Unrealistic Feature Suppression for Generative Adversarial Networks
This work addresses training stability and image quality issues in GANs for researchers and practitioners, but it is incremental as it builds on existing sampling approaches.
The paper tackles the challenge of improving GAN performance by proposing an unrealistic feature suppression (UFS) module that maintains high-quality features while suppressing unrealistic ones, achieving better Frechet inception distance and inception scores across models like WGAN-GP, SNGAN, and BigGAN.
Due to the unstable nature of minimax game between generator and discriminator, improving the performance of GANs is a challenging task. Recent studies have shown that selected high-quality samples in training improve the performance of GANs. However, sampling approaches which discard samples show limitations in some aspects such as the speed of training and optimality of the networks. In this paper we propose unrealistic feature suppression (UFS) module that keeps high-quality features and suppresses unrealistic features. UFS module keeps the training stability of networks and improves the quality of generated images. We demonstrate the effectiveness of UFS module on various models such as WGAN-GP, SNGAN, and BigGAN. By using UFS module, we achieved better Frechet inception distance and inception score compared to various baseline models. We also visualize how effectively our UFS module suppresses unrealistic features through class activation maps.