Improving The Improved Training Of Wasserstein Gans: A Consistency Term And Its Dual Effect
Abstract
Despite being impactful on a variety of problems and applications, the generative adversarial nets (GANs) are remarkably difficult to train. This issue is formally analyzed by Arjovsky & Bottou (2017), who also propose an alternative direction to avoid the caveats in the minmax two-player training of GANs. The corresponding algorithm, called Wasserstein GAN (WGAN), hinges on the 1-Lipschitz continuity of the discriminator. In this paper, we propose a novel approach to enforcing the Lipschitz continuity in the training procedure of WGANs. Our approach seamlessly connects WGAN with one of the recent semi-supervised learning methods. As a result, it gives rise to not only better photo-realistic samples than the previous methods but also state-of-the-art semi-supervised learning results. In particular, our approach gives rise to the inception score of more than 5.0 with only 1,000 CIFAR-10 images and is the first that exceeds the accuracy of 90% on the CIFAR-10 dataset using only 4,000 labeled images, to the best of our knowledge.
Publication Date
1-1-2018
Publication Title
6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings
Volume
2018-April
Number of Pages
1-17
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
85076815442 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85076815442
STARS Citation
Wei, Xiang; Gong, Boqing; Liu, Zixia; Lu, Wei; and Wang, Liqiang, "Improving The Improved Training Of Wasserstein Gans: A Consistency Term And Its Dual Effect" (2018). Scopus Export 2015-2019. 7590.
https://stars.library.ucf.edu/scopus2015/7590