{"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/re-gan-data-efficient-gans-training-via","title":"Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration","arxiv_id":null,"date":"2023-01-01","proceeding":"CVPR 2023 1","authors":["Divya Saxena","Jiannong Cao","Jiahao Xu","Tarun Kulshrestha"],"abstract":"    Training Generative Adversarial Networks (GANs) on high-fidelity images usually requires a vast number of training images. Recent research on GAN tickets reveals that dense GANs models contain sparse sub-networks or \"lottery tickets\" that, when trained separately, yield better results under limited data. However, finding GANs tickets requires an expensive process of train-prune-retrain. In this paper, we propose Re-GAN, a data-efficient GANs training that dynamically reconfigures GANs architecture during training to explore different sub-network structures in training time. Our method repeatedly prunes unimportant connections to regularize GANs network and regrows them to reduce the risk of prematurely pruning important connections. Re-GAN stabilizes the GANs models with less data and offers an alternative to the existing GANs tickets and progressive growing methods. We demonstrate that Re-GAN is a generic training methodology which achieves stability on datasets of varying sizes, domains, and resolutions (CIFAR-10, Tiny-ImageNet, and multiple few-shot generation datasets) as well as different GANs architectures (SNGAN, ProGAN, StyleGAN2 and AutoGAN). Re-GAN also improves performance when combined with the recent augmentation approaches. Moreover, Re-GAN requires fewer floating-point operations (FLOPs) and less training time by removing the unimportant connections during GANs training while maintaining comparable or even generating higher-quality samples. When compared to state-of-the-art StyleGAN2, our method outperforms without requiring any additional fine-tuning step. Code can be found at this link: https://github.com/IntellicentAI-Lab/Re-GAN    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2023/html/Saxena_Re-GAN_Data-Efficient_GANs_Training_via_Architectural_Reconfiguration_CVPR_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2023/papers/Saxena_Re-GAN_Data-Efficient_GANs_Training_via_Architectural_Reconfiguration_CVPR_2023_paper.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":"re-gan-data-efficient-gans-training-via","repo_url":"https://github.com/intellicentai-lab/re-gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"gan-hinge-loss","method_name":"GAN Hinge Loss"},{"method_slug":"progan","method_name":"ProGAN"},{"method_slug":"sngan","method_name":"SNGAN"},{"method_slug":"spectral-normalization","method_name":"Spectral Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}