{"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/guiding-infogan-with-semi-supervision","title":"Guiding InfoGAN with Semi-Supervision","arxiv_id":"1707.04487","date":"2017-07-14","proceeding":null,"authors":["Adrian Spurr","Emre Aksan","Otmar Hilliges"],"abstract":"In this paper we propose a new semi-supervised GAN architecture (ss-InfoGAN)\nfor image synthesis that leverages information from few labels (as little as\n0.22%, max. 10% of the dataset) to learn semantically meaningful and\ncontrollable data representations where latent variables correspond to label\ncategories. The architecture builds on Information Maximizing Generative\nAdversarial Networks (InfoGAN) and is shown to learn both continuous and\ncategorical codes and achieves higher quality of synthetic samples compared to\nfully unsupervised settings. Furthermore, we show that using small amounts of\nlabeled data speeds-up training convergence. The architecture maintains the\nability to disentangle latent variables for which no labels are available.\nFinally, we contribute an information-theoretic reasoning on how introducing\nsemi-supervision increases mutual information between synthetic and real data.","url_abs":"http://arxiv.org/abs/1707.04487v1","url_pdf":"http://arxiv.org/pdf/1707.04487v1.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":"guiding-infogan-with-semi-supervision","repo_url":"https://github.com/spurra/ss-infogan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"guiding-infogan-with-semi-supervision","repo_url":"https://github.com/Mmhmmmmm/ss-infogan-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1707.04487","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}