{"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/maximizing-invariant-data-perturbation-with","title":"Maximizing Invariant Data Perturbation with Stochastic Optimization","arxiv_id":"1807.05077","date":"2018-07-12","proceeding":null,"authors":["Kouichi Ikeno","Satoshi Hara"],"abstract":"Feature attribution methods, or saliency maps, are one of the most popular\napproaches for explaining the decisions of complex machine learning models such\nas deep neural networks. In this study, we propose a stochastic optimization\napproach for the perturbation-based feature attribution method. While the\noriginal optimization problem of the perturbation-based feature attribution is\ndifficult to solve because of the complex constraints, we propose to\nreformulate the problem as the maximization of a differentiable function, which\ncan be solved using gradient-based algorithms. In particular, stochastic\noptimization is well-suited for the proposed reformulation, and we can solve\nthe problem using popular algorithms such as SGD, RMSProp, and Adam. The\nexperiment on the image classification with VGG16 shows that the proposed\nmethod could identify relevant parts of the images effectively.","url_abs":"http://arxiv.org/abs/1807.05077v2","url_pdf":"http://arxiv.org/pdf/1807.05077v2.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":"maximizing-invariant-data-perturbation-with","repo_url":"https://github.com/sato9hara/PertMap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}