{"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/diverse-conditional-image-generation-by","title":"Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes","arxiv_id":"1808.01121","date":"2018-08-03","proceeding":"ECCV 2018 9","authors":["Yang He","Bernt Schiele","Mario Fritz"],"abstract":"Recent advances in Deep Learning and probabilistic modeling have led to\nstrong improvements in generative models for images. On the one hand,\nGenerative Adversarial Networks (GANs) have contributed a highly effective\nadversarial learning procedure, but still suffer from stability issues. On the\nother hand, Conditional Variational Auto-Encoders (CVAE) models provide a sound\nway of conditional modeling but suffer from mode-mixing issues. Therefore,\nrecent work has turned back to simple and stable regression models that are\neffective at generation but give up on the sampling mechanism and the latent\ncode representation. We propose a novel and efficient stochastic regression\napproach with latent drop-out codes that combines the merits of both lines of\nresearch. In addition, a new training objective increases coverage of the\ntraining distribution leading to improvements over the state of the art in\nterms of accuracy as well as diversity.","url_abs":"http://arxiv.org/abs/1808.01121v1","url_pdf":"http://arxiv.org/pdf/1808.01121v1.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":"diverse-conditional-image-generation-by","repo_url":"https://github.com/SSAW14/Image_Generation_with_Latent_Code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}