{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/pseudo-mask-matters-inweakly-supervised","title":"Pseudo-mask Matters in Weakly-supervised Semantic Segmentation","arxiv_id":"2108.12995","date":"2021-08-30","proceeding":"ICCV 2021 10","authors":["Yi Li","Zhanghui Kuang","Liyang Liu","Yimin Chen","Wayne Zhang"],"abstract":"Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we find some matters related to the pseudo-masks, including high quality pseudo-masks generation from class activation maps (CAMs), and training with noisy pseudo-mask supervision. For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Generation to project the expanded CAMs to pseudo-mask based on a new metric indicating the importance of each class on each location, instead of the scores trained from binary classifiers. (iii) Pretended Under-Fitting strategy to suppress the influence of noise in pseudo-mask; (iv) Cyclic Pseudo-mask to boost the pseudo-masks during training of fully supervised semantic segmentation (FSSS). Experiments based on our methods achieve new state-of-art results on two changeling weakly supervised semantic segmentation datasets, pushing the mIoU to 70.0% and 40.2% on PAS-CAL VOC 2012 and MS COCO 2014 respectively. Codes including segmentation framework are released at https://github.com/Eli-YiLi/PMM","url_abs":"https://arxiv.org/abs/2108.12995v2","url_pdf":"https://arxiv.org/pdf/2108.12995v2.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":"pseudo-mask-matters-inweakly-supervised","repo_url":"https://github.com/eli-yili/pmm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pseudo-mask-matters-inweakly-supervised","repo_url":"https://github.com/eli-yili/wsss_mmseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":"PMM(ScaleNet101, no saliency, no RW)","rank_in_archive_order":28,"of":39,"metrics":{"mIoU":"40.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","task":"Weakly-Supervised Semantic Segmentation","dataset":"COCO 2014 val","model":"PMM(ResNet38, no saliency, no RW)","rank_in_archive_order":30,"of":39,"metrics":{"mIoU":"36.7"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"PMM(Res2Net101, no saliency, no RW)","rank_in_archive_order":41,"of":60,"metrics":{"Mean IoU":"70.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"PMM(ResNet38, no saliency, no RW)","rank_in_archive_order":50,"of":60,"metrics":{"Mean IoU":"69.0"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"PMM(Res2Net101, no saliency, no RW)","rank_in_archive_order":45,"of":73,"metrics":{"Mean IoU":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"PMM(ResNet38)","rank_in_archive_order":54,"of":73,"metrics":{"Mean IoU":"68.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"PMM(ResNet38, no saliency, no RW)","rank_in_archive_order":55,"of":73,"metrics":{"Mean IoU":"68.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.12995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.12995"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Eli-YiLi/PMM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d274d062070f377d","entry":"do_python_eval","repo":"Eli-YiLi/PMM","repo_kind":"official","path":"pipeline/evaluation.py","file_url":"https://github.com/Eli-YiLi/PMM/blob/HEAD/pipeline/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d274d062070f377d"}},{"code_sha256_prefix":"9da0a975b889ff9b","entry":"get_indices_in_radius","repo":"Eli-YiLi/PMM","repo_kind":"official","path":"pipeline/infer_aff.py","file_url":"https://github.com/Eli-YiLi/PMM/blob/HEAD/pipeline/infer_aff.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9da0a975b889ff9b"}},{"code_sha256_prefix":"85e75787d89f2a20","entry":"scalenet101","repo":"Eli-YiLi/PMM","repo_kind":"official","path":"network/scalenet.py","file_url":"https://github.com/Eli-YiLi/PMM/blob/HEAD/network/scalenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85e75787d89f2a20"}},{"code_sha256_prefix":"9afe04f8ff5d0e2d","entry":"scalenet152","repo":"Eli-YiLi/PMM","repo_kind":"official","path":"network/scalenet.py","file_url":"https://github.com/Eli-YiLi/PMM/blob/HEAD/network/scalenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9afe04f8ff5d0e2d"}},{"code_sha256_prefix":"4a38197aa01d5c30","entry":"scalenet50","repo":"Eli-YiLi/PMM","repo_kind":"official","path":"network/scalenet.py","file_url":"https://github.com/Eli-YiLi/PMM/blob/HEAD/network/scalenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a38197aa01d5c30"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}