Guanbin Li

Ruifei Zhang, Guanbin Li, Zhen Li et al.

Accurate polyp segmentation is of great significance for the diagnosis and treatment of colorectal cancer. However, it has always been very challenging due to the diverse shape and size of polyp. In recent years, state-of-the-art methods have achieved significant breakthroughs in this task with the help of deep convolutional neural networks. However, few algorithms explicitly consider the impact of the size and shape of the polyp and the complex spatial context on the segmentation performance, which results in the algorithms still being powerless for complex samples. In fact, segmentation of polyps of different sizes relies on different local and global contextual information for regional contrast reasoning. To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM). Specifically, LCA modules deliver local context features from encoder layers to decoder layers, enhancing the attention to the hard region which is determined by the prediction map of previous layer. GCM aims to further explore the global context features and send to the decoder layers. ASM is used for adaptive selection and aggregation of context features through channel-wise attention. Our proposed approach is evaluated on the EndoScene and Kvasir-SEG Datasets, and shows outstanding performance compared with other state-of-the-art methods. The code is available at https://github.com/ReaFly/ACSNet.

Zunnan Xu, Zhihong Chen, Yong Zhang et al. · tsinghua

Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction between modalities. In this paper, we do an investigation of efficient tuning problems on referring image segmentation. We propose a novel adapter called Bridger to facilitate cross-modal information exchange and inject task-specific information into the pre-trained model. We also design a lightweight decoder for image segmentation. Our approach achieves comparable or superior performance with only 1.61\% to 3.38\% backbone parameter updates, evaluated on challenging benchmarks. The code is available at \url{https://github.com/kkakkkka/ETRIS}.

Ganlong Zhao, Guanbin Li, Yipeng Qin et al.

Dataset Condensation aims to condense a large dataset into a smaller one while maintaining its ability to train a well-performing model, thus reducing the storage cost and training effort in deep learning applications. However, conventional dataset condensation methods are optimization-oriented and condense the dataset by performing gradient or parameter matching during model optimization, which is computationally intensive even on small datasets and models. In this paper, we propose a novel dataset condensation method based on distribution matching, which is more efficient and promising. Specifically, we identify two important shortcomings of naive distribution matching (i.e., imbalanced feature numbers and unvalidated embeddings for distance computation) and address them with three novel techniques (i.e., partitioning and expansion augmentation, efficient and enriched model sampling, and class-aware distribution regularization). Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources, thereby scaling data condensation to larger datasets and models. Extensive experiments demonstrate the effectiveness of our method. Codes are available at https://github.com/uitrbn/IDM

Yang Liu, Weixing Chen, Yongjie Bai et al.

Embodied Artificial Intelligence (Embodied AI) is crucial for achieving Artificial General Intelligence (AGI) and serves as a foundation for various applications (e.g., intelligent mechatronics systems, smart manufacturing) that bridge cyberspace and the physical world. Recently, the emergence of Multi-modal Large Models (MLMs) and World Models (WMs) have attracted significant attention due to their remarkable perception, interaction, and reasoning capabilities, making them a promising architecture for embodied agents. In this survey, we give a comprehensive exploration of the latest advancements in Embodied AI. Our analysis firstly navigates through the forefront of representative works of embodied robots and simulators, to fully understand the research focuses and their limitations. Then, we analyze four main research targets: 1) embodied perception, 2) embodied interaction, 3) embodied agent, and 4) sim-to-real adaptation, covering state-of-the-art methods, essential paradigms, and comprehensive datasets. Additionally, we explore the complexities of MLMs in virtual and real embodied agents, highlighting their significance in facilitating interactions in digital and physical environments. Finally, we summarize the challenges and limitations of embodied AI and discuss potential future directions. We hope this survey will serve as a foundational reference for the research community. The associated project can be found at https://github.com/HCPLab-SYSU/Embodied_AI_Paper_List.

Yang Liu, Guanbin Li, Liang Lin

Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In this work, to address the task of event-level visual question answering, we propose a framework for cross-modal causal relational reasoning. In particular, a set of causal intervention operations is introduced to discover the underlying causal structures across visual and linguistic modalities. Our framework, named Cross-Modal Causal RelatIonal Reasoning (CMCIR), involves three modules: i) Causality-aware Visual-Linguistic Reasoning (CVLR) module for collaboratively disentangling the visual and linguistic spurious correlations via front-door and back-door causal interventions; ii) Spatial-Temporal Transformer (STT) module for capturing the fine-grained interactions between visual and linguistic semantics; iii) Visual-Linguistic Feature Fusion (VLFF) module for learning the global semantic-aware visual-linguistic representations adaptively. Extensive experiments on four event-level datasets demonstrate the superiority of our CMCIR in discovering visual-linguistic causal structures and achieving robust event-level visual question answering. The datasets, code, and models are available at https://github.com/HCPLab-SYSU/CMCIR.

Zhihong Chen, Yuhao Du, Jinpeng Hu et al.

Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical vision-and-language understanding. In this paper, we propose a self-supervised learning paradigm with multi-modal masked autoencoders (M$^3$AE), which learn cross-modal domain knowledge by reconstructing missing pixels and tokens from randomly masked images and texts. There are three key designs to make this simple approach work. First, considering the different information densities of vision and language, we adopt different masking ratios for the input image and text, where a considerably larger masking ratio is used for images. Second, we use visual and textual features from different layers to perform the reconstruction to deal with different levels of abstraction in visual and language. Third, we develop different designs for vision and language decoders (i.e., a Transformer for vision and a multi-layer perceptron for language). To perform a comprehensive evaluation and facilitate further research, we construct a medical vision-and-language benchmark including three tasks. Experimental results demonstrate the effectiveness of our approach, where state-of-the-art results are achieved on all downstream tasks. Besides, we conduct further analysis to better verify the effectiveness of different components of our approach and various settings of pre-training. The source code is available at~\url{https://github.com/zhjohnchan/M3AE}.

Hong Yan, Yang Liu, Yushen Wei et al.

Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current methods usually require sufficient labeled data for training computationally expensive models, which is labor-intensive and time-consuming. Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets. In this paper, we propose an efficient skeleton sequence learning framework, named Skeleton Sequence Learning (SSL). To comprehensively capture the human pose and obtain discriminative skeleton sequence representation, we build an asymmetric graph-based encoder-decoder pre-training architecture named SkeletonMAE, which embeds skeleton joint sequence into Graph Convolutional Network (GCN) and reconstructs the masked skeleton joints and edges based on the prior human topology knowledge. Then, the pre-trained SkeletonMAE encoder is integrated with the Spatial-Temporal Representation Learning (STRL) module to build the SSL framework. Extensive experimental results show that our SSL generalizes well across different datasets and outperforms the state-of-the-art self-supervised skeleton-based action recognition methods on FineGym, Diving48, NTU 60 and NTU 120 datasets. Additionally, we obtain comparable performance to some fully supervised methods. The code is avaliable at https://github.com/HongYan1123/SkeletonMAE.

