{"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/tell-me-where-to-look-guided-attention","title":"Tell Me Where to Look: Guided Attention Inference Network","arxiv_id":"1802.10171","date":"2018-02-27","proceeding":"CVPR 2018 6","authors":["Kunpeng Li","Ziyan Wu","Kuan-Chuan Peng","Jan Ernst","Yun Fu"],"abstract":"Weakly supervised learning with only coarse labels can obtain visual\nexplanations of deep neural network such as attention maps by back-propagating\ngradients. These attention maps are then available as priors for tasks such as\nobject localization and semantic segmentation. In one common framework we\naddress three shortcomings of previous approaches in modeling such attention\nmaps: We (1) first time make attention maps an explicit and natural component\nof the end-to-end training, (2) provide self-guidance directly on these maps by\nexploring supervision form the network itself to improve them, and (3)\nseamlessly bridge the gap between using weak and extra supervision if\navailable. Despite its simplicity, experiments on the semantic segmentation\ntask demonstrate the effectiveness of our methods. We clearly surpass the\nstate-of-the-art on Pascal VOC 2012 val. and test set. Besides, the proposed\nframework provides a way not only explaining the focus of the learner but also\nfeeding back with direct guidance towards specific tasks. Under mild\nassumptions our method can also be understood as a plug-in to existing weakly\nsupervised learners to improve their generalization performance.","url_abs":"http://arxiv.org/abs/1802.10171v1","url_pdf":"http://arxiv.org/pdf/1802.10171v1.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":"tell-me-where-to-look-guided-attention","repo_url":"https://github.com/AustinDoolittle/Pytorch-Gain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tell-me-where-to-look-guided-attention","repo_url":"https://github.com/ilyak93/GAIN-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[{"slug":"voc-2012","name":"VOC 2012","full_name":"The PASCAL Visual Object Classes Challenge 2012"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.10171","atlas_url":"https://app.syntology.ai/?focus=1802.10171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10171"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ilyak93/GAIN-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AustinDoolittle/Pytorch-Gain","reach":null}],"summary":{"ran_violates":1,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":2}},"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":3,"samples":[{"code_sha256_prefix":"a6bdc65eba7b90fd","entry":"is_bn","repo":"ilyak93/GAIN-pytorch","repo_kind":"listed","path":"models/batch_GAIN_VOC_mutilabel_singlebatch.py","file_url":"https://github.com/ilyak93/GAIN-pytorch/blob/HEAD/models/batch_GAIN_VOC_mutilabel_singlebatch.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6bdc65eba7b90fd"}},{"code_sha256_prefix":"2d63bbceb62fc65a","entry":"scalar","repo":"AustinDoolittle/Pytorch-Gain","repo_kind":"listed","path":"gain.py","file_url":"https://github.com/AustinDoolittle/Pytorch-Gain/blob/HEAD/gain.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d63bbceb62fc65a"}},{"code_sha256_prefix":"dd15a729c505a7ad","entry":"take_bn_layers","repo":"ilyak93/GAIN-pytorch","repo_kind":"listed","path":"models/batch_GAIN_VOC_mutilabel_singlebatch.py","file_url":"https://github.com/ilyak93/GAIN-pytorch/blob/HEAD/models/batch_GAIN_VOC_mutilabel_singlebatch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dd15a729c505a7ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}