{"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/pre-or-post-softmax-scores-in-gradient-based","title":"Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?","arxiv_id":"2306.13197","date":"2023-06-22","proceeding":null,"authors":["Miguel Lerma","Mirtha Lucas"],"abstract":"Gradient based attribution methods for neural networks working as classifiers use gradients of network scores. Here we discuss the practical differences between using gradients of pre-softmax scores versus post-softmax scores, and their respective advantages and disadvantages.","url_abs":"https://arxiv.org/abs/2306.13197v2","url_pdf":"https://arxiv.org/pdf/2306.13197v2.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":"pre-or-post-softmax-scores-in-gradient-based","repo_url":"https://github.com/mlerma54/adversarial-attacks-on-saliency-maps","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.13197","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}