{"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/high-resolution-deep-convolutional-generative","title":"High-Resolution Deep Convolutional Generative Adversarial Networks","arxiv_id":"1711.06491","date":"2017-11-17","proceeding":null,"authors":["Joachim D. Curtó","Irene C. Zarza","Fernando de la Torre","Irwin King","Michael R. Lyu"],"abstract":"Generative Adversarial Networks (GANs) convergence in a high-resolution\nsetting with a computational constrain of GPU memory capacity (from 12GB to 24\nGB) has been beset with difficulty due to the known lack of convergence rate\nstability. In order to boost network convergence of DCGAN (Deep Convolutional\nGenerative Adversarial Networks) and achieve good-looking high-resolution\nresults we propose a new layered network structure, HDCGAN, that incorporates\ncurrent state-of-the-art techniques for this effect. A novel dataset, Curt\\'o &\nZarza, containing human faces from different ethnical groups in a wide variety\nof illumination conditions and image resolutions is introduced. Curt\\'o is\nenhanced with HDCGAN synthetic images, thus being the first GAN augmented face\ndataset. We conduct extensive experiments on CelebA (MS-SSIM 0.1978 and\nDistance of Fr\\'echet 8.77) and Curt\\'o.","url_abs":"http://arxiv.org/abs/1711.06491v12","url_pdf":"http://arxiv.org/pdf/1711.06491v12.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":"high-resolution-deep-convolutional-generative","repo_url":"https://github.com/curto2/c","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"ms-ssim","task_name":"MS-SSIM"},{"task_slug":"ssim","task_name":"SSIM"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dcgan","method_name":"DCGAN"},{"method_slug":"hdcgan","method_name":"HDCGAN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"c-and-z","name":"C&Z","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-celeba-128x128","task":"Image Generation","dataset":"CelebA 128x128","model":"HDCGAN","rank_in_archive_order":5,"of":5,"metrics":{"MS-SSIM":"0.1978"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-64x64","task":"Image Generation","dataset":"CelebA 64x64","model":"HDCGAN","rank_in_archive_order":25,"of":39,"metrics":{"FID":"8.44"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}