Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation. Code is available at: https://hkchengrex.github.io/Tracking-Anything-with-DEVA
DeSAM: Decoupled Segment Anything Model for Generalizable Medical Image Segmentation
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences（中国科学院苏州生物医学工程技术研究所）；The Hong Kong Polytechnic University（香港理工大学）
Shanghai Jiao Tong University（上海交通大学）；WeChat, Tencent Inc（腾讯公司微信事业部）；University of Science and Technology of China（中国科学技术大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Zhejiang University（浙江大学）
The Hong Kong University of Science and Technology（香港科技大学）；Tencent（腾讯）
Significant progress has been made in Video Object Segmentation (VOS), the video object tracking task in its finest level. While the VOS task can be naturally decoupled into image semantic segmentation and video object tracking, significantly much more research effort has been made in segmentation than tracking. In this paper, we introduce "tracking-by-detection" into VOS which can coherently integrate segmentation into tracking, by proposing a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance. Notably, …
De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation
School of Computer Science, University of Nottingham Ningbo China（诺丁汉大学宁波校区计算机科学学院）；Department of Electronic Engineering, The Chinese University of Hong Kong（香港中文大学电子工程系）；School of School of Engineering & Physical Sciences, University of Lincoln（林肯大学工程与物理科学学院）；Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港科学与创新研究院）；School of Computer Science, University of Nottingham（诺丁汉大学计算机科学学院）；The Hong Kong Polytechnic University（香港理工大学）
In this work, we address the TrackRAD2025 challenge of real-time tumor tracking in cine-MRI sequences of the thoracic and abdominal regions under strong data scarcity constraints. Two complementary strategies were explored: (i) unsupervised registration with the IMPACT similarity metric and (ii) foundation model-based segmentation leveraging SAM 2.1 and its recent variants through prompt-based interaction. Due to the one-second runtime constraint, the SAM-based method was ultimately selected. The final configuration used SAM2.1 b+ with mask-based prompts from the first annotated slice, fine-tu…
Segment-Anything Models Achieve Zero-shot Robustness in Autonomous Driving
College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Graz University of Technology（格拉茨工业大学）；Virtual Vehicle Research（虚拟车辆研究院）
Object tracking is a fundamental task in computer vision with broad practical applications across various domains, including traffic monitoring, robotics, and autonomous vehicle tracking. In this project, we aim to develop a sophisticated aerial vehicle system known as Track Anything Rapter (TAR), designed to detect, segment, and track objects of interest based on user-provided multimodal queries, such as text, images, and clicks. TAR utilizes cutting-edge pre-trained models like DINO, CLIP, and SAM to estimate the relative pose of the queried object. The tracking problem is approached as a Vi…
Static Segmentation by Tracking: A Label-Efficient Approach for Fine-Grained Specimen Image Segmentation
The Ohio State University（俄亥俄州立大学）；Princeton University（普林斯顿大学）；University of Maine（缅因大学）；University of Miami（迈阿密大学）；Virginia Tech（弗吉尼亚理工大学）；Duke University（杜克大学）；Rensselaer Polytechnic Institute（拉特格斯理工学院）
DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking
Shenzhen International Graudate School Tsinghua University（清华大学深圳国际研究生院）；The Hong Kong University of Science and Technology (Guang Zhou)（香港科学与技术大学（广州））；Department of Electronic Engineering Tsinghua University（清华大学电子工程系）
Huazhong Univerisity of Science and Technology（华中科技大学）；Tsinghua University（清华大学）
Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID). In order to enhance the inference speed and reduce the complexity, current methods commonly integrate these double subtasks into a unified framework. Nevertheless, detection and ReID demand diverse features. This issue would result in an optimization contradiction during the training procedure. With the target of alleviating this contradiction, we devise a module named Global Context Disentangling (GCD) that decouples the learned representation into detection-specifi…
pFedSAM: Personalized Federated Learning of Segment Anything Model for Medical Image Segmentation
College of Computer Science and Technology, Zhejiang University, China（浙江大学计算机科学与技术学院）；Chinese Academy of Medical Sciences and Peking Union Medical College, China（中国医学科学院与北京协和医学院）；School of Computer Science, Wuhan University, China（武汉大学计算机学院）；Innovation Centre for Information, Binjiang Institute of Zhejiang University（浙江大学滨江学院信息创新中心）；Department of Data and Information, Children's Hospital, Zhejiang University School of Medicine（浙江大学医学院附属儿童医院数据与信息部）
