that contradict information in medical images. Previous attempts to enhance modality alignment in Med-LVLMs through preference optimization have inadequately mitigated clinical relevance in preference data, making these samples easily distinguishable and reducing alignment effectiveness. To address this challenge, we propose MMedPO, a novel multimodal medical preference optimization approach that considers the clinical relevance of preference samples to enhance Med-LVLM alignment. MMedPO curates multimodal preference data by introducing two types of dispreference: (1) plausible hallucinations injected through target Med-LVLMs or GPT-4o to produce medically inaccurate responses, and (2) lesion region neglect achieved through local lesion-noising, disrupting visual understanding of critical areas. We then calculate clinical relevance for each sample based on scores from multiple Med-LLMs and visual tools, and integrate these scores into the preference optimization process as weights, enabling effective alignment. Our experiments demonstrate that MMedPO significantly enhances factual accuracy in Med-LVLMs, achieving substantial improvements over existing preference optimization methods by averaging 14.2% and 51.7% across the Med-VQA and report generation tasks. Our code are available in https://github.com/aiming-lab/MMedPO.
Authors: Toshiya Yura, Ashkan Mirzaei, Igor Gilitschenski
Abstract: We introduce a method for using event camera data in novel view synthesis via Gaussian Splatting. Event cameras offer exceptional temporal resolution and a high dynamic range. Leveraging these capabilities allows us to effectively address the novel view synthesis challenge in the presence of fast camera motion. For initialization of the optimization process, our approach uses prior knowledge encoded in an event-to-video model. We also use spline interpolation for obtaining high quality poses along the event camera trajectory. This enhances the reconstruction quality from fast-moving cameras while overcoming the computational limitations traditionally associated with event-based Neural Radiance Field (NeRF) methods. Our experimental evaluation demonstrates that our results achieve higher visual fidelity and better performance than existing event-based NeRF approaches while being an order of magnitude faster to render.
Authors: Lea M\"uller, Hongsuk Choi, Anthony Zhang, Brent Yi, Jitendra Malik, Angjoo Kanazawa
Abstract: We present "Humans and Structure from Motion" (HSfM), a method for jointly reconstructing multiple human meshes, scene point clouds, and camera parameters in a metric world coordinate system from a sparse set of uncalibrated multi-view images featuring people. Our approach combines data-driven scene reconstruction with the traditional Structure-from-Motion (SfM) framework to achieve more accurate scene reconstruction and camera estimation, while simultaneously recovering human meshes. In contrast to existing scene reconstruction and SfM methods that lack metric scale information, our method estimates approximate metric scale by leveraging a human statistical model. Furthermore, it reconstructs multiple human meshes within the same world coordinate system alongside the scene point cloud, effectively capturing spatial relationships among individuals and their positions in the environment. We initialize the reconstruction of humans, scenes, and cameras using robust foundational models and jointly optimize these elements. This joint optimization synergistically improves the accuracy of each component. We compare our method to existing approaches on two challenging benchmarks, EgoHumans and EgoExo4D, demonstrating significant improvements in human localization accuracy within the world coordinate frame (reducing error from 3.51m to 1.04m in EgoHumans and from 2.9m to 0.56m in EgoExo4D). Notably, our results show that incorporating human data into the SfM pipeline improves camera pose estimation (e.g., increasing RRA@15 by 20.3% on EgoHumans). Additionally, qualitative results show that our approach improves overall scene reconstruction quality. Our code is available at: https://github.com/hongsukchoi/HSfM_RELEASE
Authors: Di Wu, Feng Yang, Benlian Xu, Pan Liao, Wenhui Zhao, Dingwen Zhang
Abstract: The application of vision-based multi-view environmental perception system has been increasingly recognized in autonomous driving technology, especially the BEV-based models. Current state-of-the-art solutions primarily encode image features from each camera view into the BEV space through explicit or implicit depth prediction. However, these methods often overlook the structured correlations among different parts of objects in 3D space and the fact that different categories of objects often occupy distinct local height ranges. For example, trucks appear at higher elevations, whereas traffic cones are near the ground. In this work, we propose a novel approach that decouples feature sampling in the \textbf{BEV} grid queries paradigm into \textbf{H}orizontal feature aggregation and \textbf{V}ertical adaptive height-aware reference point sampling (HV-BEV), aiming to improve both the aggregation of objects' complete information and awareness of diverse objects' height distribution. Specifically, a set of relevant neighboring points is dynamically constructed for each 3D reference point on the ground-aligned horizontal plane, enhancing the association of the same instance across different BEV grids, especially when the instance spans multiple image views around the vehicle. Additionally, instead of relying on uniform sampling within a fixed height range, we introduce a height-aware module that incorporates historical information, enabling the reference points to adaptively focus on the varying heights at which objects appear in different scenes. Extensive experiments validate the effectiveness of our proposed method, demonstrating its superior performance over the baseline across the nuScenes dataset. Moreover, our best-performing model achieves a remarkable 50.5\% mAP and 59.8\% NDS on the nuScenes testing set. The code is available at https://github.com/Uddd821/HV-BEV.
Authors: Francisco Caetano, Christiaan Viviers, Luis A. Zavala-Mondrag\'on, Peter H. N. de With, Fons van der Sommen
Abstract: Out-of-distribution (OOD) detection holds significant importance across many applications. While semantic and domain-shift OOD problems are well-studied, this work focuses on covariate shifts - subtle variations in the data distribution that can degrade machine learning performance. We hypothesize that detecting these subtle shifts can improve our understanding of in-distribution boundaries, ultimately improving OOD detection. In adversarial discriminators trained with Batch Normalization (BN), real and adversarial samples form distinct domains with unique batch statistics - a property we exploit for OOD detection. We introduce DisCoPatch, an unsupervised Adversarial Variational Autoencoder (VAE) framework that harnesses this mechanism. During inference, batches consist of patches from the same image, ensuring a consistent data distribution that allows the model to rely on batch statistics. DisCoPatch uses the VAE's suboptimal outputs (generated and reconstructed) as negative samples to train the discriminator, thereby improving its ability to delineate the boundary between in-distribution samples and covariate shifts. By tightening this boundary, DisCoPatch achieves state-of-the-art results in public OOD detection benchmarks. The proposed model not only excels in detecting covariate shifts, achieving 95.5% AUROC on ImageNet-1K(-C) but also outperforms all prior methods on public Near-OOD (95.0%) benchmarks. With a compact model size of 25MB, it achieves high OOD detection performance at notably lower latency than existing methods, making it an efficient and practical solution for real-world OOD detection applications. The code will be made publicly available
Authors: Zhiheng Lyu, Xueguang Ma, Wenhu Chen
Abstract: Recent agentic language models increasingly need to interact directly with real-world environments containing intertwined visual and textual information through raw camera pixels, rather than relying on separate image and tokenized text processing, underscoring the necessity of a unified perception paradigm. To close this gap, we explore this idea through Perceive Everything as Pixels (PEAP) and release PixelWorld, a benchmark that renders natural-language, tabular, mathematical and diagrammatic inputs into a single pixel space. Experiments show that PEAP attains competitive accuracy on semantic-understanding tasks, indicating that a vision transformer can capture global textual semantics without explicit tokens. In contrast, reasoning-intensive benchmarks (math and code) exhibit sharp performance drops; however, Chain-of-Thought prompting partially mitigates this gap, hinting that explicit reasoning traces compensate for the missing token structure. We also find that when visual and textual information are closely integrated, representing everything as pixels reduces preprocessing complexity and avoids misalignment issues that often arise in separate pipelines. PixelWorld therefore serves as a practical benchmark for evaluating unified vision-language models and supports broader exploration of PEAP across diverse tasks.
Authors: Vernon Y. H. Toh, Yew Ken Chia, Deepanway Ghosal, Soujanya Poria
Abstract: The releases of OpenAI's o-[n] series, such as o1, o3, and o4-mini, mark a significant paradigm shift in Large Language Models towards advanced reasoning capabilities. Notably, models like o3 have demonstrated strong performance on benchmarks like the Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI). However, this benchmark is limited to symbolic patterns, whereas humans often perceive and reason about multimodal scenarios involving both vision and language data. Thus, there is an urgent need to investigate advanced reasoning capabilities in multimodal tasks. To this end, we track the evolution of the GPT-[n] and o-[n] series models (including o1, o3, and o4-mini) on challenging multimodal puzzles from PuzzleVQA and AlgoPuzzleVQA, which demand fine-grained visual perception. Our results reveal that o-[n] series, particularly later iterations like o3 and o4-mini, significantly outperform the GPT-[n] series and show strong scalability in multimodal reasoning. Nonetheless, despite these substantial advancements and the superior capabilities demonstrated by the o-[n] series, our findings highlight that even these leading models face persistent challenges. Difficulties are particularly evident in tasks requiring precise visual perception, robust compositional reasoning across multiple visual attributes, and solving complex algorithmic or highly combinatorial puzzles, indicating critical areas for future AGI development. We plan to continuously track new models in the series and update our results in this paper accordingly. All resources used in this evaluation are openly available at https://github.com/declare-lab/LLM-PuzzleTest.