Ziyi Zhang, Weikai Chen, Hui Cheng et al.

We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo labeling to achieve class-wise global alignment [1] or rely on local structure extraction that encourages feature consistency among neighborhoods [2]. While impressive progress has been made, both lines of methods have their own drawbacks - the "global" approach is sensitive to noisy labels while the "local" counterpart suffers from source bias. In this paper, we present Divide and Contrast (DaC), a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations. Based on the prediction confidence of the source model, DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals under an adaptive contrastive learning framework. Specifically, the source-like samples are utilized for learning global class clustering thanks to their relatively clean labels. The more noisy target-specific data are harnessed at the instance level for learning the intrinsic local structures. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch. Extensive experiments on VisDA, Office-Home, and the more challenging DomainNet have verified the superior performance of DaC over current state-of-the-art approaches. The code is available at https://github.com/ZyeZhang/DaC.git.

Jiacheng Zhang, Xiangru Lin, Wei Zhang et al.

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic correspondence between the input query and its prediction output, which hinders the applicability of the consistency-based regularization widely used in current SSOD methods. We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector, to tackle these problems. Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage. Besides, we introduce a Crossview Query Consistency method to learn the semantic feature invariance of object queries from different views while avoiding the need to find deterministic query correspondence. Furthermore, we propose a Cost-based Pseudo Label Mining module to dynamically mine more pseudo boxes based on the matching cost of pseudo ground truth bounding boxes for consistency training. Extensive experiments on all SSOD settings of both COCO and Pascal VOC benchmark datasets show that our Semi-DETR method outperforms all state-of-the-art methods by clear margins. The PaddlePaddle version code1 is at https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/semi_det/semi_detr.

Ruifei Zhang, Sishuo Liu, Yizhou Yu et al.

Biomedical image segmentation plays a significant role in computer-aided diagnosis. However, existing CNN based methods rely heavily on massive manual annotations, which are very expensive and require huge human resources. In this work, we adopt a coarse-to-fine strategy and propose a self-supervised correction learning paradigm for semi-supervised biomedical image segmentation. Specifically, we design a dual-task network, including a shared encoder and two independent decoders for segmentation and lesion region inpainting, respectively. In the first phase, only the segmentation branch is used to obtain a relatively rough segmentation result. In the second step, we mask the detected lesion regions on the original image based on the initial segmentation map, and send it together with the original image into the network again to simultaneously perform inpainting and segmentation separately. For labeled data, this process is supervised by the segmentation annotations, and for unlabeled data, it is guided by the inpainting loss of masked lesion regions. Since the two tasks rely on similar feature information, the unlabeled data effectively enhances the representation of the network to the lesion regions and further improves the segmentation performance. Moreover, a gated feature fusion (GFF) module is designed to incorporate the complementary features from the two tasks. Experiments on three medical image segmentation datasets for different tasks including polyp, skin lesion and fundus optic disc segmentation well demonstrate the outstanding performance of our method compared with other semi-supervised approaches. The code is available at https://github.com/ReaFly/SemiMedSeg.

Junfan Lin, Jianlong Chang, Lingbo Liu et al.

Text-to-motion generation is an emerging and challenging problem, which aims to synthesize motion with the same semantics as the input text. However, due to the lack of diverse labeled training data, most approaches either limit to specific types of text annotations or require online optimizations to cater to the texts during inference at the cost of efficiency and stability. In this paper, we investigate offline open-vocabulary text-to-motion generation in a zero-shot learning manner that neither requires paired training data nor extra online optimization to adapt for unseen texts. Inspired by the prompt learning in NLP, we pretrain a motion generator that learns to reconstruct the full motion from the masked motion. During inference, instead of changing the motion generator, our method reformulates the input text into a masked motion as the prompt for the motion generator to ``reconstruct'' the motion. In constructing the prompt, the unmasked poses of the prompt are synthesized by a text-to-pose generator. To supervise the optimization of the text-to-pose generator, we propose the first text-pose alignment model for measuring the alignment between texts and 3D poses. And to prevent the pose generator from overfitting to limited training texts, we further propose a novel wordless training mechanism that optimizes the text-to-pose generator without any training texts. The comprehensive experimental results show that our method obtains a significant improvement against the baseline methods. The code is available at https://github.com/junfanlin/oohmg.

Weixing Chen, Yang Liu, Ce Wang et al.

Radiology Report Generation (RRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating the corresponding radiology reports according to the given radiology image. However, generating accurate lesion descriptions remains challenging due to spurious correlations from visual-linguistic biases and inherent limitations of radiological imaging, such as low resolution and noise interference. To address these issues, we propose a two-stage framework named CrossModal Causal Representation Learning (CMCRL), consisting of the Radiological Cross-modal Alignment and Reconstruction Enhanced (RadCARE) pre-training and the Visual-Linguistic Causal Intervention (VLCI) fine-tuning. In the pre-training stage, RadCARE introduces a degradation-aware masked image restoration strategy tailored for radiological images, which reconstructs high-resolution patches from low-resolution inputs to mitigate noise and detail loss. Combined with a multiway architecture and four adaptive training strategies (e.g., text postfix generation with degraded images and text prefixes), RadCARE establishes robust cross-modal correlations even with incomplete data. In the VLCI phase, we deploy causal front-door intervention through two modules: the Visual Deconfounding Module (VDM) disentangles local-global features without fine-grained annotations, while the Linguistic Deconfounding Module (LDM) eliminates context bias without external terminology databases. Experiments on IU-Xray and MIMIC-CXR show that our CMCRL pipeline significantly outperforms state-of-the-art methods, with ablation studies confirming the necessity of both stages. Code and models are available at https://github.com/WissingChen/CMCRL.

Ruifei Zhang, Peiwen Lai, Xiang Wan et al.

