Generative Adversarial Networks: An Overview

Citations Over TimeTop 1% of 2018 papers

Abstract

Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this by 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 superresolution, and classification. The aim of this review article 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.

Related Papers

• → Recent Advances in Adversarial Training for Adversarial Robustness(2021)43 cited
• → Who is Responsible for Adversarial Defense?(2021)1 cited
• → Selective Adversarial Behavior(2011)
• → 18. The Adoption of the essential features of the adversarial system(2013)
• → 7 Adversarial Experts(2001)