Authors: Xuan Li, Chang Yu, Wenxin Du, Ying Jiang, Tianyi Xie, Yunuo Chen, Yin Yang, Chenfanfu Jiang
Abstract: Recent advances in large models have significantly advanced image-to-3D reconstruction. However, the generated models are often fused into a single piece, limiting their applicability in downstream tasks. This paper focuses on 3D garment generation, a key area for applications like virtual try-on with dynamic garment animations, which require garments to be separable and simulation-ready. We introduce Dress-1-to-3, a novel pipeline that reconstructs physics-plausible, simulation-ready separated garments with sewing patterns and humans from an in-the-wild image. Starting with the image, our approach combines a pre-trained image-to-sewing pattern generation model for creating coarse sewing patterns with a pre-trained multi-view diffusion model to produce multi-view images. The sewing pattern is further refined using a differentiable garment simulator based on the generated multi-view images. Versatile experiments demonstrate that our optimization approach substantially enhances the geometric alignment of the reconstructed 3D garments and humans with the input image. Furthermore, by integrating a texture generation module and a human motion generation module, we produce customized physics-plausible and realistic dynamic garment demonstrations. Project page: https://dress-1-to-3.github.io/
Authors: Angel Villar-Corrales, Sven Behnke
Abstract: Predicting future scene representations is a crucial task for enabling robots to understand and interact with the environment. However, most existing methods rely on videos and simulations with precise action annotations, limiting their ability to leverage the large amount of available unlabeled video data. To address this challenge, we propose PlaySlot, an object-centric video prediction model that infers object representations and latent actions from unlabeled video sequences. It then uses these representations to forecast future object states and video frames. PlaySlot allows the generation of multiple possible futures conditioned on latent actions, which can be inferred from video dynamics, provided by a user, or generated by a learned action policy, thus enabling versatile and interpretable world modeling. Our results show that PlaySlot outperforms both stochastic and object-centric baselines for video prediction across different environments. Furthermore, we show that our inferred latent actions can be used to learn robot behaviors sample-efficiently from unlabeled video demonstrations. Videos and code are available on https://play-slot.github.io/PlaySlot/.
Authors: Zhao Wang, Hao Wen, Lingting Zhu, Chenming Shang, Yujiu Yang, Qi Dou
Abstract: Character video generation is a significant real-world application focused on producing high-quality videos featuring specific characters. Recent advancements have introduced various control signals to animate static characters, successfully enhancing control over the generation process. However, these methods often lack flexibility, limiting their applicability and making it challenging for users to synthesize a source character into a desired target scene. To address this issue, we propose a novel framework, AnyCharV, that flexibly generates character videos using arbitrary source characters and target scenes, guided by pose information. Our approach involves a two-stage training process. In the first stage, we develop a base model capable of integrating the source character with the target scene using pose guidance. The second stage further bootstraps controllable generation through a self-boosting mechanism, where we use the generated video in the first stage and replace the fine mask with the coarse one, enabling training outcomes with better preservation of character details. Extensive experimental results demonstrate the superiority of our method compared with previous state-of-the-art methods.
Authors: Yue Yang, Ajay Patel, Matt Deitke, Tanmay Gupta, Luca Weihs, Andrew Head, Mark Yatskar, Chris Callison-Burch, Ranjay Krishna, Aniruddha Kembhavi, Christopher Clark
Abstract: Reasoning about images with rich text, such as charts and documents, is a critical application of vision-language models (VLMs). However, VLMs often struggle in these domains due to the scarcity of diverse text-rich vision-language data. To address this challenge, we present CoSyn, a framework that leverages the coding capabilities of text-only large language models (LLMs) to automatically create synthetic text-rich multimodal data. Given input text describing a target domain (e.g., "nutrition fact labels"), CoSyn prompts an LLM to generate code (Python, HTML, LaTeX, etc.) for rendering synthetic images. With the underlying code as textual representations of the synthetic images, CoSyn can generate high-quality instruction-tuning data, again relying on a text-only LLM. Using CoSyn, we constructed a dataset comprising 400K images and 2.7M rows of vision-language instruction-tuning data. Comprehensive experiments on seven benchmarks demonstrate that models trained on our synthetic data achieve state-of-the-art performance among competitive open-source models, including Llama 3.2, and surpass proprietary models such as GPT-4V and Gemini 1.5 Flash. Furthermore, CoSyn can produce synthetic pointing data, enabling VLMs to ground information within input images, showcasing its potential for developing multimodal agents capable of acting in real-world environments.
Authors: Vishal Thengane, Jean Lahoud, Hisham Cholakkal, Rao Muhammad Anwer, Lu Yin, Xiatian Zhu, Salman Khan
Abstract: While 3D instance segmentation (3DIS) has advanced significantly, existing methods typically assume that all object classes are known in advance and are uniformly distributed. However, this assumption is unrealistic in dynamic, real-world environments where new classes emerge gradually and exhibit natural imbalance. Although some approaches have addressed class emergence, they often overlook class imbalance, resulting in suboptimal performance -- particularly on rare categories. To tackle this challenge, we propose CLIMB-3D, a unified framework for \textbf{CL}ass-incremental \textbf{Imb}alance-aware \textbf{3D}IS. Building upon established exemplar replay (ER) strategies, we show that ER alone is insufficient to achieve robust performance under constrained memory conditions. To mitigate this, we introduce a novel pseudo-label generator (PLG) that extends supervision to previously learned categories by leveraging predictions from a frozen prior model. Despite its promise, PLG tends to bias towards frequent classes. Therefore, we propose a class-balanced re-weighting (CBR) scheme, that estimates object frequencies from pseudo-labels and dynamically adjusts training bias -- without requiring access to past data. We design and evaluate three incremental scenarios for 3DIS on the challenging ScanNet200 dataset, and additionally on semantic segmentation on ScanNetV2. Our approach achieves state-of-the-art results, surpassing prior work by up to 16.76\% mAP for instance segmentation and approximately 30\% mIoU for semantic segmentation, demonstrating strong generalization across both frequent and rare classes.
Authors: Yunpeng Gao, Chenhui Li, Zhongrui You, Junli Liu, Zhen Li, Pengan Chen, Qizhi Chen, Zhonghan Tang, Liansheng Wang, Penghui Yang, Yiwen Tang, Yuhang Tang, Shuai Liang, Songyi Zhu, Ziqin Xiong, Yifei Su, Xinyi Ye, Jianan Li, Yan Ding, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li
Abstract: Vision-Language Navigation (VLN) aims to guide agents by leveraging language instructions and visual cues, playing a pivotal role in embodied AI. Indoor VLN has been extensively studied, whereas outdoor aerial VLN remains underexplored. The potential reason is that outdoor aerial view encompasses vast areas, making data collection more challenging, which results in a lack of benchmarks. To address this problem, we propose OpenFly, a platform comprising various rendering engines, a versatile toolchain, and a large-scale benchmark for aerial VLN. Firstly, we integrate diverse rendering engines and advanced techniques for environment simulation, including Unreal Engine, GTA V, Google Earth, and 3D Gaussian Splatting (3D GS). Particularly, 3D GS supports real-to-sim rendering, further enhancing the realism of our environments. Secondly, we develop a highly automated toolchain for aerial VLN data collection, streamlining point cloud acquisition, scene semantic segmentation, flight trajectory creation, and instruction generation. Thirdly, based on the toolchain, we construct a large-scale aerial VLN dataset with 100k trajectories, covering diverse heights and lengths across 18 scenes. Moreover, we propose OpenFly-Agent, a keyframe-aware VLN model emphasizing key observations during flight. For benchmarking, extensive experiments and analyses are conducted, evaluating several recent VLN methods and showcasing the superiority of our OpenFly platform and agent. The toolchain, dataset, and codes will be open-sourced.
Authors: L. Degeorge, A. Ghosh, N. Dufour, D. Picard, V. Kalogeiton
Abstract: Recent text-to-image generation models have achieved remarkable results by training on billion-scale datasets, following a `bigger is better' paradigm that prioritizes data quantity over availability (closed vs open source) and reproducibility (data decay vs established collections). We challenge this established paradigm by demonstrating that one can match or outperform models trained on massive web-scraped collections, using only ImageNet enhanced with well-designed text and image augmentations. With this much simpler setup, we achieve a +1% overall score over SD-XL on GenEval and +0.5% on DPGBench while using just 1/10th the parameters and 1/1000th the training images. This opens the way for more reproducible research as ImageNet is a widely available dataset and our standardized training setup does not require massive compute resources.
