Clinical photographs play a vital role in conversational computer-aided diagnosis, particularly in dermatology. However, existing skin disease benchmarks contain limitations like insufficient dataset size, the sole presence of categorical labels, the lack of expert inspections, and limited diversity in annotations. To address these shortcomings, we introduce DermEVAL, a large-scale benchmark specifically designed to evaluate the performance of Multimodal Large Language Models (MLLMs) in dermatology. Our benchmark includes image-text pairs depicting 16 distinct skin diseases, featuring a total of 11,347 representative images drawn from various dermatological datasets, carefully selected and annotated with the guidance of dermatologists. DermEVAL enables two primary tasks: visual question answering (VQA) and medical report generation (MRG), designed to simulate real-world medical diagnostics. We evaluate the performance of MLLMs in dermatology using multiple metrics, including traditional metrics and GPT-4V-based assessments. Our results indicate that accurately diagnosing skin diseases remains challenging for state-of-the-art MLLMs. We also demonstrate that fine-tuning MLLMs using DermEVAL significantly improves their performance on dermatology-related image–text tasks.

The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multi-modal large language models (MLLMs) struggle with temporal-sensitive video tasks, such as video temporal grounding, which requires generating timestamps to mark the occurrence of specific events. Existing strategies require MLLMs to generate absolute or relative timestamps directly. We have observed that those MLLMs tend to rely more on language patterns than visual cues when generating timestamps, affecting their performance. To address this problem, we propose VideoExpert, a general-purpose MLLM suitable for several temporal-sensitive video tasks. Inspired by the expert concept, VideoExpert integrates two parallel modules: the Temporal Expert and the Spatial Expert. The Temporal Expert is responsible for modeling time sequences and performing temporal grounding. It processes high-frame-rate yet compressed tokens to capture dynamic variations in videos and includes a lightweight prediction head for precise event localization. The Spatial Expert focuses on content detail analysis and instruction following. It handles specially designed spatial tokens and language input, aiming to generate content-related responses. These two experts collaborate seamlessly via a special token, ensuring coordinated temporal grounding and content generation. Notably, the Temporal and Spatial Experts maintain independent parameter sets. This parameter decoupling design enables specialized learning within each part without mutual interference. By offloading temporal grounding from content generation, VideoExpert prevents text pattern biases in timestamp predictions. Moreover, we introduce a Spatial Compress module to obtain spatial tokens. This module filters and compresses patch tokens while preserving key information, delivering compact yet detail-rich input for the Spatial Expert. Extensive experiments conducted on four widely-used benchmarks (i.e. Charades-STA, QVHighlight, YouCookII and NextGQA) across four tasks (temporal grounding, highlight detection, dense video captioning and grounding question answering) demonstrate the effectiveness and versatility of the VideoExpert.

We present LawDIS, a language-window-based controllable dichotomous image segmentation (DIS) framework that produces high-quality object masks. Our framework recasts DIS as an image-conditioned mask generation task within a latent diffusion model, enabling seamless integration of user controls. LawDIS is enhanced with macro-to-micro control modes. Specifically, in macro mode, we introduce a language-controlled segmentation strategy (LS) to generate an initial mask based on user-provided language prompts. In micro mode, a window-controlled refinement strategy (WR) allows flexible refinement of user-defined regions (i.e., size-adjustable windows) within the initial mask. Coordinated by a mode switcher, these modes can operate independently or jointly, making the framework well-suited for high-accuracy, personalised applications. Extensive experiments on the DIS5K benchmark reveal that our LawDIS significantly outperforms 11 cutting-edge methods across all metrics. Notably, compared to the second-best model MVANet, we achieve $F_β^ω$ gains of 4.6\% with both the LS and WR strategies and 3.6\% gains with only the LS strategy on DIS-TE. Codes will be made available at https://github.com/XinyuYanTJU/LawDIS.

