Generative adversarial network (GAN) is a framework for generating fake data using a set of real examples. However, GAN is unstable in the training stage. In order to stabilize GANs, the noise injection has been used to enlarge the overlap of the real and fake distributions at the cost of increasing variance. The diffusion (or smoothing) may reduce the intrinsic underlying dimensionality of data but it suppresses the capability of GANs to learn high-frequency information in the training procedure. Based on these observations, we propose a data representation for the GAN training, called noisy scale-space (NSS), that recursively applies the smoothing with a balanced noise to data in order to replace the high-frequency information by random data, leading to a coarse-to-fine training of GANs. We experiment with NSS using DCGAN and StyleGAN2 based on benchmark datasets in which the NSS-based GANs outperforms the state-of-the-arts in most cases.
翻译:生成对抗性网络(GAN)是使用一套真实实例生成假数据的框架。然而,GAN在培训阶段不稳定。为了稳定GANs,注入噪音是为了扩大真实和假分布的重叠,而以差异增加为代价。传播(或平滑)可能减少数据内在的基本维度,但抑制了GANs在培训过程中学习高频信息的能力。根据这些观察,我们提议GAN培训(称为超音速比例空间(NSS))的数据代表,该代表将平衡的噪音反复应用于数据,以便用随机数据取代高频信息,从而导致GANs的粗略到纯度培训。我们根据基准数据集与NSS进行实验,以DCGAN和SysteleGAN2为基础,以NSGANs为基础的GANs在多数情况下超越了最新艺术。