{"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/training-generative-adversarial-networks-via","title":"Training Generative Adversarial Networks Via Turing Test","arxiv_id":"1810.10948","date":"2018-10-25","proceeding":null,"authors":["Jianlin Su"],"abstract":"In this article, we introduce a new mode for training Generative Adversarial\nNetworks (GANs). Rather than minimizing the distance of evidence distribution\n$\\tilde{p}(x)$ and the generative distribution $q(x)$, we minimize the distance\nof $\\tilde{p}(x_r)q(x_f)$ and $\\tilde{p}(x_f)q(x_r)$. This adversarial pattern\ncan be interpreted as a Turing test in GANs. It allows us to use information of\nreal samples during training generator and accelerates the whole training\nprocedure. We even find that just proportionally increasing the size of\ndiscriminator and generator, it succeeds on 256x256 resolution without\nadjusting hyperparameters carefully.","url_abs":"http://arxiv.org/abs/1810.10948v2","url_pdf":"http://arxiv.org/pdf/1810.10948v2.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":"training-generative-adversarial-networks-via","repo_url":"https://github.com/bojone/T-GANs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}