{"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/wasserstein-introspective-neural-networks","title":"Wasserstein Introspective Neural Networks","arxiv_id":"1711.08875","date":"2017-11-24","proceeding":"CVPR 2018 6","authors":["Kwonjoon Lee","Weijian Xu","Fan Fan","Zhuowen Tu"],"abstract":"We present Wasserstein introspective neural networks (WINN) that are both a\ngenerator and a discriminator within a single model. WINN provides a\nsignificant improvement over the recent introspective neural networks (INN)\nmethod by enhancing INN's generative modeling capability. WINN has three\ninteresting properties: (1) A mathematical connection between the formulation\nof the INN algorithm and that of Wasserstein generative adversarial networks\n(WGAN) is made. (2) The explicit adoption of the Wasserstein distance into INN\nresults in a large enhancement to INN, achieving compelling results even with a\nsingle classifier --- e.g., providing nearly a 20 times reduction in model size\nover INN for unsupervised generative modeling. (3) When applied to supervised\nclassification, WINN also gives rise to improved robustness against adversarial\nexamples in terms of the error reduction. In the experiments, we report\nencouraging results on unsupervised learning problems including texture, face,\nand object modeling, as well as a supervised classification task against\nadversarial attacks.","url_abs":"http://arxiv.org/abs/1711.08875v5","url_pdf":"http://arxiv.org/pdf/1711.08875v5.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":"wasserstein-introspective-neural-networks","repo_url":"https://github.com/kjunelee/WINN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.08875","atlas_url":"https://app.syntology.ai/?focus=1711.08875","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}