Automatic analysis of colonoscopy images has been an active field of research motivated by the importance of early detection of precancerous polyps. However, detecting polyps during the live examination can be challenging due to various factors such as variation of skills and experience among the endoscopists, lack of attentiveness, and fatigue leading to a high polyp miss-rate. Therefore, there is a need for an automated system that can flag missed polyps during the examination and improve patient care. Deep learning has emerged as a promising solution to this challenge as it can assist endoscopists in detecting and classifying overlooked polyps and abnormalities in real time, improving the accuracy of diagnosis and enhancing treatment. In addition to the algorithm’s accuracy, transparency and interpretability are crucial to explaining the whys and hows of the algorithm’s prediction. Further, conclusions based on incorrect decisions may be fatal, especially in medicine. Despite these pitfalls, most algorithms are developed in private data, closed source, or proprietary software, and methods lack reproducibility. Therefore, to promote the development of efficient and transparent methods, we have organized the “Medico automatic polyp segmentation (Medico 2020)” and “MedAI: Transparency in Medical Image Segmentation (MedAI 2021)” competitions. The Medico 2020 challenge received submissions from 17 teams, while the MedAI 2021 challenge also gathered submissions from another 17 distinct teams in the following year. We present a comprehensive summary and analyze each contribution, highlight the strength of the best-performing methods, and discuss the possibility of clinical translations of such methods into the clinic. Our analysis revealed that the participants improved dice coefficient metrics from 0.8607 in 2020 to 0.8993 in 2021 despite adding diverse and challenging frames (containing irregular, smaller, sessile, or flat polyps), which are frequently missed during a routine clinical examination. For the instrument segmentation task, the best team obtained a mean Intersection over union metric of 0.9364. For the transparency task, a multi-disciplinary team, including expert gastroenterologists, accessed each submission and evaluated the team based on open-source practices, failure case analysis, ablation studies, usability and understandability of evaluations to gain a deeper understanding of the models’ credibility for clinical deployment. The best team obtained a final transparency score of 21 out of 25. Through the comprehensive analysis of the challenge, we not only highlight the advancements in polyp and surgical instrument segmentation but also encourage subjective evaluation for building more transparent and understandable AI-based colonoscopy systems. Moreover, we discuss the need for multi-center and out-of-distribution testing to address the current limitations of the methods to reduce the cancer burden and improve patient care. • We present a detailed analysis of the Medico 2020 and MedAI 2021 challenges that are aimed at advancing automated polyp and instrument segmentation in colonoscopy for early colorectal cancer diagnosis by using novel deep learning methods. • To the best of our knowledge, MedAI 2021 is the first challenge to evaluate the transparency in both GI endoscopy and colonoscopy. Through the challenge, we invited the participants to list package dependencies and architecture code (with instructions for building, compiling, and training) and share trained model weights in a standardized format. Additionally, we invited participants to include the code for model evaluation and provide repository licensing information to enable others to use the code and the trained model responsibly. Moreover, we asked the participants to explain model predictions using intermediate heatmaps, perform ablation studies, conduct a thorough failure analysis, and share their code for reproducing the results. Finally, we performed a subjective evaluation by including an expert gastroenterologist in the group and gave the final transparency score based on the usefulness and understandability of the results. Our initiative aims to promote transparency in AI research and foster the development of reliable, interpretable, and trustworthy algorithms for use in medical image segmentation. • We provide a comparative analysis of the 34 proposed methods in both challenges (3 subtasks), covering small details of each team in the form of Tables, qualitative and quantitative results (failure analysis), and an in-depth analysis of the findings. • We explore trust, safety, interpretability, transparency, and generalizability issues and provide future strategies to overcome the current limitations of developed algorithms.

Camouflage poses notable challenges in distinguishing a static target, as it usually blends seamlessly with the background. However, any movement by the target can disrupt this disguise, making it detectable. Existing video camouflaged object detection (VCOD) approaches take noisy motion estimation as input or model motion implicitly, restricting detection performance in complex dynamic scenes. In this paper, we propose a novel Explicit Motion handling and Interactive Prompting framework for VCOD, dubbed EMIP, which handles motion cues explicitly using a frozen pre-trained optical flow fundamental model. EMIP is characterized by a two-stream architecture for simultaneously conducting camouflaged segmentation and optical flow estimation. Interactions across the dual streams are realized in an interactive prompting way that is inspired by emerging visual prompt learning. Two learnable modules, i.e. the camouflaged feeder and motion collector, are designed to incorporate segmentation-to-motion and motion-to-segmentation prompts, respectively, and enhance outputs of the both streams. The prompt fed to the motion stream is learned by supervising optical flow in a self-supervised manner. Furthermore, we show that long-term historical information can also be incorporated as a prompt into EMIP and achieve more robust results with temporal consistency. By leveraging promoting techniques based on EMIP, the proposed long-term model EMIP ${}^{\dagger }$ incurs lower training cost with only 8.5M trainable parameters (less than 8% of the total model parameters). Experimental results demonstrate that both EMIP and EMIP ${}^{\dagger }$ set new state-of-the-art records on popular VCOD benchmarks. Additionally, comparative evaluations against other video segmentation models on a wider range of video segmentation tasks demonstrate the robustness and superior generalization capabilities of EMIP. Our code is made publicly available at https://github.com/zhangxin06/EMIP.

