{"work":{"id":"9fe7734e-4726-441f-abc1-88bbce75815c","openalex_id":"https://openalex.org/W2626639386","doi":"10.48550/arxiv.1706.03825","arxiv_id":"1706.03825","raw_key":null,"title":"SmoothGrad: removing noise by adding noise","authors":null,"authors_text":"Smilkov, D","year":2017,"venue":"cs.LG","abstract":"Explaining the output of a deep network remains a challenge. In the case of an image classifier, one type of explanation is to identify pixels that strongly influence the final decision. A starting point for this strategy is the gradient of the class score function with respect to the input image. This gradient can be interpreted as a sensitivity map, and there are several techniques that elaborate on this basic idea. This paper makes two contributions: it introduces SmoothGrad, a simple method that can help visually sharpen gradient-based sensitivity maps, and it discusses lessons in the visualization of these maps. We publish the code for our experiments and a website with our results.","external_url":"https://arxiv.org/abs/1706.03825","cited_by_count":755,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"1706.03825","created_at":"2026-05-10T09:38:42.783377+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"SmoothGrad: removing noise by adding noise","render_title":"SmoothGrad: removing noise by adding noise"},"hub":{"state":{"work_id":"9fe7734e-4726-441f-abc1-88bbce75815c","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":51,"external_cited_by_count":755,"distinct_field_count":7,"first_pith_cited_at":"2019-06-25T00:43:32+00:00","last_pith_cited_at":"2026-07-08T10:50:04+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T22:19:23.221460+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}