{"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/sanity-checks-for-saliency-maps","title":"Sanity Checks for Saliency Maps","arxiv_id":"1810.03292","date":"2018-10-08","proceeding":"NeurIPS 2018 12","authors":["Julius Adebayo","Justin Gilmer","Michael Muelly","Ian Goodfellow","Moritz Hardt","Been Kim"],"abstract":"Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work, we propose an actionable methodology to evaluate what kinds of explanations a given method can and cannot provide. We find that reliance, solely, on visual assessment can be misleading. Through extensive experiments we show that some existing saliency methods are independent both of the model and of the data generating process. Consequently, methods that fail the proposed tests are inadequate for tasks that are sensitive to either data or model, such as, finding outliers in the data, explaining the relationship between inputs and outputs that the model learned, and debugging the model. We interpret our findings through an analogy with edge detection in images, a technique that requires neither training data nor model. Theory in the case of a linear model and a single-layer convolutional neural network supports our experimental findings.","url_abs":"https://arxiv.org/abs/1810.03292v3","url_pdf":"https://arxiv.org/pdf/1810.03292v3.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":"sanity-checks-for-saliency-maps","repo_url":"https://github.com/adebayoj/sanity_checks_saliency","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"sanity-checks-for-saliency-maps","repo_url":"https://github.com/Shubhambindal2017/Unoffical-Implementation-of-GRAD-CAM-with-Sanity-Checks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sanity-checks-for-saliency-maps","repo_url":"https://github.com/annahedstroem/sanity-checks-revisited","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sanity-checks-for-saliency-maps","repo_url":"https://github.com/jendawkins/saliencySanity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sanity-checks-for-saliency-maps","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"}}],"tasks":[{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"}],"methods":[{"method_slug":"xgrad-cam","method_name":"XGrad-CAM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.03292","atlas_url":"https://app.syntology.ai/?focus=1810.03292","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":"1810.03292"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1810.03292\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1810.03292"},"call":"get_concepts_for_paper(arxiv_id=\"1810.03292\")"}],"by_repo":[{"repo":"adebayoj/sanity_checks_saliency","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Shubhambindal2017/Unoffical-Implementation-of-GRAD-CAM-with-Sanity-Checks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1610.02391"],"harvested_for_calls":[{"arxiv_id":"1610.02391","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1610.02391"},"call":"get_harvested_code_for_paper(arxiv_id=\"1610.02391\")"}]},{"repo":"annahedstroem/sanity-checks-revisited","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.02383"],"harvested_for_calls":[{"arxiv_id":"2405.02383","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.02383"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.02383\")"}]},{"repo":"jendawkins/saliencySanity","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pytorch/captum","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2304.11327"],"harvested_for_calls":[{"arxiv_id":"2304.11327","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.11327"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.11327\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"aa41b084578eb74420191bf9b9cab51db85954727e77b14037bb9a1a259bd7b0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}