Automatic and accurate polyp segmentation plays an essential role in early colorectal cancer diagnosis. However, it has always been a challenging task due to 1) the diverse shape, size, brightness and other appearance characteristics of polyps, 2) the tiny contrast between concealed polyps and their surrounding regions. To address these problems, we propose a lesion-aware dynamic network (LDNet) for polyp segmentation, which is a traditional u-shape encoder-decoder structure incorporated with a dynamic kernel generation and updating scheme. Specifically, the designed segmentation head is conditioned on the global context features of the input image and iteratively updated by the extracted lesion features according to polyp segmentation predictions. This simple but effective scheme endows our model with powerful segmentation performance and generalization capability. Besides, we utilize the extracted lesion representation to enhance the feature contrast between the polyp and background regions by a tailored lesion-aware cross-attention module (LCA), and design an efficient self-attention module (ESA) to capture long-range context relations, further improving the segmentation accuracy. Extensive experiments on four public polyp benchmarks and our collected large-scale polyp dataset demonstrate the superior performance of our method compared with other state-of-the-art approaches. The source code is available at https://github.com/ReaFly/LDNet.

Junfan Lin, Yuying Zhu, Lingbo Liu et al.

Traffic Signal Control (TSC) aims to reduce the average travel time of vehicles in a road network, which in turn enhances fuel utilization efficiency, air quality, and road safety, benefiting society as a whole. Due to the complexity of long-horizon control and coordination, most prior TSC methods leverage deep reinforcement learning (RL) to search for a control policy and have witnessed great success. However, TSC still faces two significant challenges. 1) The travel time of a vehicle is delayed feedback on the effectiveness of TSC policy at each traffic intersection since it is obtained after the vehicle has left the road network. Although several heuristic reward functions have been proposed as substitutes for travel time, they are usually biased and not leading the policy to improve in the correct direction. 2) The traffic condition of each intersection is influenced by the non-local intersections since vehicles traverse multiple intersections over time. Therefore, the TSC agent is required to leverage both the local observation and the non-local traffic conditions to predict the long-horizontal traffic conditions of each intersection comprehensively. To address these challenges, we propose DenseLight, a novel RL-based TSC method that employs an unbiased reward function to provide dense feedback on policy effectiveness and a non-local enhanced TSC agent to better predict future traffic conditions for more precise traffic control. Extensive experiments and ablation studies demonstrate that DenseLight can consistently outperform advanced baselines on various road networks with diverse traffic flows. The code is available at https://github.com/junfanlin/DenseLight.

Xiaoqian Xu, Pengxu Wei, Weikai Chen et al.

Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super-resolution (SR) models trained on images from different devices. In this paper, we investigate a novel and practical task coded cross-device SR, which strives to adapt a real-world SR model trained on the paired images captured by one camera to low-resolution (LR) images captured by arbitrary target devices. The proposed task is highly challenging due to the absence of paired data from various imaging devices. To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera. DADA employs the Domain-Invariant Attention (DIA) module to establish the basis of target model training even without HR supervision. Furthermore, the dual framework of DADA facilitates an Inter-domain Adversarial Adaptation (InterAA) in one branch for two LR input images from two domains, and an Intra-domain Adversarial Adaptation (IntraAA) in two branches for an LR input image. InterAA and IntraAA together improve the model transferability from the source domain to the target. We empirically conduct experiments under six Real to Real adaptation settings among three different cameras, and achieve superior performance compared with existing state-of-the-art approaches. We also evaluate the proposed DADA to address the adaptation to the video camera, which presents a promising research topic to promote the wide applications of real-world super-resolution. Our source code is publicly available at https://github.com/lonelyhope/DADA.git.

Zhihong Chen, Ruifei Zhang, Yibing Song et al.

Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities over their joint space. However, most existing VG datasets are constructed using simple description texts, which do not require sufficient reasoning over the images and texts. This has been demonstrated in a recent study~\cite{luo2022goes}, where a simple LSTM-based text encoder without pretraining can achieve state-of-the-art performance on mainstream VG datasets. Therefore, in this paper, we propose a novel benchmark of \underline{S}cene \underline{K}nowledge-guided \underline{V}isual \underline{G}rounding (SK-VG), where the image content and referring expressions are not sufficient to ground the target objects, forcing the models to have a reasoning ability on the long-form scene knowledge. To perform this task, we propose two approaches to accept the triple-type input, where the former embeds knowledge into the image features before the image-query interaction; the latter leverages linguistic structure to assist in computing the image-text matching. We conduct extensive experiments to analyze the above methods and show that the proposed approaches achieve promising results but still leave room for improvement, including performance and interpretability. The dataset and code are available at \url{https://github.com/zhjohnchan/SK-VG}.

Yang Liu, Weixing Chen, Guanbin Li et al.

We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox containing a rich set of state-of-the-art causal relation discovery and causal inference methods for various visual-linguistic reasoning tasks, such as VQA, image/video captioning, medical report generation, model generalization and robustness, etc. These methods have been included in the toolbox with PyTorch implementations under NVIDIA computing system. It not only includes training and inference codes, but also provides model weights. We believe this toolbox is by far the most complete visual-linguitic causal reasoning toolbox. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to re-implement existing methods and develop their own new causal reasoning methods. Code and models are available at https://github.com/HCPLab-SYSU/CausalVLR. The project is under active development by HCP-Lab's contributors and we will keep this document updated.

Kuo Wang, Lechao Cheng, Weikai Chen et al.

Learning from pseudo-labels that generated with VLMs~(Vision Language Models) has been shown as a promising solution to assist open vocabulary detection (OVD) in recent studies. However, due to the domain gap between VLM and vision-detection tasks, pseudo-labels produced by the VLMs are prone to be noisy, while the training design of the detector further amplifies the bias. In this work, we investigate the root cause of VLMs' biased prediction under the OVD context. Our observations lead to a simple yet effective paradigm, coded MarvelOVD, that generates significantly better training targets and optimizes the learning procedure in an online manner by marrying the capability of the detector with the vision-language model. Our key insight is that the detector itself can act as a strong auxiliary guidance to accommodate VLM's inability of understanding both the ``background'' and the context of a proposal within the image. Based on it, we greatly purify the noisy pseudo-labels via Online Mining and propose Adaptive Reweighting to effectively suppress the biased training boxes that are not well aligned with the target object. In addition, we also identify a neglected ``base-novel-conflict'' problem and introduce stratified label assignments to prevent it. Extensive experiments on COCO and LVIS datasets demonstrate that our method outperforms the other state-of-the-arts by significant margins. Codes are available at https://github.com/wkfdb/MarvelOVD

Haifan Gong, Hui Cheng, Yifan Xie et al.

