{"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/discriminator-rejection-sampling","title":"Discriminator Rejection Sampling","arxiv_id":"1810.06758","date":"2018-10-16","proceeding":"ICLR 2019 5","authors":["Samaneh Azadi","Catherine Olsson","Trevor Darrell","Ian Goodfellow","Augustus Odena"],"abstract":"We propose a rejection sampling scheme using the discriminator of a GAN to\napproximately correct errors in the GAN generator distribution. We show that\nunder quite strict assumptions, this will allow us to recover the data\ndistribution exactly. We then examine where those strict assumptions break down\nand design a practical algorithm - called Discriminator Rejection Sampling\n(DRS) - that can be used on real data-sets. Finally, we demonstrate the\nefficacy of DRS on a mixture of Gaussians and on the SAGAN model,\nstate-of-the-art in the image generation task at the time of developing this\nwork. On ImageNet, we train an improved baseline that increases the Inception\nScore from 52.52 to 62.36 and reduces the Frechet Inception Distance from 18.65\nto 14.79. We then use DRS to further improve on this baseline, improving the\nInception Score to 76.08 and the FID to 13.75.","url_abs":"http://arxiv.org/abs/1810.06758v3","url_pdf":"http://arxiv.org/pdf/1810.06758v3.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":"discriminator-rejection-sampling","repo_url":"https://github.com/vita-epfl/collaborative-gan-sampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"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":"convolution","method_name":"Convolution"},{"method_slug":"gan-hinge-loss","method_name":"GAN Hinge Loss"},{"method_slug":"sagan","method_name":"SAGAN"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spectral-normalization","method_name":"Spectral Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.06758","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}