{"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/dense-unsupervised-learning-for-video","title":"Dense Unsupervised Learning for Video Segmentation","arxiv_id":"2111.06265","date":"2021-11-11","proceeding":"NeurIPS 2021 12","authors":["Nikita Araslanov","Simone Schaub-Meyer","Stefan Roth"],"abstract":"We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid sampling to extract a set of anchors and train our model to disambiguate between them on both inter- and intra-video levels. However, a naive scheme to train such a model results in a degenerate solution. We propose to prevent this with a simple regularisation scheme, accommodating the equivariance property of the segmentation task to similarity transformations. Our training objective admits efficient implementation and exhibits fast training convergence. On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.","url_abs":"https://arxiv.org/abs/2111.06265v1","url_pdf":"https://arxiv.org/pdf/2111.06265v1.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":"dense-unsupervised-learning-for-video","repo_url":"https://github.com/visinf/dense-ulearn-vos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"unsupervised-video-object-segmentation","task_name":"Unsupervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"vos","method_name":"VOS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"Araslanov et al.","rank_in_archive_order":62,"of":81,"metrics":{"F-measure (Mean)":"71.7","F-measure (Recall)":"84.8","J&F":"69.4","Jaccard (Mean)":"67.1","Jaccard (Recall)":"80.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.06265","atlas_url":"https://app.syntology.ai/?focus=2111.06265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06265"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/visinf/dense-ulearn-vos","reach":null}],"summary":{"ran":3,"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"095e671ad6717b22","entry":"BaseNet","repo":"visinf/dense-ulearn-vos","repo_kind":"official","path":"models/net.py","file_url":"https://github.com/visinf/dense-ulearn-vos/blob/HEAD/models/net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"095e671ad6717b22"}},{"code_sha256_prefix":"d7436bd8b38a68f7","entry":"MLP","repo":"visinf/dense-ulearn-vos","repo_kind":"official","path":"models/net.py","file_url":"https://github.com/visinf/dense-ulearn-vos/blob/HEAD/models/net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d7436bd8b38a68f7"}},{"code_sha256_prefix":"0329d5667de34d21","entry":"Net","repo":"visinf/dense-ulearn-vos","repo_kind":"official","path":"models/net.py","file_url":"https://github.com/visinf/dense-ulearn-vos/blob/HEAD/models/net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0329d5667de34d21"}},{"code_sha256_prefix":"2445218fa1c1d604","entry":"convert_dict","repo":"visinf/dense-ulearn-vos","repo_kind":"official","path":"infer_vos.py","file_url":"https://github.com/visinf/dense-ulearn-vos/blob/HEAD/infer_vos.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2445218fa1c1d604"}},{"code_sha256_prefix":"b46a0e1d2d74a9c9","entry":"mask2rgb","repo":"visinf/dense-ulearn-vos","repo_kind":"official","path":"infer_vos.py","file_url":"https://github.com/visinf/dense-ulearn-vos/blob/HEAD/infer_vos.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b46a0e1d2d74a9c9"}},{"code_sha256_prefix":"bd7f22f1700017a4","entry":"mask_overlay","repo":"visinf/dense-ulearn-vos","repo_kind":"official","path":"infer_vos.py","file_url":"https://github.com/visinf/dense-ulearn-vos/blob/HEAD/infer_vos.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd7f22f1700017a4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}