{"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/infoseg-unsupervised-semantic-image","title":"InfoSeg: Unsupervised Semantic Image Segmentation with Mutual Information Maximization","arxiv_id":"2110.03477","date":"2021-10-07","proceeding":null,"authors":["Robert Harb","Patrick Knöbelreiter"],"abstract":"We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features. The core idea of our work is to leverage recent progress in self-supervised image representation learning. Representation learning methods compute a single high-level feature capturing an entire image. In contrast, we compute multiple high-level features, each capturing image segments of one particular semantic class. To this end, we propose a novel two-step learning procedure comprising a segmentation and a mutual information maximization step. In the first step, we segment images based on local and global features. In the second step, we maximize the mutual information between local features and high-level features of their respective class. For training, we provide solely unlabeled images and start from random network initialization. For quantitative and qualitative evaluation, we use established benchmarks, and COCO-Persons, whereby we introduce the latter in this paper as a challenging novel benchmark. InfoSeg significantly outperforms the current state-of-the-art, e.g., we achieve a relative increase of 26% in the Pixel Accuracy metric on the COCO-Stuff dataset.","url_abs":"https://arxiv.org/abs/2110.03477v1","url_pdf":"https://arxiv.org/pdf/2110.03477v1.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":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"representation-learning","task_name":"Representation 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-3","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Persons","model":"InfoSeg","rank_in_archive_order":1,"of":1,"metrics":{"Pixel Accuracy":"69.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-15","model":"InfoSeg","rank_in_archive_order":1,"of":3,"metrics":{"Pixel Accuracy":"38.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-1","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-3","model":"InfoSeg","rank_in_archive_order":3,"of":6,"metrics":{"Pixel Accuracy":"73.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-potsdam-1","task":"Unsupervised Semantic Segmentation","dataset":"Potsdam-3","model":"InfoSeg","rank_in_archive_order":8,"of":8,"metrics":{"Pixel Accuracy":"71.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.03477","atlas_url":"https://app.syntology.ai/?focus=2110.03477","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":"2110.03477"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.03477\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.03477"},"call":"get_concepts_for_paper(arxiv_id=\"2110.03477\")"}],"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":"efb9ff8e1215e530fb481e2cd56b9414d81f5b79430d28fe6c0b329e326aca8d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}