{"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/saliency-guided-self-attention-network-for","title":"Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation","arxiv_id":"1910.05475","date":"2019-10-12","proceeding":null,"authors":["Qi Yao","Xiaojin Gong"],"abstract":"Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest. However, its performance is still inferior to the fully supervised counterparts. To mitigate the performance gap, we propose a saliency guided self-attention network (SGAN) to address the WSSS problem. The introduced self-attention mechanism is able to capture rich and extensive contextual information but may mis-spread attentions to unexpected regions. In order to enable this mechanism to work effectively under weak supervision, we integrate class-agnostic saliency priors into the self-attention mechanism and utilize class-specific attention cues as an additional supervision for SGAN. Our SGAN is able to produce dense and accurate localization cues so that the segmentation performance is boosted. Moreover, by simply replacing the additional supervisions with partially labeled ground-truth, SGAN works effectively for semi-supervised semantic segmentation as well. Experiments on the PASCAL VOC 2012 and COCO datasets show that our approach outperforms all other state-of-the-art methods in both weakly and semi-supervised settings.","url_abs":"https://arxiv.org/abs/1910.05475v2","url_pdf":"https://arxiv.org/pdf/1910.05475v2.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":"saliency-guided-self-attention-network-for","repo_url":"https://github.com/yaoqi-zd/SGAN","is_official":1,"mentioned_in_paper":1,"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":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised 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":"SGAN","rank_in_archive_order":36,"of":39,"metrics":{"mIoU":"33.6"},"uses_additional_data":true},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"SGAN","rank_in_archive_order":58,"of":60,"metrics":{"Mean IoU":"67.2"},"uses_additional_data":true},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"SGAN","rank_in_archive_order":63,"of":73,"metrics":{"Mean IoU":"67.1"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.05475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05475"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yaoqi-zd/SGAN","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":1,"samples":[{"code_sha256_prefix":"15ce08656df9a4d0","entry":"filter_pretrained_weights","repo":"yaoqi-zd/SGAN","repo_kind":"official","path":"tools/stage2/train_sgan.py","file_url":"https://github.com/yaoqi-zd/SGAN/blob/HEAD/tools/stage2/train_sgan.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15ce08656df9a4d0"}},{"code_sha256_prefix":"b3b7c1c716f4ca66","entry":"lr_poly","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b3b7c1c716f4ca66"}},{"code_sha256_prefix":"a6a648eed2ad24be","entry":"preprocess","repo":"yaoqi-zd/SGAN","repo_kind":"official","path":"tools/stage2/infer_cam.py","file_url":"https://github.com/yaoqi-zd/SGAN/blob/HEAD/tools/stage2/infer_cam.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a6a648eed2ad24be"}},{"code_sha256_prefix":"98f7ff8f78a67d58","entry":"generate_seed_with_ignore","repo":"yaoqi-zd/SGAN","repo_kind":"official","path":"tools/stage2/infer_cam.py","file_url":"https://github.com/yaoqi-zd/SGAN/blob/HEAD/tools/stage2/infer_cam.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":"98f7ff8f78a67d58"}},{"code_sha256_prefix":"66dd49fd20705ba6","entry":"generate_seed_wo_ignore","repo":"yaoqi-zd/SGAN","repo_kind":"official","path":"tools/stage2/infer_cam.py","file_url":"https://github.com/yaoqi-zd/SGAN/blob/HEAD/tools/stage2/infer_cam.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":"66dd49fd20705ba6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}