Authors: Rui Hu, Delai Qiu, Shuyu Wei, Jiaming Zhang, Yining Wang, Shengping Liu, Jitao Sang
Abstract: Omnimodal Large Language Models (OLLMs) have shown significant progress in integrating vision and text, but still struggle with integrating vision and audio, often exhibiting suboptimal performance when processing audio queries compared to text queries. This disparity is primarily due to insufficient alignment between vision and audio modalities during training, leading to inadequate attention to visual information when using audio queries. To mitigate this issue, we propose a Self-Knowledge Distillation (Self-KD) training method where the vision-text component of the OLLM serves as the teacher and the vision-audio component as the student. This enables the model to process audio in a manner analogous to its text processing. Our experimental results demonstrate that Self-KD is an effective method for enhancing the vision-audio capabilities of OLLMs by learning from the vision-text components, which subsequently improves the interaction between audio and images and results in improved performance on multimodal tasks.
Authors: Juntian Du, Yuan Sun, Zhihu Zhou, Pinyi Chen, Runzhe Zhang, Keji Mao
Abstract: Recently, the Mamba architecture has demonstrated significant successes in various computer vision tasks, such as classification and segmentation. However, its application to optical flow estimation remains unexplored. In this paper, we introduce MambaFlow, a novel framework designed to leverage the high accuracy and efficiency of the Mamba architecture for capturing locally correlated features while preserving global information in end-to-end optical flow estimation. To our knowledge, MambaFlow is the first architecture centered around the Mamba design tailored specifically for optical flow estimation. It comprises two key components: (1) PolyMamba, which optimizes feature representation; and (2) PulseMamba, which facilitates efficient flow information dissemination. Our extensive experiments demonstrate that MambaFlow achieves remarkable results. On the Sintel benchmark, MambaFlow records an endpoint error (EPE) of 1.43 and an inference speed of 0.113 seconds, surpassing the state-of-the-art methods including GMFlow (with 18.9% lower EPE and 18.1% faster inference), SeparableFlow (5% lower EPE and 50.5% faster), CRAFT (1.11% lower EPE and 76.5% faster), and DIP (0.7% lower EPE and 77.2% faster)-demonstrating stronger potential for real-world deployment on resource-constrained devices. The source code will be made publicly available upon acceptance of the paper.
Authors: Kyle Stein, Andrew A. Mahyari, Guillermo Francia III, Eman El-Sheikh
Abstract: One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging yet crucial problem due to its ability to generalize knowledge to unseen classes from just one human-annotated image. In this paper, we introduce a transductive one-shot learning approach that employs subspace decomposition to utilize the information from labeled images in the support set and unlabeled images in the query set. These images are decomposed into a linear combination of latent variables representing primitives captured by smaller subspaces. By representing images in the query set as linear combinations of these latent primitives, we can propagate the label from a single image in the support set to query images that share similar combinations of primitives. Through a comprehensive quantitative analysis across various neural network feature extractors and datasets, we demonstrate that our approach can effectively generalize to novel classes from just one labeled image.
Authors: Kun Ouyang, Yuanxin Liu, Haoning Wu, Yi Liu, Hao Zhou, Jie Zhou, Fandong Meng, Xu Sun
Abstract: Video spatial reasoning, which involves inferring the underlying spatial structure from observed video frames, poses a significant challenge for existing Multimodal Large Language Models (MLLMs). This limitation stems primarily from 1) the absence of high-quality datasets for this task, and 2) the lack of effective training strategies to develop spatial reasoning capabilities. Motivated by the success of Reinforcement Learning with Verifiable Reward (RLVR) in unlocking LLM reasoning abilities, this work aims to improve MLLMs in video spatial reasoning through the RLVR paradigm. To this end, we introduce the $\textbf{SpaceR}$ framework. First, we present $\textbf{SpaceR-151k}$, a dataset with 91k questions spanning diverse spatial reasoning scenarios with verifiable answers, and 60k samples for maintaining general multimodal understanding. Second, we propose $\textbf{Spatially-Guided RLVR (SG-RLVR)}$, a novel reinforcement learning approach that extends Group Relative Policy Optimization (GRPO) with a novel map imagination mechanism, which encourages the model to infer spatial layouts in the thinking process, thereby facilitating more effective spatial reasoning. Extensive experiments demonstrate that SpaceR achieves state-of-the-art performance on spatial reasoning benchmarks (e.g., VSI-Bench, STI-Bench, and SPAR-Bench), while maintaining competitive results on video understanding benchmarks (e.g., Video-MME, TempCompass, and LongVideoBench). Remarkably, SpaceR surpasses the advanced GPT-4o by 11.6\% accuracy on VSI-Bench and is on par with the leading proprietary model Gemini-2.0-Flash, highlighting the effectiveness of our SpaceR-151k dataset and SG-RLVR in reinforcing spatial reasoning ability of MLLMs. Code, model, and dataset are available at https://github.com/OuyangKun10/SpaceR.
Authors: Conghao Xiong, Hao Chen, Joseph J. Y. Sung
Abstract: Computational pathology, which involves analyzing whole slide images for automated cancer diagnosis, relies on multiple instance learning, where performance depends heavily on the feature extractor and aggregator. Recent Pathology Foundation Models (PFMs), pretrained on large-scale histopathology data, have significantly enhanced both the extractor and aggregator, but they lack a systematic analysis framework. In this survey, we present a hierarchical taxonomy organizing PFMs through a top-down philosophy applicable to foundation model analysis in any domain: model scope, model pretraining, and model design. Additionally, we systematically categorize PFM evaluation tasks into slide-level, patch-level, multimodal, and biological tasks, providing comprehensive benchmarking criteria. Our analysis identifies critical challenges in both PFM development (pathology-specific methodology, end-to-end pretraining, data-model scalability) and utilization (effective adaptation, model maintenance), paving the way for future directions in this promising field. Resources referenced in this survey are available at https://github.com/BearCleverProud/AwesomeWSI.
Authors: Bofei Zhang, Zirui Shang, Zhi Gao, Wang Zhang, Rui Xie, Xiaojian Ma, Tao Yuan, Xinxiao Wu, Song-Chun Zhu, Qing Li
Abstract: Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. However, a major challenge in developing generalized GUI agents is the lack of sufficient trajectory data across various operating systems and applications, mainly due to the high cost of manual annotations. In this paper, we propose the TongUI framework that builds generalized GUI agents by learning from rich multimodal web tutorials. Concretely, we crawl and process online GUI tutorials (such as videos and articles) into GUI agent trajectory data, through which we produce the GUI-Net dataset containing 143K trajectory data across five operating systems and more than 200 applications. We develop the TongUI agent by fine-tuning Qwen2.5-VL-3B/7B models on GUI-Net, which show remarkable performance improvements on commonly used grounding and navigation benchmarks, outperforming baseline agents about 10\% on multiple benchmarks, showing the effectiveness of the GUI-Net dataset and underscoring the significance of our TongUI framework. We will fully open-source the code, the GUI-Net dataset, and the trained models soon.
Authors: Runyi Hu, Jie Zhang, Shiqian Zhao, Nils Lukas, Jiwei Li, Qing Guo, Han Qiu, Tianwei Zhang
Abstract: We present MaskMark, a simple, efficient, and flexible framework for image watermarking. MaskMark has two variants: (1) MaskMark-D, which supports global watermark embedding, watermark localization, and local watermark extraction for applications such as tamper detection; (2) MaskMark-ED, which focuses on local watermark embedding and extraction, offering enhanced robustness in small regions to support fine-grined image protection. MaskMark-D builds on the classical encoder-distortion layer-decoder training paradigm. In MaskMark-D, we introduce a simple masking mechanism during the decoding stage that enables both global and local watermark extraction. During training, the decoder is guided by various types of masks applied to watermarked images before extraction, helping it learn to localize watermarks and extract them from the corresponding local areas. MaskMark-ED extends this design by incorporating the mask into the encoding stage as well, guiding the encoder to embed the watermark in designated local regions, which improves robustness under regional attacks. Extensive experiments show that MaskMark achieves state-of-the-art performance in global and local watermark extraction, watermark localization, and multi-watermark embedding. It outperforms all existing baselines, including the recent leading model WAM for local watermarking, while preserving high visual quality of the watermarked images. In addition, MaskMark is highly efficient and adaptable. It requires only 20 hours of training on a single A6000 GPU, achieving 15x computational efficiency compared to WAM. By simply adjusting the distortion layer, MaskMark can be quickly fine-tuned to meet varying robustness requirements.
