{"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/why-are-saliency-maps-noisy-cause-of-and","title":"Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps","arxiv_id":"1902.04893","date":"2019-02-13","proceeding":null,"authors":["Beomsu Kim","Junghoon Seo","SeungHyun Jeon","Jamyoung Koo","Jeongyeol Choe","Taegyun Jeon"],"abstract":"Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were proposed to account for this phenomenon, there are few works that provide rigorous analyses of noisy saliency maps. In this paper, we firstly propose a new hypothesis that noise may occur in saliency maps when irrelevant features pass through ReLU activation functions. Then, we propose Rectified Gradient, a method that alleviates this problem through layer-wise thresholding during backpropagation. Experiments with neural networks trained on CIFAR-10 and ImageNet showed effectiveness of our method and its superiority to other attribution methods.","url_abs":"https://arxiv.org/abs/1902.04893v3","url_pdf":"https://arxiv.org/pdf/1902.04893v3.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":"why-are-saliency-maps-noisy-cause-of-and","repo_url":"https://github.com/1202kbs/Rectified-Gradient","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"why-are-saliency-maps-noisy-cause-of-and","repo_url":"https://github.com/lenbrocki/NoBias-Rectified-Gradient","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.04893","atlas_url":"https://app.syntology.ai/?focus=1902.04893","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":"1902.04893"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1902.04893\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1902.04893"},"call":"get_concepts_for_paper(arxiv_id=\"1902.04893\")"}],"by_repo":[{"repo":"1202kbs/Rectified-Gradient","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lenbrocki/NoBias-Rectified-Gradient","kind":"listed","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":"a879463fdbe70305d4c9f3d36cb1a921b40fdf386655f8632b9ad4bb5acc0aa1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}