{"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/unpaired-multi-domain-image-generation-via","title":"Unpaired Multi-Domain Image Generation via Regularized Conditional GANs","arxiv_id":"1805.02456","date":"2018-05-07","proceeding":null,"authors":["Xudong Mao","Qing Li"],"abstract":"In this paper, we study the problem of multi-domain image generation, the\ngoal of which is to generate pairs of corresponding images from different\ndomains. With the recent development in generative models, image generation has\nachieved great progress and has been applied to various computer vision tasks.\nHowever, multi-domain image generation may not achieve the desired performance\ndue to the difficulty of learning the correspondence of different domain\nimages, especially when the information of paired samples is not given. To\ntackle this problem, we propose Regularized Conditional GAN (RegCGAN) which is\ncapable of learning to generate corresponding images in the absence of paired\ntraining data. RegCGAN is based on the conditional GAN, and we introduce two\nregularizers to guide the model to learn the corresponding semantics of\ndifferent domains. We evaluate the proposed model on several tasks for which\npaired training data is not given, including the generation of edges and\nphotos, the generation of faces with different attributes, etc. The\nexperimental results show that our model can successfully generate\ncorresponding images for all these tasks, while outperforms the baseline\nmethods. We also introduce an approach of applying RegCGAN to unsupervised\ndomain adaptation.","url_abs":"http://arxiv.org/abs/1805.02456v1","url_pdf":"http://arxiv.org/pdf/1805.02456v1.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":"unpaired-multi-domain-image-generation-via","repo_url":"https://github.com/xudonmao/RegCGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}