Subtle visual signals,though often imperceptible to the human eye,contain subtle yet crucial information that can reveal hidden patterns within visual data.The ability to detect and analyze subtle signals has profound implications across various fields,e.g.,1)from medicine,where early identification of minute anomalies in medical imaging can lead to life-saving interventions,2)from in-dustry,where spotting micro-defects in production lines can prevent costly failures,3)from affective computing,where understanding micro-expression,micro-gesture,and hidden physiological signals under human interaction scenarios can benefit the deception detection.The capa-city to detect and decode these"subtle visual signals"of-fers a novel and powerful approach to anticipating trends,identifying emerging threats,and discovering new oppor-tunities.

Video saliency detection models have been achieving steady, significant improvements thanks to rapid advances in deep learning and the wide availability of large-scale training sets. However, deep learning-based visual-audio fixation prediction is still in its infancy. At present, only a few visual-audio sequences have been furnished, with real fixations being recorded in real visual-audio environments. Hence, it would neither be efficient nor necessary to recollect real fixations under the same visual-audio circumstances. To address this problem, this paper promotes a novel weakly supervised approach that alleviates the demand for large-scale training sets for visual-audio model training. By using only the video category tags, we propose the selective class activation mapping (SCAM) and its upgrade (SCAM+). In the spatial-temporal-audio circumstance, the former follows a coarse-to-fine strategy to select the most discriminative regions, which are usually capable of exhibiting high consistency with real human-eye fixations. The latter equips the SCAM with an additional multigranularity perception mechanism, making the whole process more consistent with that of the real human visual-audio system. Moreover, we distill knowledge from these regions to obtain completely new spatial-temporal-audio (STA) fixation prediction (FP) networks, enabling broad applications when video tags are unavailable. Without resorting to any real human-eye fixation, the performances of these STAFP networks are comparable to those of fully supervised networks. The code and results are publicly available at https://github.com/guotaowang/STANet .

Colonoscopy is currently one of the most sensitive screening methods for colorectal cancer. This study investigates the frontiers of intelligent colonoscopy techniques and their prospective implications for multimodal medical applications. With this goal, we begin by assessing the current data-centric and model-centric landscapes through four tasks for colonoscopic scene perception, including classification, detection, segmentation, and vision-language understanding. Our assessment reveals domain-specific challenges and underscores the need for further multimodal research in colonoscopy. To address these gaps, we establish three foundational initiatives: a large-scale multimodal instruction tuning dataset ColonINST, a colonoscopy-designed multimodal language model ColonGPT, and a multimodal benchmark. To facilitate continuous advancements in this rapidly evolving field, we provide a public website for the latest updates: https://github.com/ai4colonoscopy/IntelliScope .

Deep learning is developing rapidly and handling common computer vision tasks well. It is time to pay attention to more complex vision tasks, as model size, knowledge, and reasoning capabilities continue to improve. In this paper, we introduce and review a family of complex tasks, termed Concealed Dense Prediction (CDP), which has great value in agriculture, industry, etc. CDP's intrinsic trait is that the targets are concealed in their surroundings, thus fully perceiving them requires fine-grained representations, prior knowledge, auxiliary reasoning, etc. The contributions of this review are three-fold: (i) We introduce the scope, characteristics, and challenges specific to CDP tasks and emphasize their essential differences from generic vision tasks. (ii) We develop a taxonomy based on concealment counteracting to summarize deep learning efforts in CDP through experiments on three tasks. We compare 25 state-of-the-art methods across 12 widely used concealed datasets. (iii) We discuss the potential applications of CDP in the large model era and summarize 6 potential research directions. We offer perspectives for the future development of CDP by constructing a large-scale multimodal instruction fine-tuning dataset, CvpINST, and a concealed visual perception agent, CvpAgent.

Salient object detection (SOD) and camouflaged object detection (COD) are related but distinct binary mapping tasks, each involving multiple modalities that share commonalities while maintaining unique characteristics. Existing approaches often rely on complex, task-specific architectures, leading to redundancy and limited generalization. Our previous work, VSCode, introduced a generalist model that effectively handles four SOD tasks and two COD tasks. VSCode leveraged VST as its foundation model and incorporated 2D prompts within an encoder-decoder framework to capture domain and task-specific knowledge, utilizing a prompt discrimination loss to optimize the model. Building upon the proven effectiveness of our previous work VSCode, we identify opportunities to further strengthen generalization capabilities through focused modifications in model design and optimization strategy. To unlock this potential, we propose VSCode-v2, an extension that introduces a Mixture of Prompt Experts (MoPE) layer to generate adaptive prompts. We also redesign the training process into a two-stage approach: first learning shared features across tasks, then capturing specific characteristics. To preserve knowledge during this process, we incorporate distillation from our conference version model. Furthermore, we propose a contrastive learning mechanism with data augmentation to strengthen the relationships between prompts and feature representations. VSCode-v2 demonstrates balanced performance improvements across six SOD and COD tasks. Moreover, VSCode-v2 effectively handles various multimodal inputs and exhibits zero-shot generalization capability to novel tasks, such as RGB-D Video SOD.

