{"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/smoothgrad-removing-noise-by-adding-noise","title":"SmoothGrad: removing noise by adding noise","arxiv_id":"1706.03825","date":"2017-06-12","proceeding":null,"authors":["Daniel Smilkov","Nikhil Thorat","Been Kim","Fernanda Viégas","Martin Wattenberg"],"abstract":"Explaining the output of a deep network remains a challenge. In the case of\nan image classifier, one type of explanation is to identify pixels that\nstrongly influence the final decision. A starting point for this strategy is\nthe gradient of the class score function with respect to the input image. This\ngradient can be interpreted as a sensitivity map, and there are several\ntechniques that elaborate on this basic idea. This paper makes two\ncontributions: it introduces SmoothGrad, a simple method that can help visually\nsharpen gradient-based sensitivity maps, and it discusses lessons in the\nvisualization of these maps. We publish the code for our experiments and a\nwebsite with our results.","url_abs":"http://arxiv.org/abs/1706.03825v1","url_pdf":"http://arxiv.org/pdf/1706.03825v1.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":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/PAIR-code/saliency","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/TooTouch/WhiteBox-Part1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/ascillitoe/shap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/austinbrown34/shap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/bips-hb/innsight","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/gablabc/shap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/hs2k/pytorch-smoothgrad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/idiap/fullgrad-saliency","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/koren-v/Interpret","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/miaolan-xie/shap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/pytorch/captum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/saivarunr/xshap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/sar-gupta/convisualize_nb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/shaoshanglqy/shap-shapley","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/shap/shap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/sicara/tf-explain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/slundberg/shap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/vlue-c/PyTorch-Explanations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/vlue-c/Visual-Explanation-Methods-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smoothgrad-removing-noise-by-adding-noise","repo_url":"https://github.com/xiaoyanLi629/ScRNA-seq-integration-by-Heterogeneous-Graph-transformer-neural-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"interpretable-machine-learning","task_name":"Interpretable Machine Learning"},{"task_slug":"sensitivity","task_name":"Sensitivity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.03825","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}