{"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/cgans-with-multi-hinge-loss","title":"cGANs with Multi-Hinge Loss","arxiv_id":"1912.04216","date":"2019-12-09","proceeding":null,"authors":["Ilya Kavalerov","Wojciech Czaja","Rama Chellappa"],"abstract":"We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study the compromise between training a state of the art generator and an accurate classifier simultaneously, and propose a way to use our algorithm to measure the degree to which a generator and critic are class conditional. We show the trade-off between a generator-critic pair respecting class conditioning inputs and generating the highest quality images. With our multi-hinge loss modification we are able to improve Inception Scores and Frechet Inception Distance on the Imagenet dataset. We make our tensorflow code available at https://github.com/ilyakava/gan.","url_abs":"https://arxiv.org/abs/1912.04216v2","url_pdf":"https://arxiv.org/pdf/1912.04216v2.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":"cgans-with-multi-hinge-loss","repo_url":"https://github.com/ilyakava/BigGAN-PyTorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cgans-with-multi-hinge-loss","repo_url":"https://github.com/ilyakava/gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cgans-with-multi-hinge-loss","repo_url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/CGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-cifar-10","task":"Conditional Image Generation","dataset":"CIFAR-10","model":"MHingeGAN","rank_in_archive_order":9,"of":25,"metrics":{"FID":"7.5","Inception score":"9.58"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-cifar-100","task":"Conditional Image Generation","dataset":"CIFAR-100","model":"MHingeGAN","rank_in_archive_order":7,"of":7,"metrics":{"FID":"17.3","Inception Score":"14.36"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.04216","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}