Improving the Fairness of the Min-Max Game in GANs Training

Generative adversarial networks (GANs) have achieved great success and become more and more popular in recent years. However, understanding of the min-max game in GANs training is still limited. In this paper, we first utilize information game theory to analyze the min-max game in GANs and introduce a new viewpoint on the GANs training that the min-max game in existing GANs is unfair during training, leading to sub-optimal convergence. To tackle this, we propose a novel GAN called Information Gap GAN (IGGAN), which consists of one generator (G) and two discriminators (D 1 and D 2 ). Specifically, we apply different data augmentation methods to D 1 and D 2 , respectively. The information gap between different data augmentation methods can change the information received by each player in the min-max game and lead to all three players G, D 1 and D 2 in IGGAN obtaining incomplete information, which improves the fairness of the min-max game, yielding better convergence. We conduct extensive experiments for large-scale and limited data settings on several common datasets with two backbones, i.e., BigGAN and StyleGAN2. The results demonstrate that IGGAN can achieve a higher Inception Score (IS) and a lower Fréchet Inception Distance (FID) compared with other GANs. Codes are available at https://github.com/zzhang05/IGGAN