{"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/interpretable-explanations-of-black-boxes-by","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","arxiv_id":"1704.03296","date":"2017-04-11","proceeding":"ICCV 2017 10","authors":["Ruth Fong","Andrea Vedaldi"],"abstract":"As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In recent years, a number of image saliency methods have been developed to summarize where highly complex neural networks \"look\" in an image for evidence for their predictions. However, these techniques are limited by their heuristic nature and architectural constraints. In this paper, we make two main contributions: First, we propose a general framework for learning different kinds of explanations for any black box algorithm. Second, we specialise the framework to find the part of an image most responsible for a classifier decision. Unlike previous works, our method is model-agnostic and testable because it is grounded in explicit and interpretable image perturbations.","url_abs":"https://arxiv.org/abs/1704.03296v4","url_pdf":"https://arxiv.org/pdf/1704.03296v4.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":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/ruthcfong/perturb_explanations","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/ajsanjoaquin/mPerturb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/dakaun/meaningful-perturbation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/dizcza/EmbedderSDR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/dizcza/pytorch-mighty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/jacobgil/pytorch-explain-black-box","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/labouz/xai-pres-1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/MindSpore-scientific-2/code-4/tree/main/IEBBMP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/IEBBMP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/MindSpore-scientific-2/code-9/tree/main/IEBBMP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/MindSpore-scientific/code-12/tree/main/IEBBMP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/MindSpore-scientific/code-4/tree/main/IEBBMP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"interpretable-explanations-of-black-boxes-by","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/IEBBMP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"interpretable-machine-learning","task_name":"Interpretable Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.03296","atlas_url":"https://app.syntology.ai/?focus=1704.03296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.03296"}},"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/jacobgil/pytorch-explain-black-box","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/4/IEBBMP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/labouz/xai-pres-1","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/IEBBMP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-12/tree/main/IEBBMP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dakaun/meaningful-perturbation","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-4/tree/main/IEBBMP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ruthcfong/perturb_explanations","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dizcza/pytorch-mighty","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ajsanjoaquin/mPerturb","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dizcza/EmbedderSDR","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-4/tree/main/IEBBMP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-9/tree/main/IEBBMP","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"listed":{"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":"3d7b081f5fd132b2","entry":"postprocess","repo":"ajsanjoaquin/mPerturb","repo_kind":"listed","path":"perturb.py","file_url":"https://github.com/ajsanjoaquin/mPerturb/blob/HEAD/perturb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d7b081f5fd132b2"}},{"code_sha256_prefix":"1f0f2919b88d94f0","entry":"tv_norm","repo":"ajsanjoaquin/mPerturb","repo_kind":"listed","path":"perturb.py","file_url":"https://github.com/ajsanjoaquin/mPerturb/blob/HEAD/perturb.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":"1f0f2919b88d94f0"}},{"code_sha256_prefix":"ab2289f7c008dce2","entry":"upsample","repo":"ajsanjoaquin/mPerturb","repo_kind":"listed","path":"perturb.py","file_url":"https://github.com/ajsanjoaquin/mPerturb/blob/HEAD/perturb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab2289f7c008dce2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}