{"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/chaingan-a-sequential-approach-to-gans","title":"ChainGAN: A sequential approach to GANs","arxiv_id":"1811.08081","date":"2018-11-20","proceeding":"ICLR 2019 5","authors":["Safwan Hossain","Kiarash Jamali","Yuchen Li","Frank Rudzicz"],"abstract":"We propose a new architecture and training methodology for generative\nadversarial networks. Current approaches attempt to learn the transformation\nfrom a noise sample to a generated data sample in one shot. Our proposed\ngenerator architecture, called $\\textit{ChainGAN}$, uses a two-step process. It\nfirst attempts to transform a noise vector into a crude sample, similar to a\ntraditional generator. Next, a chain of networks, called $\\textit{editors}$,\nattempt to sequentially enhance this sample. We train each of these units\nindependently, instead of with end-to-end backpropagation on the entire chain.\nOur model is robust, efficient, and flexible as we can apply it to various\nnetwork architectures. We provide rationale for our choices and experimentally\nevaluate our model, achieving competitive results on several datasets.","url_abs":"http://arxiv.org/abs/1811.08081v2","url_pdf":"http://arxiv.org/pdf/1811.08081v2.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":"chaingan-a-sequential-approach-to-gans","repo_url":"https://github.com/safwanhossain/chainGAN_repo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","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}