{"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/dna-gan-learning-disentangled-representations","title":"DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images","arxiv_id":"1711.05415","date":"2017-11-15","proceeding":"ICLR 2018 1","authors":["Taihong Xiao","Jiapeng Hong","Jinwen Ma"],"abstract":"Disentangling factors of variation has become a very challenging problem on\nrepresentation learning. Existing algorithms suffer from many limitations, such\nas unpredictable disentangling factors, poor quality of generated images from\nencodings, lack of identity information, etc. In this paper, we propose a\nsupervised learning model called DNA-GAN which tries to disentangle different\nfactors or attributes of images. The latent representations of images are\nDNA-like, in which each individual piece (of the encoding) represents an\nindependent factor of the variation. By annihilating the recessive piece and\nswapping a certain piece of one latent representation with that of the other\none, we obtain two different representations which could be decoded into two\nkinds of images with the existence of the corresponding attribute being\nchanged. In order to obtain realistic images and also disentangled\nrepresentations, we further introduce the discriminator for adversarial\ntraining. Experiments on Multi-PIE and CelebA datasets finally demonstrate that\nour proposed method is effective for factors disentangling and even overcome\ncertain limitations of the existing methods.","url_abs":"http://arxiv.org/abs/1711.05415v2","url_pdf":"http://arxiv.org/pdf/1711.05415v2.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":"dna-gan-learning-disentangled-representations","repo_url":"https://github.com/Prinsphield/DNA-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.05415","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}