{"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/omni-gan-on-the-secrets-of-cgans-and-beyond","title":"Omni-GAN: On the Secrets of cGANs and Beyond","arxiv_id":"2011.13074","date":"2020-11-26","proceeding":"ICCV 2021 10","authors":["Peng Zhou","Lingxi Xie","Bingbing Ni","Cong Geng","Qi Tian"],"abstract":"The conditional generative adversarial network (cGAN) is a powerful tool of generating high-quality images, but existing approaches mostly suffer unsatisfying performance or the risk of mode collapse. This paper presents Omni-GAN, a variant of cGAN that reveals the devil in designing a proper discriminator for training the model. The key is to ensure that the discriminator receives strong supervision to perceive the concepts and moderate regularization to avoid collapse. Omni-GAN is easily implemented and freely integrated with off-the-shelf encoding methods (e.g., implicit neural representation, INR). Experiments validate the superior performance of Omni-GAN and Omni-INR-GAN in a wide range of image generation and restoration tasks. In particular, Omni-INR-GAN sets new records on the ImageNet dataset with impressive Inception scores of 262.85 and 343.22 for the image sizes of 128 and 256, respectively, surpassing the previous records by 100+ points. Moreover, leveraging the generator prior, Omni-INR-GAN can extrapolate low-resolution images to arbitrary resolution, even up to x60+ higher resolution. Code is available.","url_abs":"https://arxiv.org/abs/2011.13074v3","url_pdf":"https://arxiv.org/pdf/2011.13074v3.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":"omni-gan-on-the-secrets-of-cgans-and-beyond","repo_url":"https://github.com/PeterouZh/Omni-GAN-PyTorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"omni-gan-on-the-secrets-of-cgans-and-beyond","repo_url":"https://github.com/gcervantes8/Game-Image-Generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"omni-gan-on-the-secrets-of-cgans-and-beyond","repo_url":"https://github.com/2023-MindSpore-4/Code8/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"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"biggan","method_name":"BigGAN"},{"method_slug":"conditional-batch-normalization","method_name":"Conditional Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"early-stopping","method_name":"Early Stopping"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"gan-hinge-loss","method_name":"GAN Hinge Loss"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"non-local-block","method_name":"Non-Local Block"},{"method_slug":"non-local-operation","method_name":"Non-Local Operation"},{"method_slug":"off-diagonal-orthogonal-regularization","method_name":"Off-Diagonal Orthogonal Regularization"},{"method_slug":"projection-discriminator","method_name":"Projection Discriminator"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sagan","method_name":"SAGAN"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spectral-normalization","method_name":"Spectral Normalization"},{"method_slug":"ttur","method_name":"TTUR"},{"method_slug":"truncation-trick","method_name":"Truncation Trick"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-imagenet","task":"Conditional Image Generation","dataset":"ImageNet 128x128","model":"Omni-INR-GAN","rank_in_archive_order":8,"of":22,"metrics":{"FID":"6.53","Inception score":"262.85"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-imagenet","task":"Conditional Image Generation","dataset":"ImageNet 128x128","model":"Omni-GAN","rank_in_archive_order":13,"of":22,"metrics":{"FID":"8.30","Inception score":"190.94"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.13074","atlas_url":"https://app.syntology.ai/?focus=2011.13074","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}