{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/stc-spatio-temporal-contrastive-learning-for","title":"STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation","arxiv_id":"2202.03747","date":"2022-02-08","proceeding":null,"authors":["Zhengkai Jiang","Zhangxuan Gu","Jinlong Peng","Hang Zhou","Liang Liu","Yabiao Wang","Ying Tai","Chengjie Wang","Liqing Zhang"],"abstract":"Video Instance Segmentation (VIS) is a task that simultaneously requires classification, segmentation, and instance association in a video. Recent VIS approaches rely on sophisticated pipelines to achieve this goal, including RoI-related operations or 3D convolutions. In contrast, we present a simple and efficient single-stage VIS framework based on the instance segmentation method CondInst by adding an extra tracking head. To improve instance association accuracy, a novel bi-directional spatio-temporal contrastive learning strategy for tracking embedding across frames is proposed. Moreover, an instance-wise temporal consistency scheme is utilized to produce temporally coherent results. Experiments conducted on the YouTube-VIS-2019, YouTube-VIS-2021, and OVIS-2021 datasets validate the effectiveness and efficiency of the proposed method. We hope the proposed framework can serve as a simple and strong alternative for many other instance-level video association tasks.","url_abs":"https://arxiv.org/abs/2202.03747v2","url_pdf":"https://arxiv.org/pdf/2202.03747v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"}],"methods":[{"method_slug":"condinst","method_name":"CondInst"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-instance-segmentation-on-ovis-1","task":"Video Instance Segmentation","dataset":"OVIS validation","model":"STC (ResNet-50)","rank_in_archive_order":40,"of":44,"metrics":{"AP50":"33.5","AP75":"13.4","mask AP":"15.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"STC (ResNet-50)","rank_in_archive_order":28,"of":44,"metrics":{"AP50":"57.2","AP75":"38.6","AR1":"36.9","AR10":"44.5","mask AP":"36.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.03747","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}