Generative Adversarial Networks: An Overview
Why is this work in the frame?
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
The record
- Venue
- IEEE Signal Processing Magazine
- Topic
- Generative Adversarial Networks and Image Synthesis
- Field
- Computer Science
- Canadian institutions
- Université de MontréalConcordia University
- Funders
- Victoria University of WellingtonImperial College LondonUniversity of GeorgiaEngineering and Physical Sciences Research CouncilMassachusetts Institute of Technology
- Keywords
- Computer scienceGenerative grammarAdversarial systemArtificial intelligenceVariety (cybernetics)Process (computing)Image (mathematics)Point (geometry)Machine learning
- Has abstract in OpenAlex
- yes