Authors: Lin Yuan, Xiaowan Li, Yan Zhang, Jiawei Zhang, Hongbo Li, Xinbo Gao
Abstract: Advancements in image generation technologies have raised significant concerns about their potential misuse, such as producing misinformation and deepfakes. Therefore, there is an urgent need for effective methods to detect AI-generated images (AIGI). Despite progress in AIGI detection, achieving reliable performance across diverse generation models and scenes remains challenging due to the lack of source-invariant features and limited generalization capabilities in existing methods. In this work, we explore the potential of using image entropy as a cue for AIGI detection and propose Multi-granularity Local Entropy Patterns (MLEP), a set of entropy feature maps computed across shuffled small patches over multiple image scaled. MLEP comprehensively captures pixel relationships across dimensions and scales while significantly disrupting image semantics, reducing potential content bias. Leveraging MLEP, a robust CNN-based classifier for AIGI detection can be trained. Extensive experiments conducted in an open-world scenario, evaluating images synthesized by 32 distinct generative models, demonstrate significant improvements over state-of-the-art methods in both accuracy and generalization.
Authors: Yogesh Kulkarni, Pooyan Fazli
Abstract: Video-language models (Video-LLMs) excel at understanding video content but struggle with spatial relationships, temporal ordering, and cross-frame continuity. To address these limitations, we introduce VideoPASTA (Preference Alignment with Spatio-Temporal-Cross Frame Adversaries), a framework that enhances Video-LLMs through targeted preference optimization. VideoPASTA trains models to distinguish accurate video representations from carefully crafted adversarial examples that deliberately violate spatial, temporal, or cross-frame relationships. With only 7,020 preference pairs and Direct Preference Optimization, VideoPASTA enables models to learn robust representations that capture fine-grained spatial details and long-range temporal dynamics. Experiments demonstrate that VideoPASTA is model agnostic and significantly improves performance, for example, achieving gains of up to 3.8% on LongVideoBench, 4.1% on VideoMME, and 4.0% on MVBench, when applied to various state-of-the-art Video-LLMs. These results demonstrate that targeted alignment, rather than massive pretraining or architectural modifications, effectively addresses core video-language challenges. Notably, VideoPASTA achieves these improvements without any human annotation or captioning, relying solely on 32-frame sampling. This efficiency makes our approach a scalable plug-and-play solution that seamlessly integrates with existing models while preserving their original capabilities.
Authors: Wei Zhuo, Zhiyue Tang, Wufeng Xue, Hao Ding, Linlin Shen
Abstract: Few-shot semantic segmentation has gained increasing interest due to its generalization capability, i.e., segmenting pixels of novel classes requiring only a few annotated images. Prior work has focused on meta-learning for support-query matching, with extensive development in both prototype-based and aggregation-based methods. To address data scarcity, recent approaches have turned to foundation models to enhance representation transferability for novel class segmentation. Among them, a hybrid dual-modal framework including both DINOv2 and SAM has garnered attention due to their complementary capabilities. We wonder "can we build a unified model with knowledge from both foundation models?" To this end, we propose FS-DINO, with only DINOv2's encoder and a lightweight segmenter. The segmenter features a bottleneck adapter, a meta-visual prompt generator based on dense similarities and semantic embeddings, and a decoder. Through coarse-to-fine cross-model distillation, we effectively integrate SAM's knowledge into our lightweight segmenter, which can be further enhanced by 4D correlation mining on support-query pairs. Extensive experiments on COCO-20i, PASCAL-5i, and FSS-1000 demonstrate the effectiveness and superiority of our method.
Authors: Dung Nguyen, Minh Khoi Ho, Huy Ta, Thanh Tam Nguyen, Qi Chen, Kumar Rav, Quy Duong Dang, Satwik Ramchandre, Son Lam Phung, Zhibin Liao, Minh-Son To, Johan Verjans, Phi Le Nguyen, Vu Minh Hieu Phan
Abstract: Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradicting source evidence, particularly due to inadequate localization reasoning. This work reveals a critical limitation in current medical LMMs: instead of analyzing relevant pathological regions, they often rely on linguistic patterns or attend to irrelevant image areas when responding to disease-related queries. To address this, we introduce HEAL-MedVQA (Hallucination Evaluation via Localization MedVQA), a comprehensive benchmark designed to evaluate LMMs' localization abilities and hallucination robustness. HEAL-MedVQA features (i) two innovative evaluation protocols to assess visual and textual shortcut learning, and (ii) a dataset of 67K VQA pairs, with doctor-annotated anatomical segmentation masks for pathological regions. To improve visual reasoning, we propose the Localize-before-Answer (LobA) framework, which trains LMMs to localize target regions of interest and self-prompt to emphasize segmented pathological areas, generating grounded and reliable answers. Experimental results demonstrate that our approach significantly outperforms state-of-the-art biomedical LMMs on the challenging HEAL-MedVQA benchmark, advancing robustness in medical VQA.
Authors: Eliraz Orfaig, Inna Stainvas, Igal Bilik
Abstract: This work introduces RGBX-DiffusionDet, an object detection framework extending the DiffusionDet model to fuse the heterogeneous 2D data (X) with RGB imagery via an adaptive multimodal encoder. To enable cross-modal interaction, we design the dynamic channel reduction within a convolutional block attention module (DCR-CBAM), which facilitates cross-talk between subnetworks by dynamically highlighting salient channel features. Furthermore, the dynamic multi-level aggregation block (DMLAB) is proposed to refine spatial feature representations through adaptive multiscale fusion. Finally, novel regularization losses that enforce channel saliency and spatial selectivity are introduced, leading to compact and discriminative feature embeddings. Extensive experiments using RGB-Depth (KITTI), a novel annotated RGB-Polarimetric dataset, and RGB-Infrared (M$^3$FD) benchmark dataset were conducted. We demonstrate consistent superiority of the proposed approach over the baseline RGB-only DiffusionDet. The modular architecture maintains the original decoding complexity, ensuring efficiency. These results establish the proposed RGBX-DiffusionDet as a flexible multimodal object detection approach, providing new insights into integrating diverse 2D sensing modalities into diffusion-based detection pipelines.
Authors: Bangyan Liao, Zhenjun Zhao, Haoang Li, Yi Zhou, Yingping Zeng, Hao Li, Peidong Liu
Abstract: Determining the vanishing points (VPs) in a Manhattan world, as a fundamental task in many 3D vision applications, consists of jointly inferring the line-VP association and locating each VP. Existing methods are, however, either sub-optimal solvers or pursuing global optimality at a significant cost of computing time. In contrast to prior works, we introduce convex relaxation techniques to solve this task for the first time. Specifically, we employ a "soft" association scheme, realized via a truncated multi-selection error, that allows for joint estimation of VPs' locations and line-VP associations. This approach leads to a primal problem that can be reformulated into a quadratically constrained quadratic programming (QCQP) problem, which is then relaxed into a convex semidefinite programming (SDP) problem. To solve this SDP problem efficiently, we present a globally optimal outlier-robust iterative solver (called GlobustVP), which independently searches for one VP and its associated lines in each iteration, treating other lines as outliers. After each independent update of all VPs, the mutual orthogonality between the three VPs in a Manhattan world is reinforced via local refinement. Extensive experiments on both synthetic and real-world data demonstrate that GlobustVP achieves a favorable balance between efficiency, robustness, and global optimality compared to previous works. The code is publicly available at https://github.com/WU-CVGL/GlobustVP.
Authors: Timo Kaiser, Thomas Norrenbrock, Bodo Rosenhahn
Abstract: The introduction of the Segment Anything Model (SAM) has paved the way for numerous semantic segmentation applications. For several tasks, quantifying the uncertainty of SAM is of particular interest. However, the ambiguous nature of the class-agnostic foundation model SAM challenges current uncertainty quantification (UQ) approaches. This paper presents a theoretically motivated uncertainty quantification model based on a Bayesian entropy formulation jointly respecting aleatoric, epistemic, and the newly introduced task uncertainty. We use this formulation to train USAM, a lightweight post-hoc UQ method. Our model traces the root of uncertainty back to under-parameterised models, insufficient prompts or image ambiguities. Our proposed deterministic USAM demonstrates superior predictive capabilities on the SA-V, MOSE, ADE20k, DAVIS, and COCO datasets, offering a computationally cheap and easy-to-use UQ alternative that can support user-prompting, enhance semi-supervised pipelines, or balance the tradeoff between accuracy and cost efficiency.