Thyroid nodule classification aims at determining whether the nodule is benign or malignant based on a given ultrasound image. However, the label obtained by the cytological biopsy which is the golden standard in clinical medicine is not always consistent with the ultrasound imaging TI-RADS criteria. The information difference between the two causes the existing deep learning-based classification methods to be indecisive. To solve the Inconsistent Label problem, we propose an Adaptive Curriculum Learning (ACL) framework, which adaptively discovers and discards the samples with inconsistent labels. Specifically, ACL takes both hard sample and model certainty into account, and could accurately determine the threshold to distinguish the samples with Inconsistent Label. Moreover, we contribute TNCD: a Thyroid Nodule Classification Dataset to facilitate future related research on the thyroid nodules. Extensive experimental results on TNCD based on three different backbone networks not only demonstrate the superiority of our method but also prove that the less-is-more principle which strategically discards the samples with Inconsistent Label could yield performance gains. Source code and data are available at https://github.com/chenghui-666/ACL/.

Xinyi Yu, Guanbin Li, Wei Lou et al.

Nuclei segmentation is a fundamental but challenging task in the quantitative analysis of histopathology images. Although fully-supervised deep learning-based methods have made significant progress, a large number of labeled images are required to achieve great segmentation performance. Considering that manually labeling all nuclei instances for a dataset is inefficient, obtaining a large-scale human-annotated dataset is time-consuming and labor-intensive. Therefore, augmenting a dataset with only a few labeled images to improve the segmentation performance is of significant research and application value. In this paper, we introduce the first diffusion-based augmentation method for nuclei segmentation. The idea is to synthesize a large number of labeled images to facilitate training the segmentation model. To achieve this, we propose a two-step strategy. In the first step, we train an unconditional diffusion model to synthesize the Nuclei Structure that is defined as the representation of pixel-level semantic and distance transform. Each synthetic nuclei structure will serve as a constraint on histopathology image synthesis and is further post-processed to be an instance map. In the second step, we train a conditioned diffusion model to synthesize histopathology images based on nuclei structures. The synthetic histopathology images paired with synthetic instance maps will be added to the real dataset for training the segmentation model. The experimental results show that by augmenting 10% labeled real dataset with synthetic samples, one can achieve comparable segmentation results with the fully-supervised baseline. The code is released in: https://github.com/lhaof/Nudiff

Jingyu Zhuang, Chen Wang, Lingjie Liu et al.

Neural fields have achieved impressive advancements in view synthesis and scene reconstruction. However, editing these neural fields remains challenging due to the implicit encoding of geometry and texture information. In this paper, we propose DreamEditor, a novel framework that enables users to perform controlled editing of neural fields using text prompts. By representing scenes as mesh-based neural fields, DreamEditor allows localized editing within specific regions. DreamEditor utilizes the text encoder of a pretrained text-to-Image diffusion model to automatically identify the regions to be edited based on the semantics of the text prompts. Subsequently, DreamEditor optimizes the editing region and aligns its geometry and texture with the text prompts through score distillation sampling [29]. Extensive experiments have demonstrated that DreamEditor can accurately edit neural fields of real-world scenes according to the given text prompts while ensuring consistency in irrelevant areas. DreamEditor generates highly realistic textures and geometry, significantly surpassing previous works in both quantitative and qualitative evaluations.

Xinyu Xiong, Zihuang Wu, Shuangyi Tan et al.

Image segmentation plays an important role in vision understanding. Recently, the emerging vision foundation models continuously achieved superior performance on various tasks. Following such success, in this paper, we prove that the Segment Anything Model 2 (SAM2) can be a strong encoder for U-shaped segmentation models. We propose a simple but effective framework, termed SAM2-UNet, for versatile image segmentation. Specifically, SAM2-UNet adopts the Hiera backbone of SAM2 as the encoder, while the decoder uses the classic U-shaped design. Additionally, adapters are inserted into the encoder to allow parameter-efficient fine-tuning. Preliminary experiments on various downstream tasks, such as camouflaged object detection, salient object detection, marine animal segmentation, mirror detection, and polyp segmentation, demonstrate that our SAM2-UNet can simply beat existing specialized state-of-the-art methods without bells and whistles. Project page: \url{https://github.com/WZH0120/SAM2-UNet}.

Zijian He, Peixin Chen, Guangrun Wang et al.

Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos. Traditional image-based methods, relying on warping and blending, struggle with complex human movements and occlusions, limiting their effectiveness in video try-on applications. Moreover, video-based models require extensive, high-quality data and substantial computational resources. To tackle these issues, we reconceptualize video try-on as a process of generating videos conditioned on garment descriptions and human motion. Our solution, WildVidFit, employs image-based controlled diffusion models for a streamlined, one-stage approach. This model, conditioned on specific garments and individuals, is trained on still images rather than videos. It leverages diffusion guidance from pre-trained models including a video masked autoencoder for segment smoothness improvement and a self-supervised model for feature alignment of adjacent frame in the latent space. This integration markedly boosts the model's ability to maintain temporal coherence, enabling more effective video try-on within an image-based framework. Our experiments on the VITON-HD and DressCode datasets, along with tests on the VVT and TikTok datasets, demonstrate WildVidFit's capability to generate fluid and coherent videos. The project page website is at wildvidfit-project.github.io.

Jichang Li, Guanbin Li, Feng Liu et al.

Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. The key success of LNL lies in identifying as many clean samples as possible from massive noisy data, while rectifying the wrongly assigned noisy labels. Recent advances employ the predicted label distributions of individual samples to perform noise verification and noisy label correction, easily giving rise to confirmation bias. To mitigate this issue, we propose Neighborhood Collective Estimation, in which the predictive reliability of a candidate sample is re-estimated by contrasting it against its feature-space nearest neighbors. Specifically, our method is divided into two steps: 1) Neighborhood Collective Noise Verification to separate all training samples into a clean or noisy subset, 2) Neighborhood Collective Label Correction to relabel noisy samples, and then auxiliary techniques are used to assist further model optimization. Extensive experiments on four commonly used benchmark datasets, i.e., CIFAR-10, CIFAR-100, Clothing-1M and Webvision-1.0, demonstrate that our proposed method considerably outperforms state-of-the-art methods.

Yang Liu, Yushen Wei, Hong Yan et al.

Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing. Due to the emergence of huge amounts of multi-modal heterogeneous spatial/temporal/spatial-temporal data in big data era, the lack of interpretability, robustness, and out-of-distribution generalization are becoming the challenges of the existing visual models. The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge, which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities. Inspired by the strong inference ability of human-level agents, recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability. In this paper, we conduct a comprehensive review of existing causal reasoning methods for visual representation learning, covering fundamental theories, models, and datasets. The limitations of current methods and datasets are also discussed. Moreover, we propose some prospective challenges, opportunities, and future research directions for benchmarking causal reasoning algorithms in visual representation learning. This paper aims to provide a comprehensive overview of this emerging field, attract attention, encourage discussions, bring to the forefront the urgency of developing novel causal reasoning methods, publicly available benchmarks, and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently.

Ganlong Zhao, Guanbin Li, Yipeng Qin et al.

Deep models trained with noisy labels are prone to over-fitting and struggle in generalization. Most existing solutions are based on an ideal assumption that the label noise is class-conditional, i.e., instances of the same class share the same noise model, and are independent of features. While in practice, the real-world noise patterns are usually more fine-grained as instance-dependent ones, which poses a big challenge, especially in the presence of inter-class imbalance. In this paper, we propose a two-stage clean samples identification method to address the aforementioned challenge. First, we employ a class-level feature clustering procedure for the early identification of clean samples that are near the class-wise prediction centers. Notably, we address the class imbalance problem by aggregating rare classes according to their prediction entropy. Second, for the remaining clean samples that are close to the ground truth class boundary (usually mixed with the samples with instance-dependent noises), we propose a novel consistency-based classification method that identifies them using the consistency of two classifier heads: the higher the consistency, the larger the probability that a sample is clean. Extensive experiments on several challenging benchmarks demonstrate the superior performance of our method against the state-of-the-art.

Jiutao Yue, Haofeng Li, Pengxu Wei et al.

Recently deep neural networks (DNNs) have achieved significant success in real-world image super-resolution (SR). However, adversarial image samples with quasi-imperceptible noises could threaten deep learning SR models. In this paper, we propose a robust deep learning framework for real-world SR that randomly erases potential adversarial noises in the frequency domain of input images or features. The rationale is that on the SR task clean images or features have a different pattern from the attacked ones in the frequency domain. Observing that existing adversarial attacks usually add high-frequency noises to input images, we introduce a novel random frequency mask module that blocks out high-frequency components possibly containing the harmful perturbations in a stochastic manner. Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module. Based on the above ideas, we devise a novel real-world image SR framework that combines the proposed frequency mask modules and the proposed adversarial classifier with an existing super-resolution backbone network. Experiments show that our proposed method is more insensitive to adversarial attacks and presents more stable SR results than existing models and defenses.

Zhongying Deng, Cheng Tang, Ziyan Huang et al. · pku

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

Kuo Wang, Lingbo Liu, Yang Liu et al.

The prediction of traffic flow is a challenging yet crucial problem in spatial-temporal analysis, which has recently gained increasing interest. In addition to spatial-temporal correlations, the functionality of urban areas also plays a crucial role in traffic flow prediction. However, the exploration of regional functional attributes mainly focuses on adding additional topological structures, ignoring the influence of functional attributes on regional traffic patterns. Different from the existing works, we propose a novel module named POI-MetaBlock, which utilizes the functionality of each region (represented by Point of Interest distribution) as metadata to further mine different traffic characteristics in areas with different functions. Specifically, the proposed POI-MetaBlock employs a self-attention architecture and incorporates POI and time information to generate dynamic attention parameters for each region, which enables the model to fit different traffic patterns of various areas at different times. Furthermore, our lightweight POI-MetaBlock can be easily integrated into conventional traffic flow prediction models. Extensive experiments demonstrate that our module significantly improves the performance of traffic flow prediction and outperforms state-of-the-art methods that use metadata.

Zizheng Yan, Yushuang Wu, Guanbin Li et al.

Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. Specifically, our MCL regularizes the consistency of different views of target domain samples at three levels: (i) at inter-domain level, we robustly and accurately align the source and target domains using a prototype-based optimal transport method that utilizes the pros and cons of different views of target samples; (ii) at intra-domain level, we facilitate the learning of both discriminative and compact target feature representations by proposing a novel class-wise contrastive clustering loss; (iii) at sample level, we follow standard practice and improve the prediction accuracy by conducting a consistency-based self-training. Empirically, we verified the effectiveness of our MCL framework on three popular SSDA benchmarks, i.e., VisDA2017, DomainNet, and Office-Home datasets, and the experimental results demonstrate that our MCL framework achieves the state-of-the-art performance.

Zhihao Yuan, Xu Yan, Yinghong Liao et al.

3D dense captioning aims to describe individual objects by natural language in 3D scenes, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only exploiting single modal information, e.g., point cloud, previous approaches fail to produce faithful descriptions. Though aggregating 2D features into point clouds may be beneficial, it introduces an extra computational burden, especially in inference phases. In this study, we investigate a cross-modal knowledge transfer using Transformer for 3D dense captioning, X-Trans2Cap, to effectively boost the performance of single-modal 3D caption through knowledge distillation using a teacher-student framework. In practice, during the training phase, the teacher network exploits auxiliary 2D modality and guides the student network that only takes point clouds as input through the feature consistency constraints. Owing to the well-designed cross-modal feature fusion module and the feature alignment in the training phase, X-Trans2Cap acquires rich appearance information embedded in 2D images with ease. Thus, a more faithful caption can be generated only using point clouds during the inference. Qualitative and quantitative results confirm that X-Trans2Cap outperforms previous state-of-the-art by a large margin, i.e., about +21 and about +16 absolute CIDEr score on ScanRefer and Nr3D datasets, respectively.

Weixing Chen, Zhuoqian Feng, Yang Liu et al.

Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The challenge stems from dense object hierarchies and irregular affordances. Here, an interactive scene denotes a physically valid, collision-free environment directly loadable into physics simulators. Existing methods, ranging from decoupled symbolic solvers to end-to-end regression models, often suffer from error propagation or overfitting to noisy supervision containing widespread physical violations. To address these limitations, we introduce PhyScene3D, a framework that reformulates generation as a Human-Mimetic Constructive Process. The proposed Cognitive Topological Reasoning Chain (CTRC) factorizes scene synthesis into a sequential, anchor-conditioned process. It employs a 3D AABB-based placement scheme that imposes a strong structural inductive bias. To address imperfect supervision and physical infeasibility, we introduce Physics-Aware Denoising Alignment (PADA). It integrates a differentiable Signed Distance Field (SDF) with Test-Time Optimization (TTO) to project generated scenes onto a physics-feasible manifold while preserving semantic intent. Experiments demonstrate that PhyScene3D outperforms state-of-the-art approaches in both semantic accuracy and physical validity, achieving a 40% reduction in scene-wise collision rate relative to the human-annotated training data.

