{"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/class-splitting-generative-adversarial","title":"Class-Splitting Generative Adversarial Networks","arxiv_id":"1709.07359","date":"2017-09-21","proceeding":null,"authors":["Guillermo L. Grinblat","Lucas C. Uzal","Pablo M. Granitto"],"abstract":"Generative Adversarial Networks (GANs) produce systematically better quality\nsamples when class label information is provided., i.e. in the conditional GAN\nsetup. This is still observed for the recently proposed Wasserstein GAN\nformulation which stabilized adversarial training and allows considering high\ncapacity network architectures such as ResNet. In this work we show how to\nboost conditional GAN by augmenting available class labels. The new classes\ncome from clustering in the representation space learned by the same GAN model.\nThe proposed strategy is also feasible when no class information is available,\ni.e. in the unsupervised setup. Our generated samples reach state-of-the-art\nInception scores for CIFAR-10 and STL-10 datasets in both supervised and\nunsupervised setup.","url_abs":"http://arxiv.org/abs/1709.07359v2","url_pdf":"http://arxiv.org/pdf/1709.07359v2.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":"class-splitting-generative-adversarial","repo_url":"https://github.com/CIFASIS/splitting_gan","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-cifar-10","task":"Conditional Image Generation","dataset":"CIFAR-10","model":"Splitting GAN","rank_in_archive_order":17,"of":25,"metrics":{"Inception score":"8.87"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}