{"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/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"},"arxiv_metadata":null,"syntology_extracted_results":null}