{"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/saliency-maps-give-a-false-sense-of","title":"Saliency Maps Give a False Sense of Explanability to Image Classifiers: An Empirical Evaluation across Methods and Metrics","arxiv_id":null,"date":"2024-12-03","proceeding":"ACML 2024 12","authors":["Hanwei Zhang","Felipe Torres Figueroa","Holger Hermanns"],"abstract":"The interpretability of deep neural networks (DNNs) has emerged as a crucial area of research,\r\nparticularly in image classification tasks where decisions often lack transparency. Saliency maps\r\nhave been widely used as a tool to decode the inner workings of these networks by highlighting\r\nregions of input images deemed most influential in the classification process. However, recent\r\nstudies have revealed significant limitations and inconsistencies in the utility of saliency maps as\r\nexplanations. This paper aims to systematically assess the shortcomings of saliency maps and\r\nexplore alternative approaches to achieve more reliable and interpretable explanations for image\r\nclassification models. We carry out a series of experiments to show that 1) the existing evaluation\r\ndoes not provide a fair nor meaningful comparison to the existing saliency maps; these evaluations\r\nhave their implicit assumption and are not differentiable; 2) the saliency maps do not provide\r\nenough information on explaining the accuracy of network, the relationship between classes and\r\nthe modification of the images.","url_abs":"https://scholar.google.fr/citations?view_op=view_citation&hl=zh-CN&user=7QjjN2wAAAAJ&cstart=20&pagesize=80&citation_for_view=7QjjN2wAAAAJ:_kc_bZDykSQC","url_pdf":"https://openreview.net/pdf?id=Hftgajppmz","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":"saliency-maps-give-a-false-sense-of","repo_url":"https://github.com/ftorres11/saliencysense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"ftorres11/saliencysense","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1806.07421"],"harvested_for_calls":[{"arxiv_id":"1806.07421","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1806.07421"},"call":"get_harvested_code_for_paper(arxiv_id=\"1806.07421\")"}]}],"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":"24c9371927ac8682e92a671e4b3b01bc5c4211d2eccbcc7f808e27e978361c05","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}