{"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/improving-the-improved-training-of","title":"Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect","arxiv_id":"1803.01541","date":"2018-03-05","proceeding":"ICLR 2018 1","authors":["Xiang Wei","Boqing Gong","Zixia Liu","Wei Lu","Liqiang Wang"],"abstract":"Despite being impactful on a variety of problems and applications, the\ngenerative adversarial nets (GANs) are remarkably difficult to train. This\nissue is formally analyzed by \\cite{arjovsky2017towards}, who also propose an\nalternative direction to avoid the caveats in the minmax two-player training of\nGANs. The corresponding algorithm, called Wasserstein GAN (WGAN), hinges on the\n1-Lipschitz continuity of the discriminator. In this paper, we propose a novel\napproach to enforcing the Lipschitz continuity in the training procedure of\nWGANs. Our approach seamlessly connects WGAN with one of the recent\nsemi-supervised learning methods. As a result, it gives rise to not only better\nphoto-realistic samples than the previous methods but also state-of-the-art\nsemi-supervised learning results. In particular, our approach gives rise to the\ninception score of more than 5.0 with only 1,000 CIFAR-10 images and is the\nfirst that exceeds the accuracy of 90% on the CIFAR-10 dataset using only 4,000\nlabeled images, to the best of our knowledge.","url_abs":"http://arxiv.org/abs/1803.01541v1","url_pdf":"http://arxiv.org/pdf/1803.01541v1.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":"improving-the-improved-training-of","repo_url":"https://github.com/biuyq/CT-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"wgan","method_name":"WGAN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.01541","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}