Previous video object segmentation approaches mainly focus on simplex solutions linking appearance and motion, limiting effective feature collaboration between these two cues. In this work, we study a novel and efficient full-duplex strategy network (FSNet) to address this issue, by considering a better mutual restraint scheme linking motion and appearance allowing exploitation of cross-modal features from the fusion and decoding stage. Specifically, we introduce a relational cross-attention module (RCAM) to achieve bidirectional message propagation across embedding sub-spaces. To improve the model’s robustness and update inconsistent features from the spatiotemporal embeddings, we adopt a bidirectional purification module after the RCAM. Extensive experiments on five popular benchmarks show that our FSNet is robust to various challenging scenarios (e.g., motion blur and occlusion), and compares well to leading methods both for video object segmentation and video salient object detection. The project is publicly available at https://github.com/GewelsJI/FSNet .

Salient object detection (SOD) is a long-standing research topic in computer vision with increasing interest in the past decade. Since light fields record comprehensive information of natural scenes that benefit SOD in a number of ways, using light field inputs to improve saliency detection over conventional RGB inputs is an emerging trend. This paper provides the first comprehensive review and a benchmark for light field SOD, which has long been lacking in the saliency community. Firstly, we introduce light fields, including theory and data forms, and then review existing studies on light field SOD, covering ten traditional models, seven deep learning-based models, a comparative study, and a brief review. Existing datasets for light field SOD are also summarized. Secondly, we benchmark nine representative light field SOD models together with several cutting-edge RGB-D SOD models on four widely used light field datasets, providing insightful discussions and analyses, including a comparison between light field SOD and RGB-D SOD models. Due to the inconsistency of current datasets, we further generate complete data and supplement focal stacks, depth maps, and multi-view images for them, making them consistent and uniform. Our supplemental data make a universal benchmark possible. Lastly, light field SOD is a specialised problem, because of its diverse data representations and high dependency on acquisition hardware, so it differs greatly from other saliency detection tasks. We provide nine observations on challenges and future directions, and outline several open issues. All the materials including models, datasets, benchmarking results, and supplemented light field datasets are publicly available at https://github.com/kerenfu/LFSOD-Survey .

We present the first systematic study on concealed object detection (COD), which aims to identify objects that are visually embedded in their background. The high intrinsic similarities between the concealed objects and their background make COD far more challenging than traditional object detection/segmentation. To better understand this task, we collect a large-scale dataset, called COD10K, which consists of 10,000 images covering concealed objects in diverse real-world scenarios from 78 object categories. Further, we provide rich annotations including object categories, object boundaries, challenging attributes, object-level labels, and instance-level annotations. Our COD10K is the largest COD dataset to date, with the richest annotations, which enables comprehensive concealed object understanding and can even be used to help progress several other vision tasks, such as detection, segmentation, classification etc. Motivated by how animals hunt in the wild, we also design a simple but strong baseline for COD, termed the Search Identification Network (SINet). Without any bells and whistles, SINet outperforms twelve cutting-edge baselines on all datasets tested, making them robust, general architectures that could serve as catalysts for future research in COD. Finally, we provide some interesting findings, and highlight several potential applications and future directions. To spark research in this new field, our code, dataset, and online demo are available at our project page: http://mmcheng.net/cod.

In this article, we conduct a comprehensive study on the co-salient object detection (CoSOD) problem for images. CoSOD is an emerging and rapidly growing extension of salient object detection (SOD), which aims to detect the co-occurring salient objects in a group of images. However, existing CoSOD datasets often have a serious data bias, assuming that each group of images contains salient objects of similar visual appearances. This bias can lead to the ideal settings and effectiveness of models trained on existing datasets, being impaired in real-life situations, where similarities are usually semantic or conceptual. To tackle this issue, we first introduce a new benchmark, called CoSOD3k in the wild, which requires a large amount of semantic context, making it more challenging than existing CoSOD datasets. Our CoSOD3k consists of 3,316 high-quality, elaborately selected images divided into 160 groups with hierarchical annotations. The images span a wide range of categories, shapes, object sizes, and backgrounds. Second, we integrate the existing SOD techniques to build a unified, trainable CoSOD framework, which is long overdue in this field. Specifically, we propose a novel CoEG-Net that augments our prior model EGNet with a co-attention projection strategy to enable fast common information learning. CoEG-Net fully leverages previous large-scale SOD datasets and significantly improves the model scalability and stability. Third, we comprehensively summarize 40 cutting-edge algorithms, benchmarking 18 of them over three challenging CoSOD datasets (iCoSeg, CoSal2015, and our CoSOD3k), and reporting more detailed (i.e., group-level) performance analysis. Finally, we discuss the challenges and future works of CoSOD. We hope that our study will give a strong boost to growth in the CoSOD community. The benchmark toolbox and results are available on our project page at https://dpfan.net/CoSOD3K.

Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately designed training process. Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture. In this paper, we propose two effective components: joint learning (JL), and densely cooperative fusion (DCF). The JL module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery. Comprehensive experiments using 5 popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the SOTAs by an average of ~2.0% (F-measure) across 7 challenging datasets. In addition, we show that JL-DCF is readily applicable to other related multi-modal detection tasks, including RGB-T SOD and video SOD, achieving comparable or better performance.

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network ($\text{C}^{2}\text{F}$-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare$\text{C}^{2}\text{F}$-Net with state-of-the-art (SOTA) models. The results show that$\text{C}^{2}\text{F}$-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our$\text{C}^{2}\text{F}$-Net in COD downstream applications. Our code is publicly available at:https://github.com/Ben57882/C2FNet-TSCVT

Camouflaged object segmentation (COS) aims to identify objects that are "perfectly" assimilate into their surroundings, which has a wide range of valuable applications. The key challenge of COS is that there exist high intrinsic similarities between the candidate objects and noise background. In this paper, we strive to embrace challenges towards effective and efficient COS. To this end, we develop a bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature. Specifically, our PFNet contains two key modules, i.e., the positioning module (PM) and the focus module (FM). The PM is designed to mimic the detection process in predation for positioning the potential target objects from a global perspective and the FM is then used to perform the identification process in predation for progressively refining the coarse prediction via focusing on the ambiguous regions. Notably, in the FM, we develop a novel distraction mining strategy for the distraction discovery and removal, to benefit the performance of estimation. Extensive experiments demonstrate that our PFNet runs in real-time (72 FPS) and significantly outperforms 18 cutting-edge models on three challenging datasets under four standard metrics.

Appearance and motion are two important sources of information in video object segmentation (VOS). Previous methods mainly focus on using simplex solutions, lowering the upper bound of feature collaboration among and across these two cues. In this paper, we study a novel framework, termed the FSNet (Full-duplex Strategy Network), which designs a relational cross-attention module (RCAM) to achieve the bidirectional message propagation across embedding subspaces. Furthermore, the bidirectional purification module (BPM) is introduced to update the inconsistent features between the spatial-temporal embeddings, effectively improving the model robustness. By considering the mutual restraint within the full-duplex strategy, our FSNet performs the cross-modal feature-passing (i.e., transmission and receiving) simultaneously before the fusion and decoding stage, making it robust to various challenging scenarios (e.g., motion blur, occlusion) in VOS. Extensive experiments on five popular benchmarks (i.e., DAVIS16, FBMS, MCL, SegTrack-V2, and DAVSOD19) show that our FSNet outperforms other state-of-the-arts for both the VOS and video salient object detection tasks.

Owing to the difficulties of mining spatial-temporal cues, the existing approaches for video salient object detection (VSOD) are limited in understanding complex and noisy scenarios, and often fail in inferring prominent objects. To alleviate such shortcomings, we propose a simple yet efficient architecture, termed Guidance and Teaching Network (GTNet), to independently distill effective spatial and temporal cues with implicit guidance and explicit teaching at feature- and decision-level, respectively. To be specific, we (a) introduce a temporal modulator to implicitly bridge features from motion into appearance branch, which is capable of fusing cross-modal features collaboratively, and (b) utilise motion-guided mask to propagate the explicit cues during the feature aggregation. This novel learning strategy achieves satisfactory results via decoupling the complex spatial-temporal cues and mapping informative cues across different modalities. Extensive experiments on three challenging benchmarks show that the proposed method can run at$\sim$28 fps on a single TITAN Xp GPU and perform competitively against 14 cutting-edge baselines.

