{"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/guided-integrated-gradients-an-adaptive-path","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","arxiv_id":"2106.09788","date":"2021-06-17","proceeding":"CVPR 2021 1","authors":["Andrei Kapishnikov","Subhashini Venugopalan","Besim Avci","Ben Wedin","Michael Terry","Tolga Bolukbasi"],"abstract":"Integrated Gradients (IG) is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, the method often produces spurious/noisy pixel attributions in regions that are not related to the predicted class when applied to visual models. While this has been previously noted, most existing solutions are aimed at addressing the symptoms by explicitly reducing the noise in the resulting attributions. In this work, we show that one of the causes of the problem is the accumulation of noise along the IG path. To minimize the effect of this source of noise, we propose adapting the attribution path itself -- conditioning the path not just on the image but also on the model being explained. We introduce Adaptive Path Methods (APMs) as a generalization of path methods, and Guided IG as a specific instance of an APM. Empirically, Guided IG creates saliency maps better aligned with the model's prediction and the input image that is being explained. We show through qualitative and quantitative experiments that Guided IG outperforms other, related methods in nearly every experiment.","url_abs":"https://arxiv.org/abs/2106.09788v1","url_pdf":"https://arxiv.org/pdf/2106.09788v1.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":"guided-integrated-gradients-an-adaptive-path","repo_url":"https://github.com/PAIR-code/saliency","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"guided-integrated-gradients-an-adaptive-path","repo_url":"https://github.com/MindSpore-scientific-2/code-9/tree/main/Integrated-Gradient","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.09788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09788"}},"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/PAIR-code/saliency","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-9/tree/main/Integrated-Gradient","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":"4d1b7fc161031727","entry":"l1_distance","repo":"PAIR-code/saliency","repo_kind":"official","path":"saliency/core/guided_ig.py","file_url":"https://github.com/PAIR-code/saliency/blob/HEAD/saliency/core/guided_ig.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d1b7fc161031727"}},{"code_sha256_prefix":"eaf84bea21f9586f","entry":"translate_alpha_to_x","repo":"PAIR-code/saliency","repo_kind":"official","path":"saliency/core/guided_ig.py","file_url":"https://github.com/PAIR-code/saliency/blob/HEAD/saliency/core/guided_ig.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eaf84bea21f9586f"}},{"code_sha256_prefix":"76e557aa61df2acc","entry":"translate_x_to_alpha","repo":"PAIR-code/saliency","repo_kind":"official","path":"saliency/core/guided_ig.py","file_url":"https://github.com/PAIR-code/saliency/blob/HEAD/saliency/core/guided_ig.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"76e557aa61df2acc"}},{"code_sha256_prefix":"4b1324ca21b95058","entry":"CoreSaliency","repo":"PAIR-code/saliency","repo_kind":"official","path":"saliency/core/guided_ig.py","file_url":"https://github.com/PAIR-code/saliency/blob/HEAD/saliency/core/guided_ig.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4b1324ca21b95058"}},{"code_sha256_prefix":"154475c7296f2723","entry":"GuidedIG","repo":"PAIR-code/saliency","repo_kind":"official","path":"saliency/core/guided_ig.py","file_url":"https://github.com/PAIR-code/saliency/blob/HEAD/saliency/core/guided_ig.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"154475c7296f2723"}},{"code_sha256_prefix":"a2d84e2079cb06d9","entry":"guided_ig_impl","repo":"PAIR-code/saliency","repo_kind":"official","path":"saliency/core/guided_ig.py","file_url":"https://github.com/PAIR-code/saliency/blob/HEAD/saliency/core/guided_ig.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a2d84e2079cb06d9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}