{"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/mask2former-for-video-instance-segmentation","title":"Mask2Former for Video Instance Segmentation","arxiv_id":"2112.10764","date":"2021-12-20","proceeding":null,"authors":["Bowen Cheng","Anwesa Choudhuri","Ishan Misra","Alexander Kirillov","Rohit Girdhar","Alexander G. Schwing"],"abstract":"We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline. In this report, we show universal image segmentation architectures trivially generalize to video segmentation by directly predicting 3D segmentation volumes. Specifically, Mask2Former sets a new state-of-the-art of 60.4 AP on YouTubeVIS-2019 and 52.6 AP on YouTubeVIS-2021. We believe Mask2Former is also capable of handling video semantic and panoptic segmentation, given its versatility in image segmentation. We hope this will make state-of-the-art video segmentation research more accessible and bring more attention to designing universal image and video segmentation architectures.","url_abs":"https://arxiv.org/abs/2112.10764v1","url_pdf":"https://arxiv.org/pdf/2112.10764v1.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":"mask2former-for-video-instance-segmentation","repo_url":"https://github.com/facebookresearch/Mask2Former","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mask2former-for-video-instance-segmentation","repo_url":"https://github.com/nihalsid/mask2former","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mask2former-for-video-instance-segmentation","repo_url":"https://github.com/alibaba/EasyCV","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"mask2former-for-video-instance-segmentation","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"mask2former-for-video-instance-segmentation","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mask2former-for-video-instance-segmentation","repo_url":"https://github.com/pwc-1/Paper-5/tree/main/mask2former","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-instance-segmentation-on-ovis-1","task":"Video Instance Segmentation","dataset":"OVIS validation","model":"Mask2Former-VIS","rank_in_archive_order":39,"of":44,"metrics":{"AP50":"36.9","AP75":"14.1","AR1":"9.9","AR10":"24.7","mask AP":"16.6"},"uses_additional_data":false},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"Mask2Former (Swin-L)","rank_in_archive_order":6,"of":44,"metrics":{"AP50":"84.4","AP75":"67.0","mask AP":"60.4"},"uses_additional_data":false},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"Mask2Former (ResNet-101)","rank_in_archive_order":16,"of":44,"metrics":{"AP50":"72.8","AP75":"54.2","mask AP":"49.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"Mask2Former (ResNet-50)","rank_in_archive_order":20,"of":44,"metrics":{"AP50":"68.0","AP75":"50.0","mask AP":"46.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.10764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10764"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-5/tree/main/mask2former","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/EasyCV","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/Mask2Former","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nihalsid/mask2former","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"listed":{"samples":7,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"nihalsid/mask2former","repo_kind":"listed","path":"mask2former/modeling/backbone/swin.py","file_url":"https://github.com/nihalsid/mask2former/blob/HEAD/mask2former/modeling/backbone/swin.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"nihalsid/mask2former","repo_kind":"listed","path":"mask2former/modeling/backbone/swin.py","file_url":"https://github.com/nihalsid/mask2former/blob/HEAD/mask2former/modeling/backbone/swin.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"bc2cb481a75c370d","entry":"batch_dice_loss","repo":"nihalsid/mask2former","repo_kind":"listed","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/nihalsid/mask2former/blob/HEAD/mask2former/modeling/matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"code_sha256_prefix":"1edd24985036b0bf","entry":"batch_sigmoid_ce_loss","repo":"nihalsid/mask2former","repo_kind":"listed","path":"mask2former/modeling/matcher.py","file_url":"https://github.com/nihalsid/mask2former/blob/HEAD/mask2former/modeling/matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1edd24985036b0bf"}},{"code_sha256_prefix":"2dcb8123d89bb1ff","entry":"calculate_uncertainty","repo":"nihalsid/mask2former","repo_kind":"listed","path":"mask2former/modeling/criterion.py","file_url":"https://github.com/nihalsid/mask2former/blob/HEAD/mask2former/modeling/criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2dcb8123d89bb1ff"}},{"code_sha256_prefix":"89f75e54ff128be0","entry":"dice_loss","repo":"nihalsid/mask2former","repo_kind":"listed","path":"mask2former/modeling/criterion.py","file_url":"https://github.com/nihalsid/mask2former/blob/HEAD/mask2former/modeling/criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89f75e54ff128be0"}},{"code_sha256_prefix":"d0c61e8dba511aa3","entry":"sigmoid_ce_loss","repo":"nihalsid/mask2former","repo_kind":"listed","path":"mask2former/modeling/criterion.py","file_url":"https://github.com/nihalsid/mask2former/blob/HEAD/mask2former/modeling/criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0c61e8dba511aa3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}