{"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/fisher-gan","title":"Fisher GAN","arxiv_id":"1705.09675","date":"2017-05-26","proceeding":"NeurIPS 2017 12","authors":["Youssef Mroueh","Tom Sercu"],"abstract":"Generative Adversarial Networks (GANs) are powerful models for learning\ncomplex distributions. Stable training of GANs has been addressed in many\nrecent works which explore different metrics between distributions. In this\npaper we introduce Fisher GAN which fits within the Integral Probability\nMetrics (IPM) framework for training GANs. Fisher GAN defines a critic with a\ndata dependent constraint on its second order moments. We show in this paper\nthat Fisher GAN allows for stable and time efficient training that does not\ncompromise the capacity of the critic, and does not need data independent\nconstraints such as weight clipping. We analyze our Fisher IPM theoretically\nand provide an algorithm based on Augmented Lagrangian for Fisher GAN. We\nvalidate our claims on both image sample generation and semi-supervised\nclassification using Fisher GAN.","url_abs":"http://arxiv.org/abs/1705.09675v3","url_pdf":"http://arxiv.org/pdf/1705.09675v3.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":"fisher-gan","repo_url":"https://github.com/tomsercu/FisherGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fisher-gan","repo_url":"https://github.com/yjhong89/Domain-Adaptation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.09675","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}