{"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/mixture-density-generative-adversarial","title":"Mixture Density Generative Adversarial Networks","arxiv_id":"1811.00152","date":"2018-10-31","proceeding":"CVPR 2019 6","authors":["Hamid Eghbal-zadeh","Werner Zellinger","Gerhard Widmer"],"abstract":"Generative Adversarial Networks have surprising ability for generating sharp\nand realistic images, though they are known to suffer from the so-called mode\ncollapse problem. In this paper, we propose a new GAN variant called Mixture\nDensity GAN that while being capable of generating high-quality images,\novercomes this problem by encouraging the Discriminator to form clusters in its\nembedding space, which in turn leads the Generator to exploit these and\ndiscover different modes in the data. This is achieved by positioning Gaussian\ndensity functions in the corners of a simplex, using the resulting Gaussian\nmixture as a likelihood function over discriminator embeddings, and formulating\nan objective function for GAN training that is based on these likelihoods. We\ndemonstrate empirically (1) the quality of the generated images in Mixture\nDensity GAN and their strong similarity to real images, as measured by the\nFr\\'echet Inception Distance (FID), which compares very favourably with\nstate-of-the-art methods, and (2) the ability to avoid mode collapse and\ndiscover all data modes.","url_abs":"http://arxiv.org/abs/1811.00152v2","url_pdf":"http://arxiv.org/pdf/1811.00152v2.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":"mixture-density-generative-adversarial","repo_url":"https://github.com/eghbalz/mdgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.00152","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}