{"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/combogan-unrestrained-scalability-for-image","title":"ComboGAN: Unrestrained Scalability for Image Domain Translation","arxiv_id":"1712.06909","date":"2017-12-19","proceeding":null,"authors":["Asha Anoosheh","Eirikur Agustsson","Radu Timofte","Luc Van Gool"],"abstract":"This year alone has seen unprecedented leaps in the area of learning-based\nimage translation, namely CycleGAN, by Zhu et al. But experiments so far have\nbeen tailored to merely two domains at a time, and scaling them to more would\nrequire an quadratic number of models to be trained. And with two-domain models\ntaking days to train on current hardware, the number of domains quickly becomes\nlimited by the time and resources required to process them. In this paper, we\npropose a multi-component image translation model and training scheme which\nscales linearly - both in resource consumption and time required - with the\nnumber of domains. We demonstrate its capabilities on a dataset of paintings by\n14 different artists and on images of the four different seasons in the Alps.\nNote that 14 data groups would need (14 choose 2) = 91 different CycleGAN\nmodels: a total of 182 generator/discriminator pairs; whereas our model\nrequires only 14 generator/discriminator pairs.","url_abs":"http://arxiv.org/abs/1712.06909v1","url_pdf":"http://arxiv.org/pdf/1712.06909v1.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":"combogan-unrestrained-scalability-for-image","repo_url":"https://github.com/AAnoosheh/ComboGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cycle-consistency-loss","method_name":"Cycle Consistency Loss"},{"method_slug":"gan-least-squares-loss","method_name":"GAN Least Squares Loss"},{"method_slug":"instance-normalization","method_name":"Instance Normalization"},{"method_slug":"patchgan","method_name":"PatchGAN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.06909","atlas_url":"https://app.syntology.ai/?focus=1712.06909","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}