Authors: Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Gengshen Zhang, Dawei Leng, Yuhui Yin
Abstract: Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short captions. To address this, we propose Fine-Grained CLIP (FG-CLIP), which enhances fine-grained understanding through three key innovations. First, we leverage large multimodal models to generate 1.6 billion long caption-image pairs for capturing global-level semantic details. Second, a high-quality dataset is constructed with 12 million images and 40 million region-specific bounding boxes aligned with detailed captions to ensure precise, context-rich representations. Third, 10 million hard fine-grained negative samples are incorporated to improve the model's ability to distinguish subtle semantic differences. We construct a comprehensive dataset, termed FineHARD, by integrating high-quality region-specific annotations with hard fine-grained negative samples. Corresponding training methods are meticulously designed for these data. Extensive experiments demonstrate that FG-CLIP outperforms the original CLIP and other state-of-the-art methods across various downstream tasks, including fine-grained understanding, open-vocabulary object detection, image-text retrieval, and general multimodal benchmarks. These results highlight FG-CLIP's effectiveness in capturing fine-grained image details and improving overall model performance. The data, code, and models are available at https://github.com/360CVGroup/FG-CLIP.
Authors: Holly Dinkel, Marcel B\"usching, Alberta Longhini, Brian Coltin, Trey Smith, Danica Kragic, M{\aa}rten Bj\"orkman, Timothy Bretl
Abstract: This work presents DLO-Splatting, an algorithm for estimating the 3D shape of Deformable Linear Objects (DLOs) from multi-view RGB images and gripper state information through prediction-update filtering. The DLO-Splatting algorithm uses a position-based dynamics model with shape smoothness and rigidity dampening corrections to predict the object shape. Optimization with a 3D Gaussian Splatting-based rendering loss iteratively renders and refines the prediction to align it with the visual observations in the update step. Initial experiments demonstrate promising results in a knot tying scenario, which is challenging for existing vision-only methods.
Authors: Shirin Shoushtari, Edward P. Chandler, M. Salman Asif, Ulugbek S. Kamilov
Abstract: Diffusion models are widely used as priors in imaging inverse problems. However, their performance often degrades under distribution shifts between the training and test-time images. Existing methods for identifying and quantifying distribution shifts typically require access to clean test images, which are almost never available while solving inverse problems (at test time). We propose a fully unsupervised metric for estimating distribution shifts using only indirect (corrupted) measurements and score functions from diffusion models trained on different datasets. We theoretically show that this metric estimates the KL divergence between the training and test image distributions. Empirically, we show that our score-based metric, using only corrupted measurements, closely approximates the KL divergence computed from clean images. Motivated by this result, we show that aligning the out-of-distribution score with the in-distribution score -- using only corrupted measurements -- reduces the KL divergence and leads to improved reconstruction quality across multiple inverse problems.
Authors: Rui Qin, Qijie Wang, Ming Sun, Haowei Zhu, Chao Zhou, Bin Wang
Abstract: Diffusion models have gained attention for their success in modeling complex distributions, achieving impressive perceptual quality in SR tasks. However, existing diffusion-based SR methods often suffer from high computational costs, requiring numerous iterative steps for training and inference. Existing acceleration techniques, such as distillation and solver optimization, are generally task-agnostic and do not fully leverage the specific characteristics of low-level tasks like super-resolution (SR). In this study, we analyze the frequency- and spatial-domain properties of diffusion-based SR methods, revealing key insights into the temporal and spatial dependencies of high-frequency signal recovery. Specifically, high-frequency details benefit from concentrated optimization during early and late diffusion iterations, while spatially textured regions demand adaptive denoising strategies. Building on these observations, we propose the Time-Spatial-aware Sampling strategy (TSS) for the acceleration of Diffusion SR without any extra training cost. TSS combines Time Dynamic Sampling (TDS), which allocates more iterations to refining textures, and Spatial Dynamic Sampling (SDS), which dynamically adjusts strategies based on image content. Extensive evaluations across multiple benchmarks demonstrate that TSS achieves state-of-the-art (SOTA) performance with significantly fewer iterations, improving MUSIQ scores by 0.2 - 3.0 and outperforming the current acceleration methods with only half the number of steps.
Authors: Yuqi Liu, Tianyuan Qu, Zhisheng Zhong, Bohao Peng, Shu Liu, Bei Yu, Jiaya Jia
Abstract: Large vision-language models exhibit inherent capabilities to handle diverse visual perception tasks. In this paper, we introduce VisionReasoner, a unified framework capable of reasoning and solving multiple visual perception tasks within a shared model. Specifically, by designing novel multi-object cognitive learning strategies and systematic task reformulation, VisionReasoner enhances its reasoning capabilities to analyze visual inputs, and addresses diverse perception tasks in a unified framework. The model generates a structured reasoning process before delivering the desired outputs responding to user queries. To rigorously assess unified visual perception capabilities, we evaluate VisionReasoner on ten diverse tasks spanning three critical domains: detection, segmentation, and counting. Experimental results show that VisionReasoner achieves superior performance as a unified model, outperforming Qwen2.5VL by relative margins of 29.1% on COCO (detection), 22.1% on ReasonSeg (segmentation), and 15.3% on CountBench (counting).
Authors: Yang Liu, Ming Ma, Xiaomin Yu, Pengxiang Ding, Han Zhao, Mingyang Sun, Siteng Huang, Donglin Wang
Abstract: Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either require specialized sensors or fail to effectively exploit depth information for higher-order reasoning. To this end, we propose a novel Spatial Sense and Reasoning method, dubbed SSR, a novel framework that transforms raw depth data into structured, interpretable textual rationales. These textual rationales serve as meaningful intermediate representations to significantly enhance spatial reasoning capabilities. Additionally, we leverage knowledge distillation to compress the generated rationales into compact latent embeddings, which facilitate resource-efficient and plug-and-play integration into existing VLMs without retraining. To enable comprehensive evaluation, we introduce a new dataset named SSR-CoT, a million-scale visual-language reasoning dataset enriched with intermediate spatial reasoning annotations, and present SSRBench, a comprehensive multi-task benchmark. Extensive experiments on multiple benchmarks demonstrate SSR substantially improves depth utilization and enhances spatial reasoning, thereby advancing VLMs toward more human-like multi-modal understanding. Our project page is at https://yliu-cs.github.io/SSR.
Authors: Shaobin Zhuang, Zhipeng Huang, Ying Zhang, Fangyikang Wang, Canmiao Fu, Binxin Yang, Chong Sun, Chen Li, Yali Wang
Abstract: GPT has shown its remarkable success in natural language processing. However, the language sequence is not sufficient to describe spatial-temporal details in the visual world. Alternatively, the video sequence is good at capturing such details. Motivated by this fact, we propose a concise Video-GPT in this paper by treating video as new language for visual world modeling. By analogy to next token prediction in GPT, we introduce a novel next clip diffusion paradigm for pretraining Video-GPT. Different from the previous works, this distinct paradigm allows Video-GPT to tackle both short-term generation and long-term prediction, by autoregressively denoising the noisy clip according to the clean clips in the history. Extensive experiments show our Video-GPT achieves the state-of-the-art performance on video prediction, which is the key factor towards world modeling (Physics-IQ Benchmark: Video-GPT 34.97 vs. Kling 23.64 vs. Wan 20.89). Moreover, it can be well adapted on 6 mainstream video tasks in both video generation and understanding, showing its great generalization capacity in downstream. The project page is at https://zhuangshaobin.github.io/Video-GPT.github.io/.
Authors: Mia Thomas, Trevor Ablett, Jonathan Kelly
Abstract: Unmanned aerial vehicles (UAVs) enable operations in remote and hazardous environments, yet the visible-spectrum, camera-based navigation systems often relied upon by UAVs struggle in low-visibility conditions. Thermal cameras, which capture long-wave infrared radiation, are able to function effectively in darkness and smoke, where visible-light cameras fail. This work explores learned cross-spectral (thermal-visible) point features as a means to integrate thermal imagery into established camera-based navigation systems. Existing methods typically train a feature network's detection and description outputs directly, which often focuses training on image regions where thermal and visible-spectrum images exhibit similar appearance. Aiming to more fully utilize the available data, we propose a method to train the feature network on the tasks of matching and registration. We run our feature network on thermal-visible image pairs, then feed the network response into a differentiable registration pipeline. Losses are applied to the matching and registration estimates of this pipeline. Our selected model, trained on the task of matching, achieves a registration error (corner error) below 10 pixels for more than 75% of estimates on the MultiPoint dataset. We further demonstrate that our model can also be used with a classical pipeline for matching and registration.
