{"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/removing-input-features-via-a-generative-1","title":"Explaining image classifiers by removing input features using generative models","arxiv_id":"1910.04256","date":"2019-10-09","proceeding":null,"authors":["Chirag Agarwal","Anh Nguyen"],"abstract":"Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e.g. blurring, adding noise, or graying out, which often produce unrealistic, out-of-samples. Instead, we propose to integrate a generative inpainter into three representative attribution methods to remove an input feature. Our proposed change improved all three methods in (1) generating more plausible counterfactual samples under the true data distribution; (2) being more accurate according to three metrics: object localization, deletion, and saliency metrics; and (3) being more robust to hyperparameter changes. Our findings were consistent across both ImageNet and Places365 datasets and two different pairs of classifiers and inpainters.","url_abs":"https://arxiv.org/abs/1910.04256v7","url_pdf":"https://arxiv.org/pdf/1910.04256v7.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":"removing-input-features-via-a-generative-1","repo_url":"https://github.com/anguyen8/generative-attribution-methods","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.04256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04256"}},"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/anguyen8/generative-attribution-methods","reach":null}],"summary":{"ran_fixture":3},"by_repo_kind":{"official":{"samples":3,"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":"d65508bbc009f7a6","entry":"create_blurred_circular_mask","repo":"anguyen8/generative-attribution-methods","repo_kind":"official","path":"formal_MP_single_image.py","file_url":"https://github.com/anguyen8/generative-attribution-methods/blob/HEAD/formal_MP_single_image.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d65508bbc009f7a6"}},{"code_sha256_prefix":"59a9a89ba48ff535","entry":"create_blurred_circular_mask_pyramid","repo":"anguyen8/generative-attribution-methods","repo_kind":"official","path":"formal_MP_single_image.py","file_url":"https://github.com/anguyen8/generative-attribution-methods/blob/HEAD/formal_MP_single_image.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59a9a89ba48ff535"}},{"code_sha256_prefix":"caaa603c2ed7da2a","entry":"numpy_to_torch","repo":"anguyen8/generative-attribution-methods","repo_kind":"official","path":"formal_MP_single_image.py","file_url":"https://github.com/anguyen8/generative-attribution-methods/blob/HEAD/formal_MP_single_image.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":"caaa603c2ed7da2a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}