Prompt learning for vision-language models (VLMs) primarily follows end-to-end or decoupled routes to balance base and new task performance, but suffers a fundamental bottleneck: sample-wise optimization within task-specific feature spaces traps models in local optima, hindering global optimality. To address this, we identify a key insight that VLMs can be prompted within a Coupled Prompt Field-a shared space where base and new tasks are mutually constrained-and present AlignedNorm, which enforces the field coupling. By dynamically aligning the norms of prompts to VLMs' native scale, our method enables joint optimization of both tasks. Without complex designs, our method matches leading decoupled approaches on 15 datasets across 4 experimental settings, offering both a new perspective and a practical solution to the local-optima dilemma in prompt learning.

Ultrasound (US) imaging plays a crucial role in diagnosing heart and pelvic diseases, where sonographers tend to evaluate dynamic motion and structure. However, the scarcity of US videos for rare cases limitstraining opportunities for novice sonographers and deep learning models, hindering detection rates and clinical diagnostic applications. US video synthesis is a promising solution to this issue. Nevertheless, accurately imitating the intricate motion of the anatomy while preserving image fidelity presents asignificant challenge. In this work, we propose OnUVS, a novel online feature-decoupling framework for high-fidelity US video synthesis. First, to simulate realistic motion, we incorporate keypoints into anatomical learning through a weakly supervised training approach, which enhances motion representation and minimizes the need for fully annotated data. Second, we implement a dual-decoder generator that effectively balances content and textural features of generated frames, significantly enhancing the image fidelity of US videos. Third, a multi-scale discriminator further refines the sharpness and fine details, ensuring high-fidelity video synthesis. Fourth, an online learning strategy is designed to smooth coherence between frames by constraining the keypoint trajectories during inference. Validation on echocardiographic and pelvic floor US datasets demonstrates that OnUVS outperforms existing methods, achieving a 22.08% improvement in motion consistency (FVD) and 25.04% in image fidelity (FID).

Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject to a bias-variance tradeoff.Without sufficient structural constraints, excessive representationalvariance causes the model to collapse to trivial solutions.The recent LeWorldModel (LeWM) shows that this issue can be alleviated bysimply constraining latent embeddings with an isotropic Gaussian prior.However, latent representations inherently lie on low-dimensional manifoldswithin a high-dimensional ambient space, and enforcing an isotropic Gaussianprior directly in this ambient space introduces an overly strong bias.In this work, we propose ame, which seeks a favorable operatingpoint on the bias-variance frontier by applying Gaussian constraints inmultiple random subspaces rather than in the originalembedding space.This design relaxes the global constraint while preserving itsanti-collapse effect, leading to a better balance between trainingstability and representation flexibility.Extensive experiments across fourcontinuous-control environments demonstrate that consistentlyoutperforms LeWM with very clear margins.Our method is simple yet effective, and serves as a strong baseline for future JEPA-based world model research.fdefinedeeemodeThe code is available at https://github.com/intcomp/Sub-JEPA.

Open-vocabulary camouflaged object segmentation (OVCOS) seeks to segment and classify camouflaged objects in arbitrary categories, presenting unique challenges due to visual ambiguity and unseen categories. Recent approaches typically adopt a two-stage paradigm: they first segment objects, and then classify the segmented regions using vision language models (VLMs). However, such methods (i) suffer from a domain gap caused by the mismatch between VLMs' full-image training and cropped-region inferencing, and (ii) depend on generic segmentation models optimized for well-delineated objects which are less effective for camouflaged objects. Without explicit guidance, generic segmentation models often overlook subtle boundaries, leading to imprecise segmentation. In this paper, we introduce a novel VLM-guided cascaded framework to address these issues in OVCOS. For segmentation, we leverage the segment anything model (SAM), guided by the VLM. Our framework uses VLM-derived features as explicit prompts to SAM, effectively directing attention to camouflaged regions and significantly improving localization accuracy. For classification, we avoid the domain gap introduced by hard cropping. Instead, we treat the segmentation output as a soft spatial prior using the alpha channel. This retains the full image context while providing precise spatial guidance, leading to more accurate and context-aware classification of camouflaged objects. The same VLM is shared between segmentation and classification to ensure efficiency and semantic consistency. Extensive experiments on both OVCOS and conventional camouflaged object segmentation benchmarks demonstrate the clear superiority of our method, highlighting the effectiveness of leveraging rich VLM semantics for both segmentation and classification of camouflaged objects. Our code and models are open-sourced at https://github.com/intcomp/camouflaged-vlm.