RGB-D salient object detection (SOD) recently has attracted increasing research interest by benefiting conventional RGB SOD with extra depth information. However, existing RGB-D SOD models often fail to perform well in terms of both efficiency and accuracy, which hinders their potential applications on mobile devices and real-world problems. An underlying challenge is that the model accuracy usually degrades when the model is simplified to have few parameters. To tackle this dilemma and also inspired by the fact that depth quality is a key factor influencing the accuracy, we propose a novel depth quality-inspired feature manipulation (DQFM) process, which is efficient itself and can serve as a gating mechanism for filtering depth features to greatly boost the accuracy. DQFM resorts to the alignment of low-level RGB and depth features, as well as holistic attention of the depth stream to explicitly control and enhance cross-modal fusion. We embed DQFM to obtain an efficient light-weight model called DFM-Net, where we also design a tailored depth backbone and a two-stage decoder for further efficiency consideration. Extensive experimental results demonstrate that our DFM-Net achieves state-of-the-art accuracy when comparing to existing non-efficient models, and meanwhile runs at 140ms on CPU (2.2x faster than the prior fastest efficient model) with only ~8.5Mb model size (14.9% of the prior lightest). Our code will be available at https://github.com/zwbx/DFM-Net.

We present a comprehensive study on a new task named camouflaged object detection (COD), which aims to identify objects that are “seamlessly” embedded in their surroundings. The high intrinsic similarities between the target object and the background make COD far more challenging than the traditional object detection task. To address this issue, we elaborately collect a novel dataset, called COD10K, which comprises 10,000 images covering camouflaged objects in various natural scenes, over 78 object categories. All the images are densely annotated with category, bounding-box, object-/instance-level, and matting-level labels. This dataset could serve as a catalyst for progressing many vision tasks, e.g., localization, segmentation, and alpha-matting, etc. In addition, we develop a simple but effective framework for COD, termed Search Identification Network (SINet). Without any bells and whistles, SINet outperforms various state-of-the-art object detection baselines on all datasets tested, making it a robust, general framework that can help facilitate future research in COD. Finally, we conduct a large-scale COD study, evaluating 13 cutting-edge models, providing some interesting findings, and showing several potential applications. Our research offers the community an opportunity to explore more in this new field. The code will be available at https://github.com/DengPingFan/SINet/.

Co-salient object detection (CoSOD) is a newly emerging and rapidly growing branch of salient object detection (SOD), which aims to detect the co-occurring salient objects in multiple images. However, existing CoSOD datasets often have a serious data bias, which assumes that each group of images contains salient objects of similar visual appearances. This bias results in the ideal settings and the effectiveness of the models, trained on existing datasets, may be impaired in real-life situations, where the similarity is usually semantic or conceptual. To tackle this issue, we first collect a new high-quality dataset, named CoSOD3k, which contains 3,316 images divided into 160 groups with multiple level annotations, i.e., category, bounding box, object, and instance levels. CoSOD3k makes a significant leap in terms of diversity, difficulty and scalability, benefiting related vision tasks. Besides, we comprehensively summarize 34 cutting-edge algorithms, benchmarking 19 of them over four existing CoSOD datasets (MSRC, iCoSeg, Image Pair and CoSal2015) and our CoSOD3k with a total of ~61K images (largest scale), and reporting group-level performance analysis. Finally, we discuss the challenge and future work of CoSOD. Our study would give a strong boost to growth in the CoSOD community. Benchmark toolbox and results are available on our project page.

This paper proposes a novel joint learning and densely-cooperative fusion (JL-DCF) architecture for RGB-D salient object detection. Existing models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately-designed training process. In contrast, our JL-DCF learns from both RGB and depth inputs through a Siamese network. To this end, we propose two effective components: joint learning (JL), and densely-cooperative fusion (DCF). The JL module provides robust saliency feature learning, while the latter is introduced for complementary feature discovery. Comprehensive experiments on four popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the top-1 D3Net model by an average of ~1.9% (S-measure) across six challenging datasets, showing that the proposed framework offers a potential solution for real-world applications and could provide more insight into the cross-modality complementarity task. The code will be available at https://github.com/kerenfu/JLDCF/.

Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. Automated detection of lung infections from computed tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions from CT slices faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. To address these challenges, a novel COVID-19 Lung Infection Segmentation Deep Network (Inf-Net) is proposed to automatically identify infected regions from chest CT slices. In our Inf-Net, a parallel partial decoder is used to aggregate the high-level features and generate a global map. Then, the implicit reverse attention and explicit edge-attention are utilized to model the boundaries and enhance the representations. Moreover, to alleviate the shortage of labeled data, we present a semi-supervised segmentation framework based on a randomly selected propagation strategy, which only requires a few labeled images and leverages primarily unlabeled data. Our semi-supervised framework can improve the learning ability and achieve a higher performance. Extensive experiments on our COVID-SemiSeg and real CT volumes demonstrate that the proposed Inf-Net outperforms most cutting-edge segmentation models and advances the state-of-the-art performance.