{"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/generative-multi-adversarial-networks","title":"Generative Multi-Adversarial Networks","arxiv_id":"1611.01673","date":"2016-11-05","proceeding":null,"authors":["Ishan Durugkar","Ian Gemp","Sridhar Mahadevan"],"abstract":"Generative adversarial networks (GANs) are a framework for producing a\ngenerative model by way of a two-player minimax game. In this paper, we propose\nthe \\emph{Generative Multi-Adversarial Network} (GMAN), a framework that\nextends GANs to multiple discriminators. In previous work, the successful\ntraining of GANs requires modifying the minimax objective to accelerate\ntraining early on. In contrast, GMAN can be reliably trained with the original,\nuntampered objective. We explore a number of design perspectives with the\ndiscriminator role ranging from formidable adversary to forgiving teacher.\nImage generation tasks comparing the proposed framework to standard GANs\ndemonstrate GMAN produces higher quality samples in a fraction of the\niterations when measured by a pairwise GAM-type metric.","url_abs":"http://arxiv.org/abs/1611.01673v3","url_pdf":"http://arxiv.org/pdf/1611.01673v3.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":"generative-multi-adversarial-networks","repo_url":"https://github.com/iDurugkar/GMAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01673","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}