Accurate medical image segmentation is essential for effective diagnosis and treatment. Previously we proposed PraNet-V1 as a means to enhance polyp segmentation, introducing a reverse attention (RA) module that utilizes background information. However, PraNet-V1 struggles with multiclass segmentation tasks. To address this limitation, we here propose PraNet-V2, which can effectively handle a broader range of tasks, including multiclass segmentation. At the core of PraNet-V2 is our dual-supervised reverse attention (DSRA) module, which incorporates explicit background supervision, independent background modeling, and semantically enriched attention fusion. Our PraNet-V2 framework exhibits strong performance on four polyp segmentation datasets. Moreover, the integration of DSRA into three state-of-the-art semantic segmentation models enables iterative refinement of foreground segmentation, yielding improvements of up to 1.36% in mean Dice score. Jittor code and supplementary materials are available at https://github.com/ai4colonoscopy/PraNet-V2/tree/main/binary_seg/jittor.

Recently, indiscernible/camouflaged scene understanding has attracted lots of research attention in the vision community. We further advance the frontier of this field by systematically studying a new challenge named indiscernible object counting (IOC), the goal of which is to count objects that are blended with respect to their surroundings. Due to a lack of appropriate IOC datasets, we present a large-scale dataset IOCfish5K which contains a total of 5,637 high-resolution images and 659,024 annotated center points. Our dataset consists of a large number of indiscernible objects (mainly fish) in underwater scenes, making the annotation process all the more challenging. IOCfish5K is superior to existing datasets with indiscernible scenes because of its larger scale, higher image resolutions, more annotations, and denser scenes. All these aspects make it the most challenging dataset for IOC so far, supporting progress in this area. Benefiting from the recent advancements of depth estimation foundation models, we construct high-quality depth maps for IOCfish5K by generating pseudo labels using the Depth Anything V2 model. The RGB-D version of IOCfish5K is named IOCfish5K-D. For benchmarking purposes on IOCfish5K, we select 16 mainstream methods for object counting and carefully evaluate them. For multimodal IOCfish5K-D, we evaluate other 4 popular multimodal counting methods. Furthermore, we propose IOCFormer, a new strong baseline that combines density and regression branches in a unified framework and can effectively tackle object counting under concealed scenes. We also propose IOCFormer-D to enable the effective usage of depth modality to help count objects hidden in their environments. Experiments show that IOCFormer and IOCFormer-D achieve state-of-the-art scores on IOCfish5K and IOCfish5K-D, respectively. The resources are publicly available at github.com/GuoleiSun/Indiscernible-Object-Counting .

To develop and validate the Q-Bone system, an intelligent quantitative system for anatomically driven assessment of alveolar bone loss and assistance in the diagnosis of periodontitis across multiple clinical centers and imaging devices. This study included 1,273 periodontitis cases from four clinical centers using diverse imaging devices. A multitask deep learning model, Deep Gradient Network (DGNet), was employed for tooth segmentation and anatomical keypoint localization, and was integrated with an anatomically driven, curvature-based quantification algorithm for alveolar bone resorption ratio (ABRR) measurement. Performance was evaluated using internal and multicenter external datasets, including patient-level agreement analysis for Stage, Grade, and Extent. The Q-Bone system demonstrated strong performance: tooth segmentation achieved an S-measure of 0.929, and keypoint localization reached a PRCK@0.5 of 0.994 in internal validation. Tooth-level ABRR showed high agreement with specialist measurements, with an ICC of 0.973 and minimal bias (− 0.238

Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer (CRC) in clinical practice. However, due to scale variation and blurry polyp boundaries, it is still a challenging task to achieve satisfactory segmentation performance with different scales and shapes. In this study, we present a novel Edge-aware Feature Aggregation Network (EFA-Net) for polyp segmentation, which can fully make use of cross-level and multi-scale features to enhance the performance of polyp segmentation. Specifically, we first present an Edge-aware Guidance Module (EGM) to combine the low-level features with the high-level features to learn an edge-enhanced feature, which is incorporated into each decoder unit using a layer-by-layer strategy. Besides, a Scale-aware Convolution Module (SCM) is proposed to learn scale-aware features by using dilated convolutions with different ratios, in order to effectively deal with scale variation. Further, a Cross-level Fusion Module (CFM) is proposed to effectively integrate the cross-level features, which can exploit the local and global contextual information. Finally, the outputs of CFMs are adaptively weighted by using the learned edge-aware feature, which are then used to produce multiple side-out segmentation maps. Experimental results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and effectiveness.

