{"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/improved-artgan-for-conditional-synthesis-of","title":"Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork","arxiv_id":"1708.09533","date":"2017-08-31","proceeding":null,"authors":["Wei Ren Tan","Chee Seng Chan","Hernan Aguirre","Kiyoshi Tanaka"],"abstract":"This paper proposes a series of new approaches to improve Generative\nAdversarial Network (GAN) for conditional image synthesis and we name the\nproposed model as ArtGAN. One of the key innovation of ArtGAN is that, the\ngradient of the loss function w.r.t. the label (randomly assigned to each\ngenerated image) is back-propagated from the categorical discriminator to the\ngenerator. With the feedback from the label information, the generator is able\nto learn more efficiently and generate image with better quality. Inspired by\nrecent works, an autoencoder is incorporated into the categorical discriminator\nfor additional complementary information. Last but not least, we introduce a\nnovel strategy to improve the image quality. In the experiments, we evaluate\nArtGAN on CIFAR-10 and STL-10 via ablation studies. The empirical results\nshowed that our proposed model outperforms the state-of-the-art results on\nCIFAR-10 in terms of Inception score. Qualitatively, we demonstrate that ArtGAN\nis able to generate plausible-looking images on Oxford-102 and CUB-200, as well\nas able to draw realistic artworks based on style, artist, and genre. The\nsource code and models are available at: https://github.com/cs-chan/ArtGAN","url_abs":"http://arxiv.org/abs/1708.09533v2","url_pdf":"http://arxiv.org/pdf/1708.09533v2.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":"improved-artgan-for-conditional-synthesis-of","repo_url":"https://github.com/cs-chan/ArtGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"improved-artgan-for-conditional-synthesis-of","repo_url":"https://github.com/cs-chan/Artwork-Synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}