{"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-instance-segmentation-with-a-propose","title":"Video Instance Segmentation with a Propose-Reduce Paradigm","arxiv_id":"2103.13746","date":"2021-03-25","proceeding":"ICCV 2021 10","authors":["Huaijia Lin","Ruizheng Wu","Shu Liu","Jiangbo Lu","Jiaya Jia"],"abstract":"Video instance segmentation (VIS) aims to segment and associate all instances of predefined classes for each frame in videos. Prior methods usually obtain segmentation for a frame or clip first, and merge the incomplete results by tracking or matching. These methods may cause error accumulation in the merging step. Contrarily, we propose a new paradigm -- Propose-Reduce, to generate complete sequences for input videos by a single step. We further build a sequence propagation head on the existing image-level instance segmentation network for long-term propagation. To ensure robustness and high recall of our proposed framework, multiple sequences are proposed where redundant sequences of the same instance are reduced. We achieve state-of-the-art performance on two representative benchmark datasets -- we obtain 47.6% in terms of AP on YouTube-VIS validation set and 70.4% for J&F on DAVIS-UVOS validation set. Code is available at https://github.com/dvlab-research/ProposeReduce.","url_abs":"https://arxiv.org/abs/2103.13746v2","url_pdf":"https://arxiv.org/pdf/2103.13746v2.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-instance-segmentation-with-a-propose","repo_url":"https://github.com/dvlab-research/proposereduce","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-video-object-segmentation","task_name":"Unsupervised Video Object Segmentation"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-4","task":"Unsupervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"Propose-Reduce","rank_in_archive_order":2,"of":10,"metrics":{"F-measure (Mean)":"73.8","J&F":"70.4","Jaccard (Mean)":"67.0"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.13746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13746"}},"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/dvlab-research/proposereduce","reach":null}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"7e8ca60fbece7dea","entry":"Refine","repo":"dvlab-research/proposereduce","repo_kind":"official","path":"mmdet/models/prop_heads/seq_prop_head.py","file_url":"https://github.com/dvlab-research/proposereduce/blob/HEAD/mmdet/models/prop_heads/seq_prop_head.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7e8ca60fbece7dea"}},{"code_sha256_prefix":"c81f13f1ca949a3c","entry":"Registry","repo":"dvlab-research/proposereduce","repo_kind":"official","path":"mmdet/models/prop_heads/seq_prop_head.py","file_url":"https://github.com/dvlab-research/proposereduce/blob/HEAD/mmdet/models/prop_heads/seq_prop_head.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c81f13f1ca949a3c"}},{"code_sha256_prefix":"e6747fc7f19f1968","entry":"ConvModule","repo":"dvlab-research/proposereduce","repo_kind":"official","path":"mmdet/models/prop_heads/seq_prop_head.py","file_url":"https://github.com/dvlab-research/proposereduce/blob/HEAD/mmdet/models/prop_heads/seq_prop_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e6747fc7f19f1968"}},{"code_sha256_prefix":"1ec668377e125876","entry":"SeqPropHead","repo":"dvlab-research/proposereduce","repo_kind":"official","path":"mmdet/models/prop_heads/seq_prop_head.py","file_url":"https://github.com/dvlab-research/proposereduce/blob/HEAD/mmdet/models/prop_heads/seq_prop_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1ec668377e125876"}},{"code_sha256_prefix":"ea08e84fefac65ab","entry":"kaiming_init","repo":"dvlab-research/proposereduce","repo_kind":"official","path":"mmdet/models/prop_heads/seq_prop_head.py","file_url":"https://github.com/dvlab-research/proposereduce/blob/HEAD/mmdet/models/prop_heads/seq_prop_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea08e84fefac65ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}