{"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/adversarial-dropout-for-supervised-and-semi","title":"Adversarial Dropout for Supervised and Semi-supervised Learning","arxiv_id":"1707.03631","date":"2017-07-12","proceeding":null,"authors":["Sungrae Park","Jun-Keon Park","Su-Jin Shin","Il-Chul Moon"],"abstract":"Recently, the training with adversarial examples, which are generated by\nadding a small but worst-case perturbation on input examples, has been proved\nto improve generalization performance of neural networks. In contrast to the\nindividually biased inputs to enhance the generality, this paper introduces\nadversarial dropout, which is a minimal set of dropouts that maximize the\ndivergence between the outputs from the network with the dropouts and the\ntraining supervisions. The identified adversarial dropout are used to\nreconfigure the neural network to train, and we demonstrated that training on\nthe reconfigured sub-network improves the generalization performance of\nsupervised and semi-supervised learning tasks on MNIST and CIFAR-10. We\nanalyzed the trained model to reason the performance improvement, and we found\nthat adversarial dropout increases the sparsity of neural networks more than\nthe standard dropout does.","url_abs":"http://arxiv.org/abs/1707.03631v2","url_pdf":"http://arxiv.org/pdf/1707.03631v2.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":"adversarial-dropout-for-supervised-and-semi","repo_url":"https://github.com/sungraepark/Adversarial-Dropout","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-dropout-for-supervised-and-semi","repo_url":"https://github.com/alexboii/Adversarial-Dropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-dropout-for-supervised-and-semi","repo_url":"https://github.com/tiff-wang/adversarial-dropout-reproducibility-challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.03631","atlas_url":"https://app.syntology.ai/?focus=1707.03631","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}