{"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/uncertainty-estimation-via-response-scaling","title":"Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation","arxiv_id":"2112.07431","date":"2021-12-14","proceeding":null,"authors":["Yi Li","Yiqun Duan","Zhanghui Kuang","Yimin Chen","Wayne Zhang","Xiaomeng Li"],"abstract":"Weakly-Supervised Semantic Segmentation (WSSS) segments objects without a heavy burden of dense annotation. While as a price, generated pseudo-masks exist obvious noisy pixels, which result in sub-optimal segmentation models trained over these pseudo-masks. But rare studies notice or work on this problem, even these noisy pixels are inevitable after their improvements on pseudo-mask. So we try to improve WSSS in the aspect of noise mitigation. And we observe that many noisy pixels are of high confidence, especially when the response range is too wide or narrow, presenting an uncertain status. Thus, in this paper, we simulate noisy variations of response by scaling the prediction map multiple times for uncertainty estimation. The uncertainty is then used to weight the segmentation loss to mitigate noisy supervision signals. We call this method URN, abbreviated from Uncertainty estimation via Response scaling for Noise mitigation. Experiments validate the benefits of URN, and our method achieves state-of-the-art results at 71.2% and 41.5% on PASCAL VOC 2012 and MS COCO 2014 respectively, without extra models like saliency detection. Code is available at https://github.com/XMed-Lab/URN.","url_abs":"https://arxiv.org/abs/2112.07431v1","url_pdf":"https://arxiv.org/pdf/2112.07431v1.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":"uncertainty-estimation-via-response-scaling","repo_url":"https://github.com/xmed-lab/urn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation-1","task_name":"Weakly supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","task":"Weakly-Supervised Semantic Segmentation","dataset":"COCO 2014 val","model":"URN(Res2Net-101, no saliency, no RW)","rank_in_archive_order":24,"of":39,"metrics":{"mIoU":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","task":"Weakly-Supervised Semantic Segmentation","dataset":"COCO 2014 val","model":"URN(ScaleNet-101, no saliency, no RW)","rank_in_archive_order":25,"of":39,"metrics":{"mIoU":"40.8"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","task":"Weakly-Supervised Semantic Segmentation","dataset":"COCO 2014 val","model":"URN(ResNet-101, no saliency, no RW)","rank_in_archive_order":26,"of":39,"metrics":{"mIoU":"40.7"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","task":"Weakly-Supervised Semantic Segmentation","dataset":"COCO 2014 val","model":"URN(ResNet-38, no saliency, no RW)","rank_in_archive_order":27,"of":39,"metrics":{"mIoU":"40.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"URN(Res2Net-101, no saliency, no RW)","rank_in_archive_order":27,"of":60,"metrics":{"Mean IoU":"71.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"URN(ScaleNet-101, no saliency, no RW)","rank_in_archive_order":33,"of":60,"metrics":{"Mean IoU":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"URN(ResNet-38, no saliency, no RW)","rank_in_archive_order":38,"of":60,"metrics":{"Mean IoU":"70.6"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"URN(ResNet-101, no saliency, no RW)","rank_in_archive_order":45,"of":60,"metrics":{"Mean IoU":"69.7"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"URN(Res2Net-101, no saliency, no RW)","rank_in_archive_order":26,"of":73,"metrics":{"Mean IoU":"71.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"URN(ScaleNet-101, no saliency, no RW)","rank_in_archive_order":43,"of":73,"metrics":{"Mean IoU":"70.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"URN(ResNet-101, no saliency, no RW)","rank_in_archive_order":46,"of":73,"metrics":{"Mean IoU":"69.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"URN(ResNet-38, no saliency, no RW)","rank_in_archive_order":50,"of":73,"metrics":{"Mean IoU":"69.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.07431","atlas_url":"https://app.syntology.ai/?focus=2112.07431","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":"2112.07431"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.07431\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.07431"},"call":"get_concepts_for_paper(arxiv_id=\"2112.07431\")"}],"by_repo":[{"repo":"xmed-lab/urn","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":"005314d64f087b5aeae61986917be4fb999fdd43d4c1b31e47ddc16dfb10463d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}