Noise Dimension of GAN: An Image Compression Perspective

arXiv:2403.09196v1 Announce Type: new
Abstract: Generative adversial network (GAN) is a type of generative model that maps a high-dimensional noise to samples in target distribution. However, the dimension of noise required in GAN is not well understood. Previous approaches view GAN as a mapping from a continuous distribution to another continous distribution. In this paper, we propose to view GAN as a discrete sampler instead. From this perspective, we build a connection between the minimum noise required and the bits …

abstract arxiv compression continuous cs.cv distribution gan generative however image mapping maps network noise perspective samples type view