Existing concealed object segmentation (COS) methods frequently utilize reversible strategies to address uncertain regions. However, these approaches are typically restricted to the mask domain, leaving the potential of the RGB domain underexplored. To address this, we propose the Reversible Unfolding Network (RUN), which applies reversible strategies across both mask and RGB domains through a theoretically grounded framework, enabling accurate segmentation. RUN first formulates a novel COS model by incorporating an extra residual sparsity constraint to minimize segmentation uncertainties. The iterative optimization steps of the proposed model are then unfolded into a multistage network, with each step corresponding to a stage. Each stage of RUN consists of two reversible modules: the Segmentation-Oriented Foreground Separation (SOFS) module and the Reconstruction-Oriented Background Extraction (ROBE) module. SOFS applies the reversible strategy at the mask level and introduces Reversible State Space to capture non-local information. ROBE extends this to the RGB domain, employing a reconstruction network to address conflicting foreground and background regions identified as distortion-prone areas, which arise from their separate estimation by independent modules. As the stages progress, RUN gradually facilitates reversible modeling of foreground and background in both the mask and RGB domains, directing the network's attention to uncertain regions and mitigating false-positive and false-negative results. Extensive experiments demonstrate the superior performance of RUN and highlight the potential of unfolding-based frameworks for COS and other high-level vision tasks. We will release the code and models.

Pneumoconiosis is a severe occupational lung disease caused by long-term exposure to inhaled dust, early diagnosis is critical for effective management and health protection. However, current deep approaches struggle with the subtle radiographic manifestations of pneumoconiosis, strict diagnostic and limited data availability. In this paper, we propose Symmetric Local-Global Multi-Supervised (SLGMS), a novel framework inspired by the diagnostic practices of specialized radiologists. SLGMS a mechanism for generating symmetric global and local views with a symmetric VMamba feature network, effectively mimicking the region-by-region analysis and comparative assessment of symmetric performed by radiologists. Additionally, it incorporates a local-global knowledge distillation architecture tailored multi-supervised learning to explore relationships between local and global views while to clinical diagnostic criteria for pneumoconiosis. Evaluated on pneumoconiosis datasets collected medical hospitals in China, SLGMS demonstrates superior performance, achieving an average improvement of 6.19% in accuracy, sensitivity, specificity, and AUC metrics on the internal test set and 3.28% external validation dataset compared to state-of-the-art methods. On the public NIH ChestX-ray14 a transferable variant of SLGMS achieved a new state-of-the-art AUC of 82.9%, while the full SLGMS an average improvement of 3.5% on its supplemental fibrosis dataset. By bridging diagnostic prior with deep learning, SLGMS offers an effective paradigm for early diagnosis of occupational pneumoconiosis data-scarce environments, with broader applicability and scalability to other thoracic diseases.

Large models have accelerated the development of intelligent interpretation in remote sensing. Many remote sensing foundation models (RSFM) have emerged in recent years, sparking a new wave of deep learning in this field. Fine-tuning techniques serve as a bridge between remote sensing downstream tasks and advanced foundation models. As RSFMs become more powerful, fine-tuning techniques are expected to lead the next research frontier in numerous critical remote sensing applications. Advanced fine-tuning techniques can reduce the data and computational resource requirements during the downstream adaptation process. Current fine-tuning techniques for remote sensing are still in their early stages, leaving a large space for optimization and application. To elucidate the current development and future trends of remote sensing fine-tuning techniques, this survey offers a comprehensive overview of recent research. Specifically, this survey summarizes the applications and innovations of each work and categorizes recent remote sensing fine-tuning techniques into six types: adapter-based, prompt-based, reparameterization-based, hybrid methods, partial tuning, and improved tuning. In the final section, this survey suggests nine areas worth exploring in this field. Remote sensing fine-tuning methods in this survey can be found at https://github.com/DongshuoYin/Remote-Sensing-Tuning-A-Survey.

