Improving the Speed and Quality of GAN by Adversarial Training

Abstract

Generative adversarial networks (GAN) have shown remarkable results in image generation tasks. High fidelity class-conditional GAN methods often rely on stabilization techniques by constraining the global Lipschitz continuity. Such regularization leads to less expressive models and slower convergence speed; other techniques, such as the large batch training, require unconventional computing power and are not widely accessible. In this paper, we develop an efficient algorithm, namely FastGAN (Free AdverSarial Training), to improve the speed and quality of GAN training based on the adversarial training technique. We benchmark our method on CIFAR10, a subset of ImageNet, and the full ImageNet datasets. We choose strong baselines such as SNGAN and SAGAN; the results demonstrate that our training algorithm can achieve better generation quality (in terms of the Inception score and Frechet Inception distance) with less overall training time. Most notably, our training algorithm brings ImageNet training to the broader public by requiring 2-4 GPUs.

References in corpus (8)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Self-Attention Generative Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• The Numerics of GANs
• On the Convergence and Robustness of Training GANs with Regularized Optimal Transport
• LOGAN: Latent Optimisation for Generative Adversarial Networks
• Lipschitz Generative Adversarial Nets

Cited by in corpus (4)

• RobustBench: a standardized adversarial robustness benchmark
• Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• Deblending Galaxies with Generative Adversarial Networks