{"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/reliable-propagation-correction-modulation","title":"Reliable Propagation-Correction Modulation for Video Object Segmentation","arxiv_id":"2112.02853","date":"2021-12-06","proceeding":null,"authors":["Xiaohao Xu","Jinglu Wang","Xiao Li","Yan Lu"],"abstract":"Error propagation is a general but crucial problem in online semi-supervised video object segmentation. We aim to suppress error propagation through a correction mechanism with high reliability. The key insight is to disentangle the correction from the conventional mask propagation process with reliable cues. We introduce two modulators, propagation and correction modulators, to separately perform channel-wise re-calibration on the target frame embeddings according to local temporal correlations and reliable references respectively. Specifically, we assemble the modulators with a cascaded propagation-correction scheme. This avoids overriding the effects of the reliable correction modulator by the propagation modulator. Although the reference frame with the ground truth label provides reliable cues, it could be very different from the target frame and introduce uncertain or incomplete correlations. We augment the reference cues by supplementing reliable feature patches to a maintained pool, thus offering more comprehensive and expressive object representations to the modulators. In addition, a reliability filter is designed to retrieve reliable patches and pass them in subsequent frames. Our model achieves state-of-the-art performance on YouTube-VOS18/19 and DAVIS17-Val/Test benchmarks. Extensive experiments demonstrate that the correction mechanism provides considerable performance gain by fully utilizing reliable guidance. Code is available at: https://github.com/JerryX1110/RPCMVOS.","url_abs":"https://arxiv.org/abs/2112.02853v1","url_pdf":"https://arxiv.org/pdf/2112.02853v1.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":"reliable-propagation-correction-modulation","repo_url":"https://github.com/jerryx1110/rpcmvos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"RPCMVOS","rank_in_archive_order":27,"of":78,"metrics":{"F-measure (Mean)":"94","J&F":"90.6","Jaccard (Mean)":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"RPCMVOS-Full-Res","rank_in_archive_order":16,"of":59,"metrics":{"F-measure (Mean)":"84.3","J&F":"81","Jaccard (Mean)":"77.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"RPCMVOS","rank_in_archive_order":23,"of":59,"metrics":{"F-measure (Mean)":"82.6","J&F":"79.2","Jaccard (Mean)":"75.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"RPCMVOS","rank_in_archive_order":32,"of":81,"metrics":{"F-measure (Mean)":"86","J&F":"83.7","Jaccard (Mean)":"81.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"RPCMVOS-MS","rank_in_archive_order":21,"of":53,"metrics":{"F-Measure (Seen)":"87.9","F-Measure (Unseen)":"86.9","Jaccard (Seen)":"83.3","Jaccard (Unseen)":"78.9","Overall":"84.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"RPCMVOS","rank_in_archive_order":25,"of":53,"metrics":{"F-Measure (Seen)":"87.7","F-Measure (Unseen)":"86.7","Jaccard (Seen)":"83.1","Overall":"84","Speed (FPS)":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-18","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2019","model":"RPCMVOS","rank_in_archive_order":17,"of":22,"metrics":{"F-Measure (Seen)":"86.9","F-Measure (Unseen)":"87.1","Jaccard (Seen)":"82.6","Jaccard (Unseen)":"79.1","Overall":"83.9"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017-test-1","task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"RPCMVOS","rank_in_archive_order":3,"of":10,"metrics":{"F-measure":"82.6","Jaccard":"75.8","Mean Jaccard & F-Measure":"79.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos-2019-2","task":"Video Object Segmentation","dataset":"YouTube-VOS 2019","model":"RPCMVOS","rank_in_archive_order":5,"of":10,"metrics":{"F-Measure (Seen)":"86.9","F-Measure (Unseen)":"87.1","Jaccard (Seen)":"82.6","Jaccard (Unseen)":"79.1","Mean Jaccard & F-Measure":"83.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.02853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02853"}},"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/jerryx1110/rpcmvos","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"7221953c05ccc6b9","entry":"all_to_onehot","repo":"jerryx1110/rpcmvos","repo_kind":"official","path":"dataloaders/datasets.py","file_url":"https://github.com/jerryx1110/rpcmvos/blob/HEAD/dataloaders/datasets.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7221953c05ccc6b9"}},{"code_sha256_prefix":"4d0070cfa5e25a53","entry":"build_aspp","repo":"jerryx1110/rpcmvos","repo_kind":"official","path":"networks/deeplab/aspp.py","file_url":"https://github.com/jerryx1110/rpcmvos/blob/HEAD/networks/deeplab/aspp.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":"4d0070cfa5e25a53"}},{"code_sha256_prefix":"def8ad790566e5e1","entry":"build_decoder","repo":"jerryx1110/rpcmvos","repo_kind":"official","path":"networks/deeplab/decoder.py","file_url":"https://github.com/jerryx1110/rpcmvos/blob/HEAD/networks/deeplab/decoder.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":"def8ad790566e5e1"}},{"code_sha256_prefix":"ca820f23f256da70","entry":"calculate_attention_head","repo":"jerryx1110/rpcmvos","repo_kind":"official","path":"networks/layers/attention.py","file_url":"https://github.com/jerryx1110/rpcmvos/blob/HEAD/networks/layers/attention.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":"ca820f23f256da70"}},{"code_sha256_prefix":"79e4aea1f2a0ea7c","entry":"calculate_attention_head_for_eval","repo":"jerryx1110/rpcmvos","repo_kind":"official","path":"networks/layers/attention.py","file_url":"https://github.com/jerryx1110/rpcmvos/blob/HEAD/networks/layers/attention.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":"79e4aea1f2a0ea7c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}