{"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/locate-self-supervised-object-discovery-via","title":"LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training","arxiv_id":"2308.11239","date":"2023-08-22","proceeding":null,"authors":["Silky Singh","Shripad Deshmukh","Mausoom Sarkar","Balaji Krishnamurthy"],"abstract":"Learning object segmentation in image and video datasets without human supervision is a challenging problem. Humans easily identify moving salient objects in videos using the gestalt principle of common fate, which suggests that what moves together belongs together. Building upon this idea, we propose a self-supervised object discovery approach that leverages motion and appearance information to produce high-quality object segmentation masks. Specifically, we redesign the traditional graph cut on images to include motion information in a linear combination with appearance information to produce edge weights. Remarkably, this step produces object segmentation masks comparable to the current state-of-the-art on multiple benchmarks. To further improve performance, we bootstrap a segmentation network trained on these preliminary masks as pseudo-ground truths to learn from its own outputs via self-training. We demonstrate the effectiveness of our approach, named LOCATE, on multiple standard video object segmentation, image saliency detection, and object segmentation benchmarks, achieving results on par with and, in many cases surpassing state-of-the-art methods. We also demonstrate the transferability of our approach to novel domains through a qualitative study on in-the-wild images. Additionally, we present extensive ablation analysis to support our design choices and highlight the contribution of each component of our proposed method.","url_abs":"https://arxiv.org/abs/2308.11239v3","url_pdf":"https://arxiv.org/pdf/2308.11239v3.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":"locate-self-supervised-object-discovery-via","repo_url":"https://github.com/silky1708/locate","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic 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/video-object-segmentation-on-davis-2016","task":"Video Object Segmentation","dataset":"DAVIS 2016","model":"LOCATE","rank_in_archive_order":23,"of":24,"metrics":{"Contour Accuracy":"88.7","mIoU":"80.9"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-fbms-59","task":"Video Object Segmentation","dataset":"FBMS-59","model":"LOCATE","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"68.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-segtrack-v2-1","task":"Video Object Segmentation","dataset":"SegTrack-v2","model":"LOCATE","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"79.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.11239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11239"}},"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/silky1708/locate","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"463ac08b66bf3530","entry":"cached_grid","repo":"silky1708/locate","repo_kind":"official","path":"dist.py","file_url":"https://github.com/silky1708/locate/blob/HEAD/dist.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":"463ac08b66bf3530"}},{"code_sha256_prefix":"dd58544ae91e6043","entry":"clamp_probs","repo":"silky1708/locate","repo_kind":"official","path":"dist.py","file_url":"https://github.com/silky1708/locate/blob/HEAD/dist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dd58544ae91e6043"}},{"code_sha256_prefix":"819b7f223154f50c","entry":"grid","repo":"silky1708/locate","repo_kind":"official","path":"dist.py","file_url":"https://github.com/silky1708/locate/blob/HEAD/dist.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":"819b7f223154f50c"}},{"code_sha256_prefix":"f47176fee17b8548","entry":"iou","repo":"silky1708/locate","repo_kind":"official","path":"eval_utils.py","file_url":"https://github.com/silky1708/locate/blob/HEAD/eval_utils.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":"f47176fee17b8548"}},{"code_sha256_prefix":"5d5e51ae09a58b2a","entry":"scan_train_flow","repo":"silky1708/locate","repo_kind":"official","path":"config.py","file_url":"https://github.com/silky1708/locate/blob/HEAD/config.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":"5d5e51ae09a58b2a"}},{"code_sha256_prefix":"864224ccca348ed5","entry":"autosized_default_font","repo":"silky1708/locate","repo_kind":"official","path":"eval_utils.py","file_url":"https://github.com/silky1708/locate/blob/HEAD/eval_utils.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":"864224ccca348ed5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}