{"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/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":{"atlas_url":"https://app.syntology.ai/?focus=1807.08024","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}