Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork

Tan, Wei Ren and Chan, Chee Seng and Aguirre, Hernan E. and Tanaka, Kiyoshi (2019) Improved ArtGAN for Conditional Synthesis of Natural Image and Artwork. IEEE Transactions on Image Processing, 28 (1). pp. 394-409. ISSN 1057-7149, DOI

Full text not available from this repository.
Official URL:


This paper proposes a series of new approaches to improve generative adversarial network (GAN) for conditional image synthesis and we name the proposed model as 'ArtGAN. ' One of the key innovation of ArtGAN is that, the gradient of the loss function w.r.t. the label (randomly assigned to each generated image) is back-propagated from the categorical discriminator to the generator. With the feedback from the label information, the generator is able to learn more efficiently and generate image with better quality. Inspired by recent works, an autoencoder is incorporated into the categorical discriminator for additional complementary information. Last but not least, we introduce a novel strategy to improve the image quality. In the experiments, we evaluate ArtGAN on CIFAR-10 and STL-10 via ablation studies. The empirical results showed that our proposed model outperforms the state-of-the-art results on CIFAR-10 in terms of Inception score. Qualitatively, we demonstrate that ArtGAN is able to generate plausible-looking images on Oxford-102 and CUB-200, as well as able to draw realistic artworks based on style, artist, and genre. The source code and models are available at:

Item Type: Article
Funders: Fundamental Research Grant Scheme (FRGS) MoHE from the Ministry of Education Malaysia under Grant FP004-2016, UM Frontier Research from University of Malaya under Grant FG002-17AFR
Uncontrolled Keywords: ArtGAN; artwork synthesis; deep learning; Generative adversarial networks; image synthesis
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Computer Science & Information Technology
Depositing User: Ms. Juhaida Abd Rahim
Date Deposited: 27 Feb 2019 02:20
Last Modified: 27 Feb 2019 02:20

Actions (login required)

View Item View Item