{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/explaining-image-classifiers-by","title":"Explaining Image Classifiers by Counterfactual Generation","arxiv_id":"1807.08024","date":"2018-07-20","proceeding":"ICLR 2019 5","authors":["Chun-Hao Chang","Elliot Creager","Anna Goldenberg","David Duvenaud"],"abstract":"When an image classifier makes a prediction, which parts of the image are\nrelevant and why? We can rephrase this question to ask: which parts of the\nimage, if they were not seen by the classifier, would most change its decision?\nProducing an answer requires marginalizing over images that could have been\nseen but weren't. We can sample plausible image in-fills by conditioning a\ngenerative model on the rest of the image. We then optimize to find the image\nregions that most change the classifier's decision after in-fill. Our approach\ncontrasts with ad-hoc in-filling approaches, such as blurring or injecting\nnoise, which generate inputs far from the data distribution, and ignore\ninformative relationships between different parts of the image. Our method\nproduces more compact and relevant saliency maps, with fewer artifacts compared\nto previous methods.","url_abs":"http://arxiv.org/abs/1807.08024v3","url_pdf":"http://arxiv.org/pdf/1807.08024v3.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":"explaining-image-classifiers-by","repo_url":"https://github.com/zzzace2000/FIDO-saliency","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.08024","atlas_url":"https://app.syntology.ai/?focus=1807.08024","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1807.08024"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1807.08024\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1807.08024"},"call":"get_concepts_for_paper(arxiv_id=\"1807.08024\")"}],"by_repo":[{"repo":"zzzace2000/FIDO-saliency","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"04f00682d9bdda00c8fdcf33d95cb967e1011741b2902371d27c9e405c169c1c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}