{"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/transfgu-a-top-down-approach-to-fine-grained","title":"TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation","arxiv_id":"2112.01515","date":"2021-12-02","proceeding":null,"authors":["Zhaoyuan Yin","Pichao Wang","Fan Wang","Xianzhe Xu","Hanling Zhang","Hao Li","Rong Jin"],"abstract":"Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up approaches that try to group pixels into regions based on their visual cues or certain predefined rules. As a result, it is difficult for these bottom-up approaches to generate fine-grained semantic segmentation when coming to complicated scenes with multiple objects and some objects sharing similar visual appearance. In contrast, we propose the first top-down unsupervised semantic segmentation framework for fine-grained segmentation in extremely complicated scenarios. Specifically, we first obtain rich high-level structured semantic concept information from large-scale vision data in a self-supervised learning manner, and use such information as a prior to discover potential semantic categories presented in target datasets. Secondly, the discovered high-level semantic categories are mapped to low-level pixel features by calculating the class activate map (CAM) with respect to certain discovered semantic representation. Lastly, the obtained CAMs serve as pseudo labels to train the segmentation module and produce the final semantic segmentation. Experimental results on multiple semantic segmentation benchmarks show that our top-down unsupervised segmentation is robust to both object-centric and scene-centric datasets under different semantic granularity levels, and outperforms all the current state-of-the-art bottom-up methods. Our code is available at \\url{https://github.com/damo-cv/TransFGU}.","url_abs":"https://arxiv.org/abs/2112.01515v2","url_pdf":"https://arxiv.org/pdf/2112.01515v2.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":"transfgu-a-top-down-approach-to-fine-grained","repo_url":"https://github.com/damo-cv/transfgu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-6","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-171","model":"TransFGU (ViT-S/8)","rank_in_archive_order":2,"of":4,"metrics":{"Pixel Accuracy":"34.32","mIoU":"11.93"},"uses_additional_data":true},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-8","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-81","model":"TransFGU (ViT-S/8)","rank_in_archive_order":3,"of":4,"metrics":{"Pixel Accuracy":"64.3","mIoU":"12.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.01515","atlas_url":"https://app.syntology.ai/?focus=2112.01515","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":"2112.01515"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.01515\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.01515"},"call":"get_concepts_for_paper(arxiv_id=\"2112.01515\")"}],"by_repo":[{"repo":"damo-cv/transfgu","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"436042179c5ce96e5ca83b7ce683ec521bc8a31a5552b8da01c98e336a35d852","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}