Authors: Haiquan Wen, Yiwei He, Zhenglin Huang, Tianxiao Li, Zihan Yu, Xingru Huang, Lu Qi, Baoyuan Wu, Xiangtai Li, Guangliang Cheng
Abstract: Advances in AI generative models facilitate super-realistic video synthesis, amplifying misinformation risks via social media and eroding trust in digital content. Several research works have explored new deepfake detection methods on AI-generated images to alleviate these risks. However, with the fast development of video generation models, such as Sora and WanX, there is currently a lack of large-scale, high-quality AI-generated video datasets for forgery detection. In addition, existing detection approaches predominantly treat the task as binary classification, lacking explainability in model decision-making and failing to provide actionable insights or guidance for the public. To address these challenges, we propose \textbf{GenBuster-200K}, a large-scale AI-generated video dataset featuring 200K high-resolution video clips, diverse latest generative techniques, and real-world scenes. We further introduce \textbf{BusterX}, a novel AI-generated video detection and explanation framework leveraging multimodal large language model (MLLM) and reinforcement learning for authenticity determination and explainable rationale. To our knowledge, GenBuster-200K is the {\it \textbf{first}} large-scale, high-quality AI-generated video dataset that incorporates the latest generative techniques for real-world scenarios. BusterX is the {\it \textbf{first}} framework to integrate MLLM with reinforcement learning for explainable AI-generated video detection. Extensive comparisons with state-of-the-art methods and ablation studies validate the effectiveness and generalizability of BusterX. The code, models, and datasets will be released.
Authors: Zekai Li, Xinhao Zhong, Samir Khaki, Zhiyuan Liang, Yuhao Zhou, Mingjia Shi, Ziqiao Wang, Xuanlei Zhao, Wangbo Zhao, Ziheng Qin, Mengxuan Wu, Pengfei Zhou, Haonan Wang, David Junhao Zhang, Jia-Wei Liu, Shaobo Wang, Dai Liu, Linfeng Zhang, Guang Li, Kun Wang, Zheng Zhu, Zhiheng Ma, Joey Tianyi Zhou, Jiancheng Lv, Yaochu Jin, Peihao Wang, Kaipeng Zhang, Lingjuan Lyu, Yiran Huang, Zeynep Akata, Zhiwei Deng, Xindi Wu, George Cazenavette, Yuzhang Shang, Justin Cui, Jindong Gu, Qian Zheng, Hao Ye, Shuo Wang, Xiaobo Wang, Yan Yan, Angela Yao, Mike Zheng Shou, Tianlong Chen, Hakan Bilen, Baharan Mirzasoleiman, Manolis Kellis, Konstantinos N. Plataniotis, Zhangyang Wang, Bo Zhao, Yang You, Kai Wang
Abstract: In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets. To further improve the performance of synthetic datasets, various training pipelines and optimization objectives have been proposed, greatly advancing the field of dataset distillation. Recent decoupled dataset distillation methods introduce soft labels and stronger data augmentation during the post-evaluation phase and scale dataset distillation up to larger datasets (e.g., ImageNet-1K). However, this raises a question: Is accuracy still a reliable metric to fairly evaluate dataset distillation methods? Our empirical findings suggest that the performance improvements of these methods often stem from additional techniques rather than the inherent quality of the images themselves, with even randomly sampled images achieving superior results. Such misaligned evaluation settings severely hinder the development of DD. Therefore, we propose DD-Ranking, a unified evaluation framework, along with new general evaluation metrics to uncover the true performance improvements achieved by different methods. By refocusing on the actual information enhancement of distilled datasets, DD-Ranking provides a more comprehensive and fair evaluation standard for future research advancements.
Authors: Peiyuan Zhang, Haofeng Huang, Yongqi Chen, Will Lin, Zhengzhong Liu, Ion Stoica, Eric Xing, Hao Zhang
Abstract: Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient sparse attention that replaces full attention at \emph{both} training and inference. In VSA, a lightweight coarse stage pools tokens into tiles and identifies high-weight \emph{critical tokens}; a fine stage computes token-level attention only inside those tiles subjecting to block computing layout to ensure hard efficiency. This leads to a single differentiable kernel that trains end-to-end, requires no post-hoc profiling, and sustains 85\% of FlashAttention3 MFU. We perform a large sweep of ablation studies and scaling-law experiments by pretraining DiTs from 60M to 1.4B parameters. VSA reaches a Pareto point that cuts training FLOPS by 2.53$\times$ with no drop in diffusion loss. Retrofitting the open-source Wan-2.1 model speeds up attention time by 6$\times$ and lowers end-to-end generation time from 31s to 18s with comparable quality. These results establish trainable sparse attention as a practical alternative to full attention and a key enabler for further scaling of video diffusion models.
Authors: Qianqian Zhang, WeiJun Wang, Yunxing Liu, Li Zhou, Hao Zhao, Junshe An, Zihan Wang
Abstract: Target detection in high-resolution remote sensing imagery faces challenges due to the low recognition accuracy of small targets and high computational costs. The computational complexity of the Transformer architecture increases quadratically with image resolution, while Convolutional Neural Networks (CNN) architectures are forced to stack deeper convolutional layers to expand their receptive fields, leading to an explosive growth in computational demands. To address these computational constraints, we leverage Mamba's linear complexity for efficiency. However, Mamba's performance declines for small targets, primarily because small targets occupy a limited area in the image and have limited semantic information. Accurate identification of these small targets necessitates not only Mamba's global attention capabilities but also the precise capture of fine local details. To this end, we enhance Mamba by developing the Enhanced Small Target Detection (ESTD) module and the Convolutional Attention Residual Gate (CARG) module. The ESTD module bolsters local attention to capture fine-grained details, while the CARG module, built upon Mamba, emphasizes spatial and channel-wise information, collectively improving the model's ability to capture distinctive representations of small targets. Additionally, to highlight the semantic representation of small targets, we design a Mask Enhanced Pixel-level Fusion (MEPF) module for multispectral fusion, which enhances target features by effectively fusing visible and infrared multimodal information.
Authors: Qianxiong Xu, Lanyun Zhu, Xuanyi Liu, Guosheng Lin, Cheng Long, Ziyue Li, Rui Zhao
Abstract: Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use the well-learned knowledge of foundation models (e.g., SAM) to simplify the learning process. Recently, SAM 2 has extended SAM by supporting video segmentation, whose class-agnostic matching ability is useful to FSS. A simple idea is to encode support foreground (FG) features as memory, with which query FG features are matched and fused. Unfortunately, the FG objects in different frames of SAM 2's video data are always the same identity, while those in FSS are different identities, i.e., the matching step is incompatible. Therefore, we design Pseudo Prompt Generator to encode pseudo query memory, matching with query features in a compatible way. However, the memories can never be as accurate as the real ones, i.e., they are likely to contain incomplete query FG, and some unexpected query background (BG) features, leading to wrong segmentation. Hence, we further design Iterative Memory Refinement to fuse more query FG features into the memory, and devise a Support-Calibrated Memory Attention to suppress the unexpected query BG features in memory. Extensive experiments have been conducted on PASCAL-5$^i$ and COCO-20$^i$ to validate the effectiveness of our design, e.g., the 1-shot mIoU can be 4.2% better than the best baseline.
Authors: Zhihao Li, Yufei Wang, Heliang Zheng, Yihao Luo, Bihan Wen
Abstract: High-fidelity 3D object synthesis remains significantly more challenging than 2D image generation due to the unstructured nature of mesh data and the cubic complexity of dense volumetric grids. Existing two-stage pipelines-compressing meshes with a VAE (using either 2D or 3D supervision), followed by latent diffusion sampling-often suffer from severe detail loss caused by inefficient representations and modality mismatches introduced in VAE. We introduce Sparc3D, a unified framework that combines a sparse deformable marching cubes representation Sparcubes with a novel encoder Sparconv-VAE. Sparcubes converts raw meshes into high-resolution ($1024^3$) surfaces with arbitrary topology by scattering signed distance and deformation fields onto a sparse cube, allowing differentiable optimization. Sparconv-VAE is the first modality-consistent variational autoencoder built entirely upon sparse convolutional networks, enabling efficient and near-lossless 3D reconstruction suitable for high-resolution generative modeling through latent diffusion. Sparc3D achieves state-of-the-art reconstruction fidelity on challenging inputs, including open surfaces, disconnected components, and intricate geometry. It preserves fine-grained shape details, reduces training and inference cost, and integrates naturally with latent diffusion models for scalable, high-resolution 3D generation.
