IEEE Signal Processing Magazine
Generative Adversarial Networks: An Overview
✓ Free legal copy found
Preprint, hosted by Cornell University (arxiv.org)
This is the authors’ own version from before peer review, so it may differ from the published paper.
Read the free PDF →Other free copies
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.
DOI: 10.1109/msp.2017.2765202 · Publisher: Institute of Electrical and Electronics Engineers (IEEE)