Jun Wei, Yiwen Hu, Guanbin Li et al.

Accurate polyp segmentation is of great importance for colorectal cancer diagnosis and treatment. However, due to the high cost of producing accurate mask annotations, existing polyp segmentation methods suffer from severe data shortage and impaired model generalization. Reversely, coarse polyp bounding box annotations are more accessible. Thus, in this paper, we propose a boosted BoxPolyp model to make full use of both accurate mask and extra coarse box annotations. In practice, box annotations are applied to alleviate the over-fitting issue of previous polyp segmentation models, which generate fine-grained polyp area through the iterative boosted segmentation model. To achieve this goal, a fusion filter sampling (FFS) module is firstly proposed to generate pixel-wise pseudo labels from box annotations with less noise, leading to significant performance improvements. Besides, considering the appearance consistency of the same polyp, an image consistency (IC) loss is designed. Such IC loss explicitly narrows the distance between features extracted by two different networks, which improves the robustness of the model. Note that our BoxPolyp is a plug-and-play model, which can be merged into any appealing backbone. Quantitative and qualitative experimental results on five challenging benchmarks confirm that our proposed model outperforms previous state-of-the-art methods by a large margin.

Duojun Huang, Jichang Li, Weikai Chen et al.

Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target samples. Conventional AL methods do not consider the existence of domain shift, and hence, fail to identify the truly valuable samples in the context of domain adaptation. To accommodate active learning and domain adaption, the two naturally different tasks, in a collaborative framework, we advocate that a customized learning strategy for the target data is the key to the success of ADA solutions. We present Divide-and-Adapt (DiaNA), a new ADA framework that partitions the target instances into four categories with stratified transferable properties. With a novel data subdivision protocol based on uncertainty and domainness, DiaNA can accurately recognize the most gainful samples. While sending the informative instances for annotation, DiaNA employs tailored learning strategies for the remaining categories. Furthermore, we propose an informativeness score that unifies the data partitioning criteria. This enables the use of a Gaussian mixture model (GMM) to automatically sample unlabeled data into the proposed four categories. Thanks to the "divideand-adapt" spirit, DiaNA can handle data with large variations of domain gap. In addition, we show that DiaNA can generalize to different domain adaptation settings, such as unsupervised domain adaptation (UDA), semi-supervised domain adaptation (SSDA), source-free domain adaptation (SFDA), etc.

Zhihong Chen, Guanbin Li, Xiang Wan

Medical vision-and-language pre-training (Med-VLP) has received considerable attention owing to its applicability to extracting generic vision-and-language representations from medical images and texts. Most existing methods mainly contain three elements: uni-modal encoders (i.e., a vision encoder and a language encoder), a multi-modal fusion module, and pretext tasks, with few studies considering the importance of medical domain expert knowledge and explicitly exploiting such knowledge to facilitate Med-VLP. Although there exist knowledge-enhanced vision-and-language pre-training (VLP) methods in the general domain, most require off-the-shelf toolkits (e.g., object detectors and scene graph parsers), which are unavailable in the medical domain. In this paper, we propose a systematic and effective approach to enhance Med-VLP by structured medical knowledge from three perspectives. First, considering knowledge can be regarded as the intermediate medium between vision and language, we align the representations of the vision encoder and the language encoder through knowledge. Second, we inject knowledge into the multi-modal fusion model to enable the model to perform reasoning using knowledge as the supplementation of the input image and text. Third, we guide the model to put emphasis on the most critical information in images and texts by designing knowledge-induced pretext tasks. To perform a comprehensive evaluation and facilitate further research, we construct a medical vision-and-language benchmark including three tasks. Experimental results illustrate the effectiveness of our approach, where state-of-the-art performance is achieved on all downstream tasks. Further analyses explore the effects of different components of our approach and various settings of pre-training.

Wei Lou, Haofeng Li, Guanbin Li et al.

Recently deep neural networks, which require a large amount of annotated samples, have been widely applied in nuclei instance segmentation of H\&E stained pathology images. However, it is inefficient and unnecessary to label all pixels for a dataset of nuclei images which usually contain similar and redundant patterns. Although unsupervised and semi-supervised learning methods have been studied for nuclei segmentation, very few works have delved into the selective labeling of samples to reduce the workload of annotation. Thus, in this paper, we propose a novel full nuclei segmentation framework that chooses only a few image patches to be annotated, augments the training set from the selected samples, and achieves nuclei segmentation in a semi-supervised manner. In the proposed framework, we first develop a novel consistency-based patch selection method to determine which image patches are the most beneficial to the training. Then we introduce a conditional single-image GAN with a component-wise discriminator, to synthesize more training samples. Lastly, our proposed framework trains an existing segmentation model with the above augmented samples. The experimental results show that our proposed method could obtain the same-level performance as a fully-supervised baseline by annotating less than 5% pixels on some benchmarks.

Ricong Huang, Peiwen Lai, Yipeng Qin et al.

Audio-driven facial reenactment is a crucial technique that has a range of applications in film-making, virtual avatars and video conferences. Existing works either employ explicit intermediate face representations (e.g., 2D facial landmarks or 3D face models) or implicit ones (e.g., Neural Radiance Fields), thus suffering from the trade-offs between interpretability and expressive power, hence between controllability and quality of the results. In this work, we break these trade-offs with our novel parametric implicit face representation and propose a novel audio-driven facial reenactment framework that is both controllable and can generate high-quality talking heads. Specifically, our parametric implicit representation parameterizes the implicit representation with interpretable parameters of 3D face models, thereby taking the best of both explicit and implicit methods. In addition, we propose several new techniques to improve the three components of our framework, including i) incorporating contextual information into the audio-to-expression parameters encoding; ii) using conditional image synthesis to parameterize the implicit representation and implementing it with an innovative tri-plane structure for efficient learning; iii) formulating facial reenactment as a conditional image inpainting problem and proposing a novel data augmentation technique to improve model generalizability. Extensive experiments demonstrate that our method can generate more realistic results than previous methods with greater fidelity to the identities and talking styles of speakers.

Wei Lou, Xinyi Yu, Chenyu Liu et al.

Cell segmentation for multi-modal microscopy images remains a challenge due to the complex textures, patterns, and cell shapes in these images. To tackle the problem, we first develop an automatic cell classification pipeline to label the microscopy images based on their low-level image characteristics, and then train a classification model based on the category labels. Afterward, we train a separate segmentation model for each category using the images in the corresponding category. Besides, we further deploy two types of segmentation models to segment cells with roundish and irregular shapes respectively. Moreover, an efficient and powerful backbone model is utilized to enhance the efficiency of our segmentation model. Evaluated on the Tuning Set of NeurIPS 2022 Cell Segmentation Challenge, our method achieves an F1-score of 0.8795 and the running time for all cases is within the time tolerance.

