{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/tokencut-segmenting-objects-in-images-and","title":"TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut","arxiv_id":"2209.00383","date":"2022-09-01","proceeding":null,"authors":["Yangtao Wang","Xi Shen","Yuan Yuan","Yuming Du","Maomao Li","Shell Xu Hu","James L Crowley","Dominique Vaufreydaz"],"abstract":"In this paper, we describe a graph-based algorithm that uses the features obtained by a self-supervised transformer to detect and segment salient objects in images and videos. With this approach, the image patches that compose an image or video are organised into a fully connected graph, where the edge between each pair of patches is labeled with a similarity score between patches using features learned by the transformer. Detection and segmentation of salient objects is then formulated as a graph-cut problem and solved using the classical Normalized Cut algorithm. Despite the simplicity of this approach, it achieves state-of-the-art results on several common image and video detection and segmentation tasks. For unsupervised object discovery, this approach outperforms the competing approaches by a margin of 6.1%, 5.7%, and 2.6%, respectively, when tested with the VOC07, VOC12, and COCO20K datasets. For the unsupervised saliency detection task in images, this method improves the score for Intersection over Union (IoU) by 4.4%, 5.6% and 5.2%. When tested with the ECSSD, DUTS, and DUT-OMRON datasets, respectively, compared to current state-of-the-art techniques. This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.","url_abs":"https://arxiv.org/abs/2209.00383v3","url_pdf":"https://arxiv.org/pdf/2209.00383v3.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":[],"tasks":[{"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":"unsupervised-instance-segmentation","task_name":"Unsupervised Instance Segmentation"},{"task_slug":"unsupervised-object-segmentation","task_name":"Unsupervised Object Segmentation"},{"task_slug":"unsupervised-saliency-detection","task_name":"Unsupervised Saliency Detection"},{"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-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-instance-segmentation-on-coco","task":"Unsupervised Instance Segmentation","dataset":"COCO val2017","model":"TokenCut","rank_in_archive_order":5,"of":5,"metrics":{"AP":"2.4","AP50":"4.8","AP75":"1.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-object-segmentation-on-fbms-59","task":"Unsupervised Object Segmentation","dataset":"FBMS-59","model":"TokenCut","rank_in_archive_order":6,"of":7,"metrics":{"mIoU":"60.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-object-segmentation-on-segtrack","task":"Unsupervised Object Segmentation","dataset":"SegTrack-v2","model":"TokenCut","rank_in_archive_order":7,"of":8,"metrics":{"mIoU":"59.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.00383","atlas_url":"https://app.syntology.ai/?focus=2209.00383","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2209.00383"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2209.00383\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2209.00383"},"call":"get_concepts_for_paper(arxiv_id=\"2209.00383\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"27801e5b0b2ce174170cd09cb5ff48787da91887f0c45ea209fa1d9549625522","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}