{"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/generator-knows-what-discriminator-should","title":"Generator Knows What Discriminator Should Learn in Unconditional GANs","arxiv_id":"2207.13320","date":"2022-07-27","proceeding":null,"authors":["Gayoung Lee","Hyunsu Kim","Junho Kim","Seonghyeon Kim","Jung-Woo Ha","Yunjey Choi"],"abstract":"Recent methods for conditional image generation benefit from dense supervision such as segmentation label maps to achieve high-fidelity. However, it is rarely explored to employ dense supervision for unconditional image generation. Here we explore the efficacy of dense supervision in unconditional generation and find generator feature maps can be an alternative of cost-expensive semantic label maps. From our empirical evidences, we propose a new generator-guided discriminator regularization(GGDR) in which the generator feature maps supervise the discriminator to have rich semantic representations in unconditional generation. In specific, we employ an U-Net architecture for discriminator, which is trained to predict the generator feature maps given fake images as inputs. Extensive experiments on mulitple datasets show that our GGDR consistently improves the performance of baseline methods in terms of quantitative and qualitative aspects. Code is available at https://github.com/naver-ai/GGDR","url_abs":"https://arxiv.org/abs/2207.13320v1","url_pdf":"https://arxiv.org/pdf/2207.13320v1.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":"generator-knows-what-discriminator-should","repo_url":"https://github.com/naver-ai/ggdr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"unconditional-image-generation","task_name":"Unconditional Image Generation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.13320","atlas_url":"https://app.syntology.ai/?focus=2207.13320","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}