Tao Chen, Ze Lin, Hui Li et al.

Given the long textual product information and the product image, Multi-modal Product Summarization (MPS) aims to increase customers' desire to purchase by highlighting product characteristics with a short textual summary. Existing MPS methods can produce promising results. Nevertheless, they still 1) lack end-to-end product summarization, 2) lack multi-grained multi-modal modeling, and 3) lack multi-modal attribute modeling. To improve MPS, we propose an end-to-end multi-grained multi-modal attribute-aware product summarization method (MMAPS) for generating high-quality product summaries in e-commerce. MMAPS jointly models product attributes and generates product summaries. We design several multi-grained multi-modal tasks to better guide the multi-modal learning of MMAPS. Furthermore, we model product attributes based on both text and image modalities so that multi-modal product characteristics can be manifested in the generated summaries. Extensive experiments on a real large-scale Chinese e-commence dataset demonstrate that our model outperforms state-of-the-art product summarization methods w.r.t. several summarization metrics. Our code is publicly available at: https://github.com/KDEGroup/MMAPS.

Lechao Cheng, Chaowei Fang, Dingwen Zhang et al.

Significant progress has been made in learning image classification neural networks under long-tail data distribution using robust training algorithms such as data re-sampling, re-weighting, and margin adjustment. Those methods, however, ignore the impact of data imbalance on feature normalization. The dominance of majority classes (head classes) in estimating statistics and affine parameters causes internal covariate shifts within less-frequent categories to be overlooked. To alleviate this challenge, we propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. In addition, a moving average-based expectation maximization (EM) algorithm is employed to estimate the statistical parameters of multiple Gaussian distributions. However, the EM algorithm is sensitive to initialization and can easily become stuck in local minima where the multiple Gaussian components continue to focus on majority classes. To tackle this issue, we developed a dual-path learning framework that employs class-aware split feature normalization to diversify the estimated Gaussian distributions, allowing the Gaussian components to fit with training samples of less-frequent classes more comprehensively. Extensive experiments on commonly used datasets demonstrated that the proposed method outperforms existing methods on long-tailed image classification.

Haofeng Li, Junjia Huang, Guanbin Li et al.

Deep neural networks (DNNs) have been widely adopted in brain lesion detection and segmentation. However, locating small lesions in 2D MRI slices is challenging, and requires to balance between the granularity of 3D context aggregation and the computational complexity. In this paper, we propose a novel view-disentangled transformer to enhance the extraction of MRI features for more accurate tumour detection. First, the proposed transformer harvests long-range correlation among different positions in a 3D brain scan. Second, the transformer models a stack of slice features as multiple 2D views and enhance these features view-by-view, which approximately achieves the 3D correlation computing in an efficient way. Third, we deploy the proposed transformer module in a transformer backbone, which can effectively detect the 2D regions surrounding brain lesions. The experimental results show that our proposed view-disentangled transformer performs well for brain lesion detection on a challenging brain MRI dataset.

Jingyu Zhuang, Ziliang Chen, Pengxu Wei et al.

In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain. Due to the lack of their specific belonging, existing methods indiscriminately regard them as a single class unknown. We challenge this broadly-adopted practice that may arouse unexpected detrimental effects because the decision boundaries between the implicit categories have been fully ignored. Instead, we propose Self-supervised Class-Discovering Adapter (SCDA) that attempts to achieve OSDA by gradually discovering those implicit classes, then incorporating them to restructure the classifier and update the domain-adaptive features iteratively. SCDA performs two alternate steps to achieve implicit class discovery and self-supervised OSDA, respectively. By jointly optimizing for two tasks, SCDA achieves the state-of-the-art in OSDA and shows a competitive performance to unearth the implicit target classes.

Ganlong Zhao, Guanbin Li, Yipeng Qin et al.

In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples. Unlike previous methods that only consider ID samples to be useful and aim to filter out OOD ones completely during training, we argue that the exploration and exploitation of both ID and OOD samples can benefit SSL. To support our claim, i) we propose a prototype-based clustering and identification algorithm that explores the inherent similarity and difference among samples at feature level and effectively cluster them around several predefined ID and OOD prototypes, thereby enhancing feature learning and facilitating ID/OOD identification; ii) we propose an importance-based sampling method that exploits the difference in importance of each ID and OOD sample to SSL, thereby reducing the sampling bias and improving the training. Our proposed method achieves state-of-the-art in several challenging benchmarks, and improves upon existing SSL methods even when ID samples are totally absent in unlabeled data.

Zhihong Chen, Shizhe Diao, Benyou Wang et al.

Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representations from medical images and texts. Practically, there exist two typical types, \textit{i.e.}, the fusion-encoder type and the dual-encoder type, depending on whether a heavy fusion module is used. The former is superior at multi-modal tasks owing to the sufficient interaction between modalities; the latter is good at uni-modal and cross-modal tasks due to the single-modality encoding ability. To take advantage of these two types, we propose an effective yet straightforward scheme named PTUnifier to unify the two types. We first unify the input format by introducing visual and textual prompts, which serve as a feature bank that stores the most representative images/texts. By doing so, a single model could serve as a \textit{foundation model} that processes various tasks adopting different input formats (\textit{i.e.}, image-only, text-only, and image-text-pair). Furthermore, we construct a prompt pool (instead of static ones) to improve diversity and scalability. Experimental results show that our approach achieves state-of-the-art results on a broad range of tasks, spanning uni-modal tasks (\textit{i.e.}, image/text classification and text summarization), cross-modal tasks (\textit{i.e.}, image-to-text generation and image-text/text-image retrieval), and multi-modal tasks (\textit{i.e.}, visual question answering), demonstrating the effectiveness of our approach. Note that the adoption of prompts is orthogonal to most existing Med-VLP approaches and could be a beneficial and complementary extension to these approaches.

Zhijia Liang, Jiaming Li, Weikai Chen et al.

