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.
翻译:由于产生者和歧视者之间小型游戏的不稳定性,改进GANs的性能是一项具有挑战性的任务,最近的研究表明,培训中选定的高质量样品提高了GANs的性能,然而,丢弃样品的采样方法在某些方面显示出局限性,例如培训速度和网络的最佳性能,在本文件中,我们提出了不切实际的特性抑制模块,以保持高质量的特性和抑制不现实的特性。UFS模块保持网络的培训稳定性,提高生成图像的质量。我们展示了诸如WGAN-GP、SNGAN和BIGAN等各种模型的UFS模块的有效性。我们通过使用UFS模块,实现了与各种基线模型相比更好的Frechet起始距离和起始分数。我们还设想了我们的UFS模块通过课堂激活图如何有效地压制不切实际的特性。