Cutting-edge works have demonstrated that text-to-image (T2I) diffusion models can generate adversarial patches that mislead state-of-the-art object detectors in the physical world, revealing detectors' vulnerabilities and risks. However, these methods neglect the T2I patches' attack effectiveness when observed from different views in the physical world (i.e., angle robustness of the T2I adversarial patches). In this paper, we study the angle robustness of T2I adversarial patches comprehensively, revealing their angle-robust issues, demonstrating that texts affect the angle robustness of generated patches significantly, and task-specific linguistic instructions fail to enhance the angle robustness. Motivated by the studies, we introduce Angle-Robust Concept Learning (AngleRoCL), a simple and flexible approach that learns a generalizable concept (i.e., text embeddings in implementation) representing the capability of generating angle-robust patches. The learned concept can be incorporated into textual prompts and guides T2I models to generate patches with their attack effectiveness inherently resistant to viewpoint variations. Through extensive simulation and physical-world experiments on five SOTA detectors across multiple views, we demonstrate that AngleRoCL significantly enhances the angle robustness of T2I adversarial patches compared to baseline methods. Our patches maintain high attack success rates even under challenging viewing conditions, with over 50% average relative improvement in attack effectiveness across multiple angles. This research advances the understanding of physically angle-robust patches and provides insights into the relationship between textual concepts and physical properties in T2I-generated contents. We released our code at https://github.com/tsingqguo/anglerocl.

Interactive segmentation aims to segment the specified target on the image with positive and negative clicks from users. Interactive ambiguity is a crucial issue in this field, which refers to the possibility of multiple compliant outcomes with the same clicks, such as selecting a part of an object versus the entire object, a single object versus a combination of multiple objects, and so on. The existing methods cannot provide intuitive guidance to the model, which leads to unstable output results and makes it difficult to meet the large-scale and efficient annotation requirements for specific targets in some scenarios. To bridge this gap, we introduce RefCut, a reference-based interactive segmentation framework designed to address part ambiguity and object ambiguity in segmenting specific targets. Users only need to provide a reference image and corresponding reference masks, and the model will be optimized based on them, which greatly reduces the interactive burden on users when annotating a large number of such targets. In addition, to enrich these two kinds of ambiguous data, we propose a new Target Disassembly Dataset which contains two subsets of part disassembly and object disassembly for evaluation. In the combination evaluation of multiple datasets, our RefCut achieved state-of-the-art performance. Extensive experiments and visualized results demonstrate that RefCut advances the field of intuitive and controllable interactive segmentation. Our code will be publicly available and the demo video is in https://www.lin-zheng.com/refcut.

Recent breakthroughs in understanding the human brain have revealed its impressive ability to efficiently process and interpret human thoughts, opening up the possibility of intervening in brain signals. In this paper, we aim to develop a straightforward framework that uses other modalities, such as natural language, to translate the original “dreamland”. We present DreamConnect, employing a dual-stream diffusion framework to manipulate visually stimulated brain signals. By integrating an asynchronous diffusion strategy, our framework establishes an effective interface with human “dreams”, and progressively refines their final image synthesis. Through extensive experiments, we demonstrate the efficacy of our method to accurately direct human brain signals in desired directions, ultimately enabling concept manipulation through direct manipulation of the functional magnetic resonance imaging (fMRI) signals. We hope that this work will motivate the use of brain signals in human-computer interaction applications.

In this study, we present Colon-X, an open initiative aimed at advancing multimodal intelligence in colonoscopy. We begin by constructing ColonVQA, the most comprehensive multimodal dataset ever built for colonoscopy, featuring over 1.1M+ visual question answering entries across 76 clinical findings and 18 multimodal tasks. Beyond serving as a community-wide data foundation, we further investigate a critical yet underexplored transition in colonoscopy - evolving from multimodal understanding to clinical reasoning: (a) To capture the current landscape of multimodal understanding behaviors, we systematically assess the generalizability of 22 multimodal large language models and examine their reliability under human-induced perturbations. The results reveal that clinical outputs from leading MLLMs remain far from robust and trustworthy. (b) To narrow this gap, we further explore reasoning-centric intelligence tailored for colonoscopy. Specifically, we curate ColonReason, a clinically grounded reasoning dataset annotated through a multi-agent debating pipeline, and develop ColonR1, the first R1-styled model that mitigates reward information collapse through task-adaptive rewards and gradient-stable policy optimization. Under data-scarce conditions, our ColonR1 achieves 56.61