Streaming video reasoning requires models to operate in a setting where history grows without bound while meaningful evidence remains scarce. In such a landscape, relevant signal is like an oasis-small, critical, and easily lost in a desert of redundancy. Enlarging memory only widens the desert; aggressive compression dries up the oasis. The real difficulty lies in discovering where to look, not how much to remember. We therefore introduce OASIS, a novel framework for streaming video reasoning that tackles this challenge through structured, on-demand retrieval. It organizes streaming history into hierarchical events and performs reasoning as controlled refinement-short-context inference first, followed by semantically grounded retrieval only when uncertainty arises. As the retrieval is driven by high-level intent rather than embedding similarity, the retrieved memory is substantially more accurate and less noisy. Additionally, the mechanism is plug-and-play, training-free, and readily attaches to different streaming MLLM backbones. Experiments across multiple benchmarks and backbones show that OASIS achieves strong gains in long-horizon accuracy and compositional reasoning with bounded token cost and low request delay. Code is available at https://github.com/Solus-sano/OASIS.

Weizhi Zhong, Jichang Li, Yinqi Cai et al.

Audio-driven lip sync has recently drawn significant attention due to its widespread application in the multimedia domain. Individuals exhibit distinct lip shapes when speaking the same utterance, attributed to the unique speaking styles of individuals, posing a notable challenge for audio-driven lip sync. Earlier methods for such task often bypassed the modeling of personalized speaking styles, resulting in sub-optimal lip sync conforming to the general styles. Recent lip sync techniques attempt to guide the lip sync for arbitrary audio by aggregating information from a style reference video, yet they can not preserve the speaking styles well due to their inaccuracy in style aggregation. This work proposes an innovative audio-aware style reference scheme that effectively leverages the relationships between input audio and reference audio from style reference video to address the style-preserving audio-driven lip sync. Specifically, we first develop an advanced Transformer-based model adept at predicting lip motion corresponding to the input audio, augmented by the style information aggregated through cross-attention layers from style reference video. Afterwards, to better render the lip motion into realistic talking face video, we devise a conditional latent diffusion model, integrating lip motion through modulated convolutional layers and fusing reference facial images via spatial cross-attention layers. Extensive experiments validate the efficacy of the proposed approach in achieving precise lip sync, preserving speaking styles, and generating high-fidelity, realistic talking face videos.

Yushuang Wu, Zizheng Yan, Ce Chen et al.

3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g. 3D computer-aided design models. However, the domain gap between synthetic and real data limits the generalizability of these methods. Thus, we propose a new task, SCoDA, for the domain adaptation of real scan shape completion from synthetic data. A new dataset, ScanSalon, is contributed with a bunch of elaborate 3D models created by skillful artists according to scans. To address this new task, we propose a novel cross-domain feature fusion method for knowledge transfer and a novel volume-consistent self-training framework for robust learning from real data. Extensive experiments prove our method is effective to bring an improvement of 6%~7% mIoU.

Yuncheng Jiang, Zixun Zhang, Ruimao Zhang et al.

Accurate polyp detection is essential for assisting clinical rectal cancer diagnoses. Colonoscopy videos contain richer information than still images, making them a valuable resource for deep learning methods. Great efforts have been made to conduct video polyp detection through multi-frame temporal/spatial aggregation. However, unlike common fixed-camera video, the camera-moving scene in colonoscopy videos can cause rapid video jitters, leading to unstable training for existing video detection models. Additionally, the concealed nature of some polyps and the complex background environment further hinder the performance of existing video detectors. In this paper, we propose the \textbf{YONA} (\textbf{Y}ou \textbf{O}nly \textbf{N}eed one \textbf{A}djacent Reference-frame) method, an efficient end-to-end training framework for video polyp detection. YONA fully exploits the information of one previous adjacent frame and conducts polyp detection on the current frame without multi-frame collaborations. Specifically, for the foreground, YONA adaptively aligns the current frame's channel activation patterns with its adjacent reference frames according to their foreground similarity. For the background, YONA conducts background dynamic alignment guided by inter-frame difference to eliminate the invalid features produced by drastic spatial jitters. Moreover, YONA applies cross-frame contrastive learning during training, leveraging the ground truth bounding box to improve the model's perception of polyp and background. Quantitative and qualitative experiments on three public challenging benchmarks demonstrate that our proposed YONA outperforms previous state-of-the-art competitors by a large margin in both accuracy and speed.

Jiaming Li, Zhijia Liang, Weikai Chen et al.

Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories described by attribute-rich texts. While existing open-vocabulary detectors show promise at the base-category level, they underperform in fine-grained settings due to the semantic entanglement of subjects and attributes in pretrained vision-language model (VLM) embeddings -- leading to over-representation of attributes, mislocalization, and semantic drift in embedding space. We propose GUIDED, a decomposition framework specifically designed to address the semantic entanglement between subjects and attributes in fine-grained prompts. By separating object localization and fine-grained recognition into distinct pathways, HUIDED aligns each subtask with the module best suited for its respective roles. Specifically, given a fine-grained class name, we first use a language model to extract a coarse-grained subject and its descriptive attributes. Then the detector is guided solely by the subject embedding, ensuring stable localization unaffected by irrelevant or overrepresented attributes. To selectively retain helpful attributes, we introduce an attribute embedding fusion module that incorporates attribute information into detection queries in an attention-based manner. This mitigates over-representation while preserving discriminative power. Finally, a region-level attribute discrimination module compares each detected region against full fine-grained class names using a refined vision-language model with a projection head for improved alignment. Extensive experiments on FG-OVD and 3F-OVD benchmarks show that GUIDED achieves new state-of-the-art results, demonstrating the benefits of disentangled modeling and modular optimization. Our code will be released at https://github.com/lijm48/GUIDED.

Wei Lou, Xiang Wan, Guanbin Li et al.

Nuclei classification provides valuable information for histopathology image analysis. However, the large variations in the appearance of different nuclei types cause difficulties in identifying nuclei. Most neural network based methods are affected by the local receptive field of convolutions, and pay less attention to the spatial distribution of nuclei or the irregular contour shape of a nucleus. In this paper, we first propose a novel polygon-structure feature learning mechanism that transforms a nucleus contour into a sequence of points sampled in order, and employ a recurrent neural network that aggregates the sequential change in distance between key points to obtain learnable shape features. Next, we convert a histopathology image into a graph structure with nuclei as nodes, and build a graph neural network to embed the spatial distribution of nuclei into their representations. To capture the correlations between the categories of nuclei and their surrounding tissue patterns, we further introduce edge features that are defined as the background textures between adjacent nuclei. Lastly, we integrate both polygon and graph structure learning mechanisms into a whole framework that can extract intra and inter-nucleus structural characteristics for nuclei classification. Experimental results show that the proposed framework achieves significant improvements compared to the state-of-the-art methods.