Perturbative GAN: GAN with Perturbation Layers
Abstract
Perturbative GAN, which replaces convolution layers of existing convolutional GANs (DCGAN, WGAN-GP, BIGGAN, etc.) with perturbation layers that adds a fixed noise mask, is proposed. Compared with the convolu-tional GANs, the number of parameters to be trained is smaller, the convergence of training is faster, the incep-tion score of generated images is higher, and the overall training cost is reduced. Algorithmic generation of the noise masks is also proposed, with which the training, as well as the generation, can be boosted with hardware acceleration. Perturbative GAN is evaluated using con-ventional datasets (CIFAR10, LSUN, ImageNet), both in the cases when a perturbation layer is adopted only for Generators and when it is introduced to both Generator and Discriminator.
Cite
@article{arxiv.1902.01514,
title = {Perturbative GAN: GAN with Perturbation Layers},
author = {Yuma Kishi and Tsutomu Ikegami and Shin-ichi O'uchi and Ryousei Takano and Wakana Nogami and Tomohiro Kudoh},
journal= {arXiv preprint arXiv:1902.01514},
year = {2019}
}