{"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/deligan-generative-adversarial-networks-for","title":"DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data","arxiv_id":"1706.02071","date":"2017-06-07","proceeding":"CVPR 2017 7","authors":["Swaminathan Gurumurthy","Ravi Kiran Sarvadevabhatla","Venkatesh Babu Radhakrishnan"],"abstract":"A class of recent approaches for generating images, called Generative\nAdversarial Networks (GAN), have been used to generate impressively realistic\nimages of objects, bedrooms, handwritten digits and a variety of other image\nmodalities. However, typical GAN-based approaches require large amounts of\ntraining data to capture the diversity across the image modality. In this\npaper, we propose DeLiGAN -- a novel GAN-based architecture for diverse and\nlimited training data scenarios. In our approach, we reparameterize the latent\ngenerative space as a mixture model and learn the mixture model's parameters\nalong with those of GAN. This seemingly simple modification to the GAN\nframework is surprisingly effective and results in models which enable\ndiversity in generated samples although trained with limited data. In our work,\nwe show that DeLiGAN can generate images of handwritten digits, objects and\nhand-drawn sketches, all using limited amounts of data. To quantitatively\ncharacterize intra-class diversity of generated samples, we also introduce a\nmodified version of \"inception-score\", a measure which has been found to\ncorrelate well with human assessment of generated samples.","url_abs":"http://arxiv.org/abs/1706.02071v1","url_pdf":"http://arxiv.org/pdf/1706.02071v1.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":"deligan-generative-adversarial-networks-for","repo_url":"https://github.com/RAF96/ifmo-2019-deep-learning-coursework","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deligan-generative-adversarial-networks-for","repo_url":"https://github.com/val-iisc/deligan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.02071","atlas_url":"https://app.syntology.ai/?focus=1706.02071","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}