Authors: Changze Lv, Tianlong Li, Wenhao Liu, Yufei Gu, Jianhan Xu, Cenyuan Zhang, Muling Wu, Xiaoqing Zheng, Xuanjing Huang
Abstract: Spiking Neural Networks (SNNs) have emerged as a promising alternative to conventional Artificial Neural Networks (ANNs), demonstrating comparable performance in both visual and linguistic tasks while offering the advantage of improved energy efficiency. Despite these advancements, the integration of linguistic and visual features into a unified representation through spike trains poses a significant challenge, and the application of SNNs to multimodal scenarios remains largely unexplored. This paper presents SpikeCLIP, a novel framework designed to bridge the modality gap in spike-based computation. Our approach employs a two-step recipe: an ``alignment pre-training'' to align features across modalities, followed by a ``dual-loss fine-tuning'' to refine the model's performance. Extensive experiments reveal that SNNs achieve results on par with ANNs while substantially reducing energy consumption across various datasets commonly used for multimodal model evaluation. Furthermore, SpikeCLIP maintains robust image classification capabilities, even when dealing with classes that fall outside predefined categories. This study marks a significant advancement in the development of energy-efficient and biologically plausible multimodal learning systems. Our code is available at https://github.com/Lvchangze/SpikeCLIP.
Authors: Luigi Sigillo, Eleonora Grassucci, Aurelio Uncini, Danilo Comminiello
Abstract: Neural network generalizability is becoming a broad research field due to the increasing availability of datasets from different sources and for various tasks. This issue is even wider when processing medical data, where a lack of methodological standards causes large variations being provided by different imaging centers or acquired with various devices and cofactors. To overcome these limitations, we introduce a novel, generalizable, data- and task-agnostic framework able to extract salient features from medical images. The proposed quaternion wavelet network (QUAVE) can be easily integrated with any pre-existing medical image analysis or synthesis task, and it can be involved with real, quaternion, or hypercomplex-valued models, generalizing their adoption to single-channel data. QUAVE first extracts different sub-bands through the quaternion wavelet transform, resulting in both low-frequency/approximation bands and high-frequency/fine-grained features. Then, it weighs the most representative set of sub-bands to be involved as input to any other neural model for image processing, replacing standard data samples. We conduct an extensive experimental evaluation comprising different datasets, diverse image analysis, and synthesis tasks including reconstruction, segmentation, and modality translation. We also evaluate QUAVE in combination with both real and quaternion-valued models. Results demonstrate the effectiveness and the generalizability of the proposed framework that improves network performance while being flexible to be adopted in manifold scenarios and robust to domain shifts. The full code is available at: https://github.com/ispamm/QWT.
Authors: Peng Kuang, Zhibo Wang, Zhixuan Chu, Jingyi Wang, Kui Ren
Abstract: Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts, leading to the proposition of numberous debiasing methods. However, it remains to be asked: \textit{Do existing benchmarks for debiasing really represent biases in the real world?} Recent works attempt to address such concerns by sampling from real-world data (instead of synthesizing) according to some predefined biased distributions to ensure the realism of individual samples. However, the realism of the biased distribution is more critical yet challenging and underexplored due to the complexity of real-world bias distributions. To tackle the problem, we propose a fine-grained framework for analyzing biased distributions, based on which we empirically and theoretically identify key characteristics of biased distributions in the real world that are poorly represented by existing benchmarks. Towards applicable debiasing in the real world, we further introduce two novel real-world-inspired biases to bridge this gap and build a systematic evaluation framework for real-world debiasing, RDBench\footnote{RDBench: Code to be released. Preliminary version in supplementary material for anonimized review.}. Furthermore, focusing on the practical setting of debiasing w/o bias label, we find real-world biases pose a novel \textit{Sparse bias capturing} challenge to the existing paradigm. We propose a simple yet effective approach named Debias in Destruction (DiD), to address the challenge, whose effectiveness is validated with extensive experiments on 8 datasets of various biased distributions.
Authors: Zizhao Chen, Mustafa Omer Gul, Yiwei Chen, Gloria Geng, Anne Wu, Yoav Artzi
Abstract: Multi-turn interactions between large language models (LLMs) and users naturally include implicit feedback signals. If an LLM responds in an unexpected way to an instruction, the user is likely to signal it by rephrasing the request, expressing frustration, or pivoting to an alternative task. Such signals are task-independent and occupy a relatively constrained subspace of language, allowing the LLM to identify them even if it fails on the actual task. We introduce ReSpect, a method to learn from such signals in past interactions via retrospection without additional annotations. We deploy ReSpect in a new multimodal interaction scenario, where humans instruct a multimodal LLM to solve an abstract reasoning task with a combinatorial solution space. Through thousands of interactions with humans, we show how ReSpect gradually improves task completion rate from 31% to 82%, all without any external annotation.
Authors: Sobhan Hemati, Ghazal Alabtah, Saghir Alfasly, H. R. Tizhoosh
Abstract: A crucial step to efficiently integrate Whole Slide Images (WSIs) in computational pathology is assigning a single high-quality feature vector, i.e., one embedding, to each WSI. With the existence of many pre-trained deep neural networks and the emergence of foundation models, extracting embeddings for sub-images (i.e., tiles or patches) is straightforward. However, for WSIs, given their high resolution and gigapixel nature, inputting them into existing GPUs as a single image is not feasible. As a result, WSIs are usually split into many patches. Feeding each patch to a pre-trained model, each WSI can then be represented by a set of patches, hence, a set of embeddings. Hence, in such a setup, WSI representation learning reduces to set representation learning where for each WSI we have access to a set of patch embeddings. To obtain a single embedding from a set of patch embeddings for each WSI, multiple set-based learning schemes have been proposed in the literature. In this paper, we evaluate the WSI search performance of multiple recently developed aggregation techniques (mainly set representation learning techniques) including simple average or max pooling operations, Deep Sets, Memory networks, Focal attention, Gaussian Mixture Model (GMM) Fisher Vector, and deep sparse and binary Fisher Vector on four different primary sites including bladder, breast, kidney, and Colon from TCGA. Further, we benchmark the search performance of these methods against the median of minimum distances of patch embeddings, a non-aggregating approach used for WSI retrieval.
Authors: Indrashis Das, Mahmoud Safari, Steven Adriaensen, Frank Hutter
Abstract: Activation functions are fundamental elements of deep learning architectures as they significantly influence training dynamics. ReLU, while widely used, is prone to the dying neuron problem, which has been mitigated by variants such as LeakyReLU, PReLU, and ELU that better handle negative neuron outputs. Recently, self-gated activations like GELU and Swish have emerged as state-of-the-art alternatives, leveraging their smoothness to ensure stable gradient flow and prevent neuron inactivity. In this work, we introduce the Gompertz Linear Unit (GoLU), a novel self-gated activation function defined as $\mathrm{GoLU}(x) = x \, \mathrm{Gompertz}(x)$, where $\mathrm{Gompertz}(x) = e^{-e^{-x}}$. The GoLU activation leverages the right-skewed asymmetry in the Gompertz function to reduce variance in the latent space more effectively compared to GELU and Swish, while preserving robust gradient flow. Extensive experiments across diverse tasks, including Image Classification, Language Modeling, Semantic Segmentation, Object Detection, Instance Segmentation, and Diffusion, highlight GoLU's superior performance relative to state-of-the-art activation functions, establishing GoLU as a robust alternative to existing activation functions.
Authors: Jiwan Chung, Saejin Kim, Yongrae Jo, Jaewoo Park, Dongjun Min, Youngjae Yu
Abstract: As large language models expand beyond natural language to domains such as mathematics, multimodal understanding, and embodied agents, tokens increasingly reflect metric relationships rather than purely linguistic meaning. We introduce DIST2Loss, a distance-aware framework designed to train autoregressive discrete models by leveraging predefined distance relationships among output tokens. At its core, DIST2Loss transforms continuous exponential family distributions derived from inherent distance metrics into discrete, categorical optimization targets compatible with the models' architectures. This approach enables the models to learn and preserve meaningful distance relationships during token generation while maintaining compatibility with existing architectures. Empirical evaluations show consistent performance gains in diverse multimodal applications, including visual grounding, robotic manipulation, generative reward modeling, and image generation using vector-quantized features. These improvements are most notable in low-data regimes, demonstrating DIST2Loss's strength under resource constraints.
