{"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/vita-video-instance-segmentation-via-object","title":"VITA: Video Instance Segmentation via Object Token Association","arxiv_id":"2206.04403","date":"2022-06-09","proceeding":null,"authors":["Miran Heo","Sukjun Hwang","Seoung Wug Oh","Joon-Young Lee","Seon Joo Kim"],"abstract":"We introduce a novel paradigm for offline Video Instance Segmentation (VIS), based on the hypothesis that explicit object-oriented information can be a strong clue for understanding the context of the entire sequence. To this end, we propose VITA, a simple structure built on top of an off-the-shelf Transformer-based image instance segmentation model. Specifically, we use an image object detector as a means of distilling object-specific contexts into object tokens. VITA accomplishes video-level understanding by associating frame-level object tokens without using spatio-temporal backbone features. By effectively building relationships between objects using the condensed information, VITA achieves the state-of-the-art on VIS benchmarks with a ResNet-50 backbone: 49.8 AP, 45.7 AP on YouTube-VIS 2019 & 2021, and 19.6 AP on OVIS. Moreover, thanks to its object token-based structure that is disjoint from the backbone features, VITA shows several practical advantages that previous offline VIS methods have not explored - handling long and high-resolution videos with a common GPU, and freezing a frame-level detector trained on image domain. Code is available at https://github.com/sukjunhwang/VITA.","url_abs":"https://arxiv.org/abs/2206.04403v2","url_pdf":"https://arxiv.org/pdf/2206.04403v2.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":"vita-video-instance-segmentation-via-object","repo_url":"https://github.com/sukjunhwang/vita","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-instance-segmentation-on-ovis-1","task":"Video Instance Segmentation","dataset":"OVIS validation","model":"VITA (Swin-L)","rank_in_archive_order":32,"of":44,"metrics":{"AP50":"51.9","AP75":"24.9","AR1":"14.9","AR10":"33.0","mask AP":"27.7"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-2","task":"Video Instance Segmentation","dataset":"YouTube-VIS 2021","model":"VITA (Swin-L)","rank_in_archive_order":13,"of":26,"metrics":{"AP50":"80.6","AP75":"61.0","AR1":"47.7","AR10":"62.6","mask AP":"57.5"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.04403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04403"}},"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/sukjunhwang/vita","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":0,"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":"bc2cb481a75c370d","entry":"batch_dice_loss","repo":"sukjunhwang/vita","repo_kind":"official","path":"vita/modeling/vita_matcher.py","file_url":"https://github.com/sukjunhwang/vita/blob/HEAD/vita/modeling/vita_matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"code_sha256_prefix":"1edd24985036b0bf","entry":"batch_sigmoid_ce_loss","repo":"sukjunhwang/vita","repo_kind":"official","path":"vita/modeling/vita_matcher.py","file_url":"https://github.com/sukjunhwang/vita/blob/HEAD/vita/modeling/vita_matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1edd24985036b0bf"}},{"code_sha256_prefix":"2dcb8123d89bb1ff","entry":"calculate_uncertainty","repo":"sukjunhwang/vita","repo_kind":"official","path":"vita/modeling/vita_criterion.py","file_url":"https://github.com/sukjunhwang/vita/blob/HEAD/vita/modeling/vita_criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2dcb8123d89bb1ff"}},{"code_sha256_prefix":"89f75e54ff128be0","entry":"dice_loss","repo":"sukjunhwang/vita","repo_kind":"official","path":"vita/modeling/vita_criterion.py","file_url":"https://github.com/sukjunhwang/vita/blob/HEAD/vita/modeling/vita_criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"89f75e54ff128be0"}},{"code_sha256_prefix":"47bff92e02f2844a","entry":"interpolate","repo":"sukjunhwang/vita","repo_kind":"official","path":"vita/utils/misc.py","file_url":"https://github.com/sukjunhwang/vita/blob/HEAD/vita/utils/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"47bff92e02f2844a"}},{"code_sha256_prefix":"58cc9ff3bf75e753","entry":"nested_tensor_from_tensor_list","repo":"sukjunhwang/vita","repo_kind":"official","path":"vita/utils/misc.py","file_url":"https://github.com/sukjunhwang/vita/blob/HEAD/vita/utils/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"58cc9ff3bf75e753"}},{"code_sha256_prefix":"d0c61e8dba511aa3","entry":"sigmoid_ce_loss","repo":"sukjunhwang/vita","repo_kind":"official","path":"vita/modeling/vita_criterion.py","file_url":"https://github.com/sukjunhwang/vita/blob/HEAD/vita/modeling/vita_criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d0c61e8dba511aa3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}