{"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/video-k-net-a-simple-strong-and-unified","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","arxiv_id":"2204.04656","date":"2022-04-10","proceeding":"CVPR 2022 1","authors":["Xiangtai Li","Wenwei Zhang","Jiangmiao Pang","Kai Chen","Guangliang Cheng","Yunhai Tong","Chen Change Loy"],"abstract":"This paper presents Video K-Net, a simple, strong, and unified framework for fully end-to-end video panoptic segmentation. The method is built upon K-Net, a method that unifies image segmentation via a group of learnable kernels. We observe that these learnable kernels from K-Net, which encode object appearances and contexts, can naturally associate identical instances across video frames. Motivated by this observation, Video K-Net learns to simultaneously segment and track \"things\" and \"stuff\" in a video with simple kernel-based appearance modeling and cross-temporal kernel interaction. Despite the simplicity, it achieves state-of-the-art video panoptic segmentation results on Citscapes-VPS, KITTI-STEP, and VIPSeg without bells and whistles. In particular, on KITTI-STEP, the simple method can boost almost 12\\% relative improvements over previous methods. On VIPSeg, Video K-Net boosts almost 15\\% relative improvements and results in 39.8 % VPQ. We also validate its generalization on video semantic segmentation, where we boost various baselines by 2\\% on the VSPW dataset. Moreover, we extend K-Net into clip-level video framework for video instance segmentation, where we obtain 40.5% mAP for ResNet50 backbone and 54.1% mAP for Swin-base on YouTube-2019 validation set. We hope this simple, yet effective method can serve as a new, flexible baseline in unified video segmentation design. Both code and models are released at https://github.com/lxtGH/Video-K-Net.","url_abs":"https://arxiv.org/abs/2204.04656v2","url_pdf":"https://arxiv.org/pdf/2204.04656v2.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":[{"paper_slug":"video-k-net-a-simple-strong-and-unified","repo_url":"https://github.com/lxtgh/video-k-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic 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"},{"task_slug":"video-panoptic-segmentation","task_name":"Video Panoptic Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"k-net","method_name":"K-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"Video K-Net (Swin-Base)","rank_in_archive_order":13,"of":44,"metrics":{"AP50":"79.0","AP75":"59.6","AR1":"49.7","AR10":"59.9","mask AP":"54.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-panoptic-segmentation-on-cityscapes-vps","task":"Video Panoptic Segmentation","dataset":"Cityscapes-VPS","model":"Video K-Net (Swin-B)","rank_in_archive_order":3,"of":8,"metrics":{"VPQ":"62.2","VPQ (stuff)":"71.8","VPQ (thing)":"49.8"},"uses_additional_data":true},{"leaderboard":"/sota/video-panoptic-segmentation-on-kitti-step","task":"Video Panoptic Segmentation","dataset":"KITTI-STEP","model":"Video K-Net (Swin-L)","rank_in_archive_order":1,"of":6,"metrics":{"AQ":"73.0","SQ":"75.0","STQ":"74.0"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.04656","atlas_url":"https://app.syntology.ai/?focus=2204.04656","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}