Authors: Tianyu Chen, Yasi Zhang, Zhendong Wang, Ying Nian Wu, Oscar Leong, Mingyuan Zhou
Abstract: Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn meaningful distributions from corrupted samples. This limitation restricts their applicability in scientific domains where clean data is scarce or costly to obtain. In this work, we introduce denoising score distillation (DSD), a surprisingly effective and novel approach for training high-quality generative models from low-quality data. DSD first pretrains a diffusion model exclusively on noisy, corrupted samples and then distills it into a one-step generator capable of producing refined, clean outputs. While score distillation is traditionally viewed as a method to accelerate diffusion models, we show that it can also significantly enhance sample quality, particularly when starting from a degraded teacher model. Across varying noise levels and datasets, DSD consistently improves generative performancewe summarize our empirical evidence in Fig. 1. Furthermore, we provide theoretical insights showing that, in a linear model setting, DSD identifies the eigenspace of the clean data distributions covariance matrix, implicitly regularizing the generator. This perspective reframes score distillation as not only a tool for efficiency but also a mechanism for improving generative models, particularly in low-quality data settings.
Authors: Ziqing Fan, Cheng Liang, Chaoyi Wu, Ya Zhang, Yanfeng Wang, Weidi Xie
Abstract: Recent advances in reasoning-enhanced large language models (LLMs) and multimodal LLMs (MLLMs) have significantly improved performance in complex tasks, yet medical AI models often overlook the structured reasoning processes inherent in clinical practice. In this work, we present ChestX-Reasoner, a radiology diagnosis MLLM designed to leverage process supervision mined directly from clinical reports, reflecting the step-by-step reasoning followed by radiologists. We construct a large dataset by extracting and refining reasoning chains from routine radiology reports. Our two-stage training framework combines supervised fine-tuning and reinforcement learning guided by process rewards to better align model reasoning with clinical standards. We introduce RadRBench-CXR, a comprehensive benchmark featuring 59K visual question answering samples with 301K clinically validated reasoning steps, and propose RadRScore, a metric evaluating reasoning factuality, completeness, and effectiveness. ChestX-Reasoner outperforms existing medical and general-domain MLLMs in both diagnostic accuracy and reasoning ability, achieving 16%, 5.9%, and 18% improvements in reasoning ability compared to the best medical MLLM, the best general MLLM, and its base model, respectively, as well as 3.3%, 24%, and 27% improvements in outcome accuracy. All resources are open-sourced to facilitate further research in medical reasoning MLLMs.
Authors: Edson Araujo, Andrew Rouditchenko, Yuan Gong, Saurabhchand Bhati, Samuel Thomas, Brian Kingsbury, Leonid Karlinsky, Rogerio Feris, James R. Glass, Hilde Kuehne
Abstract: Recent advances in audio-visual learning have shown promising results in learning representations across modalities. However, most approaches rely on global audio representations that fail to capture fine-grained temporal correspondences with visual frames. Additionally, existing methods often struggle with conflicting optimization objectives when trying to jointly learn reconstruction and cross-modal alignment. In this work, we propose CAV-MAE Sync as a simple yet effective extension of the original CAV-MAE framework for self-supervised audio-visual learning. We address three key challenges: First, we tackle the granularity mismatch between modalities by treating audio as a temporal sequence aligned with video frames, rather than using global representations. Second, we resolve conflicting optimization goals by separating contrastive and reconstruction objectives through dedicated global tokens. Third, we improve spatial localization by introducing learnable register tokens that reduce semantic load on patch tokens. We evaluate the proposed approach on AudioSet, VGG Sound, and the ADE20K Sound dataset on zero-shot retrieval, classification and localization tasks demonstrating state-of-the-art performance and outperforming more complex architectures.
Authors: Xuyang Wang, Siyuan Duan, Qizhi Li, Guiduo Duan, Yuan Sun, Dezhong Peng
Abstract: Trustworthy multi-view learning has attracted extensive attention because evidence learning can provide reliable uncertainty estimation to enhance the credibility of multi-view predictions. Existing trusted multi-view learning methods implicitly assume that multi-view data is secure. However, in safety-sensitive applications such as autonomous driving and security monitoring, multi-view data often faces threats from adversarial perturbations, thereby deceiving or disrupting multi-view models. This inevitably leads to the adversarial unreliability problem (AUP) in trusted multi-view learning. To overcome this tricky problem, we propose a novel multi-view learning framework, namely Reliable Disentanglement Multi-view Learning (RDML). Specifically, we first propose evidential disentanglement learning to decompose each view into clean and adversarial parts under the guidance of corresponding evidences, which is extracted by a pretrained evidence extractor. Then, we employ the feature recalibration module to mitigate the negative impact of adversarial perturbations and extract potential informative features from them. Finally, to further ignore the irreparable adversarial interferences, a view-level evidential attention mechanism is designed. Extensive experiments on multi-view classification tasks with adversarial attacks show that RDML outperforms the state-of-the-art methods by a relatively large margin. Our code is available at https://github.com/Willy1005/2025-IJCAI-RDML.
Authors: Radek Osmulski, Gabriel de Souza P. Moreira, Ronay Ak, Mengyao Xu, Benedikt Schifferer, Even Oldridge
Abstract: Document retrieval is an important task for search and Retrieval-Augmented Generation (RAG) applications. Large Language Models (LLMs) have contributed to improving the accuracy of text-based document retrieval. However, documents with complex layout and visual elements like tables, charts and infographics are not perfectly represented in textual format. Recently, image-based document retrieval pipelines have become popular, which use visual large language models (VLMs) to retrieve relevant page images given a query. Current evaluation benchmarks on visual document retrieval are limited, as they primarily focus only English language, rely on synthetically generated questions and offer a small corpus size. Therefore, we introduce MIRACL-VISION, a multilingual visual document retrieval evaluation benchmark. MIRACL-VISION covers 18 languages, and is an extension of the MIRACL dataset, a popular benchmark to evaluate text-based multilingual retrieval pipelines. MIRACL was built using a human-intensive annotation process to generate high-quality questions. In order to reduce MIRACL-VISION corpus size to make evaluation more compute friendly while keeping the datasets challenging, we have designed a method for eliminating the "easy" negatives from the corpus. We conducted extensive experiments comparing MIRACL-VISION with other benchmarks, using popular public text and image models. We observe a gap in state-of-the-art VLM-based embedding models on multilingual capabilities, with up to 59.7% lower retrieval accuracy than a text-based retrieval models. Even for the English language, the visual models retrieval accuracy is 12.1% lower compared to text-based models. MIRACL-VISION is a challenging, representative, multilingual evaluation benchmark for visual retrieval pipelines and will help the community build robust models for document retrieval.
Authors: Qianyue Hu, Junyan Wu, Wei Lu, Xiangyang Luo
Abstract: Diffusion Models (DMs) have achieved remarkable success in realistic voice cloning (VC), while they also increase the risk of malicious misuse. Existing proactive defenses designed for traditional VC models aim to disrupt the forgery process, but they have been proven incompatible with DMs due to the intricate generative mechanisms of diffusion. To bridge this gap, we introduce VoiceCloak, a multi-dimensional proactive defense framework with the goal of obfuscating speaker identity and degrading perceptual quality in potential unauthorized VC. To achieve these goals, we conduct a focused analysis to identify specific vulnerabilities within DMs, allowing VoiceCloak to disrupt the cloning process by introducing adversarial perturbations into the reference audio. Specifically, to obfuscate speaker identity, VoiceCloak first targets speaker identity by distorting representation learning embeddings to maximize identity variation, which is guided by auditory perception principles. Additionally, VoiceCloak disrupts crucial conditional guidance processes, particularly attention context, thereby preventing the alignment of vocal characteristics that are essential for achieving convincing cloning. Then, to address the second objective, VoiceCloak introduces score magnitude amplification to actively steer the reverse trajectory away from the generation of high-quality speech. Noise-guided semantic corruption is further employed to disrupt structural speech semantics captured by DMs, degrading output quality. Extensive experiments highlight VoiceCloak's outstanding defense success rate against unauthorized diffusion-based voice cloning.
Authors: Umberto Cappellazzo, Minsu Kim, Stavros Petridis, Daniele Falavigna, Alessio Brutti
Abstract: Audio-Visual Speech Recognition (AVSR) enhances robustness in noisy environments by integrating visual cues. While recent advances integrate Large Language Models (LLMs) into AVSR, their high computational cost hinders deployment in resource-constrained settings. To address this, we propose Llama-SMoP, an efficient Multimodal LLM that employs a Sparse Mixture of Projectors (SMoP) module to scale model capacity without increasing inference costs. By incorporating sparsely-gated mixture-of-experts (MoE) projectors, Llama-SMoP enables the use of smaller LLMs while maintaining strong performance. We explore three SMoP configurations and show that Llama-SMoP DEDR (Disjoint-Experts, Disjoint-Routers), which uses modality-specific routers and experts, achieves superior performance on ASR, VSR, and AVSR tasks. Ablation studies confirm its effectiveness in expert activation, scalability, and noise robustness.