{"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/information-theoretic-visual-explanation-for","title":"Information-Theoretic Visual Explanation for Black-Box Classifiers","arxiv_id":"2009.11150","date":"2020-09-23","proceeding":null,"authors":["Jihun Yi","Eunji Kim","Siwon Kim","Sungroh Yoon"],"abstract":"In this work, we attempt to explain the prediction of any black-box classifier from an information-theoretic perspective. For each input feature, we compare the classifier outputs with and without that feature using two information-theoretic metrics. Accordingly, we obtain two attribution maps--an information gain (IG) map and a point-wise mutual information (PMI) map. IG map provides a class-independent answer to \"How informative is each pixel?\", and PMI map offers a class-specific explanation of \"How much does each pixel support a specific class?\" Compared to existing methods, our method improves the correctness of the attribution maps in terms of a quantitative metric. We also provide a detailed analysis of an ImageNet classifier using the proposed method, and the code is available online.","url_abs":"https://arxiv.org/abs/2009.11150v2","url_pdf":"https://arxiv.org/pdf/2009.11150v2.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":"information-theoretic-visual-explanation-for","repo_url":"https://github.com/nuclearboy95/XAI-Information-Theoretic-Explanation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.11150","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}