CVLGMLMar 5, 2018

Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect

arXiv:1803.01541v1280 citations
Originality Incremental advance
AI Analysis

This addresses the problem of training instability in GANs for researchers and practitioners, offering incremental improvements by integrating semi-supervised learning techniques.

The paper tackles the training instability of Wasserstein GANs by introducing a novel consistency term to enforce Lipschitz continuity, resulting in improved photo-realistic samples and state-of-the-art semi-supervised learning performance, including an inception score over 5.0 with 1,000 CIFAR-10 images and over 90% accuracy with 4,000 labeled images.

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 \cite{arjovsky2017towards}, 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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes