{"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/veegan-reducing-mode-collapse-in-gans-using","title":"VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning","arxiv_id":"1705.07761","date":"2017-05-22","proceeding":"NeurIPS 2017 12","authors":["Akash Srivastava","Lazar Valkov","Chris Russell","Michael U. Gutmann","Charles Sutton"],"abstract":"Deep generative models provide powerful tools for distributions over\ncomplicated manifolds, such as those of natural images. But many of these\nmethods, including generative adversarial networks (GANs), can be difficult to\ntrain, in part because they are prone to mode collapse, which means that they\ncharacterize only a few modes of the true distribution. To address this, we\nintroduce VEEGAN, which features a reconstructor network, reversing the action\nof the generator by mapping from data to noise. Our training objective retains\nthe original asymptotic consistency guarantee of GANs, and can be interpreted\nas a novel autoencoder loss over the noise. In sharp contrast to a traditional\nautoencoder over data points, VEEGAN does not require specifying a loss\nfunction over the data, but rather only over the representations, which are\nstandard normal by assumption. On an extensive set of synthetic and real world\nimage datasets, VEEGAN indeed resists mode collapsing to a far greater extent\nthan other recent GAN variants, and produces more realistic samples.","url_abs":"http://arxiv.org/abs/1705.07761v3","url_pdf":"http://arxiv.org/pdf/1705.07761v3.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":"veegan-reducing-mode-collapse-in-gans-using","repo_url":"https://github.com/alex98chen/testGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.07761","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}