{"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/boosting-unsupervised-semantic-segmentation","title":"Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals","arxiv_id":"2404.16818","date":"2024-04-25","proceeding":null,"authors":["Oliver Hahn","Nikita Araslanov","Simone Schaub-Meyer","Stefan Roth"],"abstract":"Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global semantic categories within an image corpus without any form of annotation. Building upon recent advances in self-supervised representation learning, we focus on how to leverage these large pre-trained models for the downstream task of unsupervised segmentation. We present PriMaPs - Principal Mask Proposals - decomposing images into semantically meaningful masks based on their feature representation. This allows us to realize unsupervised semantic segmentation by fitting class prototypes to PriMaPs with a stochastic expectation-maximization algorithm, PriMaPs-EM. Despite its conceptual simplicity, PriMaPs-EM leads to competitive results across various pre-trained backbone models, including DINO and DINOv2, and across different datasets, such as Cityscapes, COCO-Stuff, and Potsdam-3. Importantly, PriMaPs-EM is able to boost results when applied orthogonally to current state-of-the-art unsupervised semantic segmentation pipelines. Code is available at https://github.com/visinf/primaps.","url_abs":"https://arxiv.org/abs/2404.16818v2","url_pdf":"https://arxiv.org/pdf/2404.16818v2.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":"boosting-unsupervised-semantic-segmentation","repo_url":"https://github.com/visinf/primaps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dino","method_name":"DINO"},{"method_slug":"pca","method_name":"PCA"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"PriMaPs+STEGO (DINO ViT-B/8)","rank_in_archive_order":6,"of":29,"metrics":{"Clustering [Accuracy]":"57.9","Clustering [mIoU]":"29.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"PriMaPs+HP (DINO ViT-S/8)","rank_in_archive_order":15,"of":29,"metrics":{"Clustering [Accuracy]":"57.8","Clustering [mIoU]":"25.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on","task":"Unsupervised Semantic Segmentation","dataset":"Cityscapes test","model":"PriMaPs-EM + STEGO (DINO ViT-B/8)","rank_in_archive_order":5,"of":14,"metrics":{"Accuracy":"78.6","mIoU":"21.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on","task":"Unsupervised Semantic Segmentation","dataset":"Cityscapes test","model":"PriMaPs-EM (DINO ViT-S/8)","rank_in_archive_order":8,"of":14,"metrics":{"Accuracy":"81.2","mIoU":"19.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-potsdam-1","task":"Unsupervised Semantic Segmentation","dataset":"Potsdam-3","model":"PriMaPs-EM+HP (DINO ViT-B/8)","rank_in_archive_order":1,"of":8,"metrics":{"Accuracy":"83.3","mIoU":"71.0"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-potsdam-1","task":"Unsupervised Semantic Segmentation","dataset":"Potsdam-3","model":"PriMaPs-EM (DINO ViT-B/8)","rank_in_archive_order":5,"of":8,"metrics":{"Accuracy":"80.5","mIoU":"67.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.16818","atlas_url":"https://app.syntology.ai/?focus=2404.16818","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":"2404.16818"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2404.16818\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2404.16818"},"call":"get_concepts_for_paper(arxiv_id=\"2404.16818\")"}],"by_repo":[{"repo":"visinf/primaps","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":"32e7d4ebdfb089eabf882aa14a7d73b6d5d6255cd324f56c22680c917f3f51a7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}