Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image synthesis, semantic image editing, style transfer, image super-resolution and classification. The aim of this review paper is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible. In addition to identifying different methods for training and constructing GANs, we also point to remaining challenges in their theory and application.
@article{arxiv.1710.07035,
title = {Generative Adversarial Networks: An Overview},
author = {Antonia Creswell and Tom White and Vincent Dumoulin and Kai Arulkumaran and Biswa Sengupta and Anil A Bharath},
journal= {arXiv preprint arXiv:1710.07035},
year = {2018}
}
Comments
Accepted in the IEEE Signal Processing Magazine Special Issue on Deep Learning for Visual Understanding