A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

TL;DR

This paper provides a comprehensive review of GANs, covering their algorithms, theoretical foundations, and diverse applications across multiple fields, highlighting connections, evolution, and future research directions.

Contribution

It offers an integrated overview of GAN variants, their theoretical issues, and applications, filling gaps in understanding their relationships and development.

Findings

Analyzed connections among GAN variants

Summarized theoretical challenges in GANs

Reviewed diverse applications in multiple domains

Abstract

Generative adversarial networks (GANs) are a hot research topic recently. GANs have been widely studied since 2014, and a large number of algorithms have been proposed. However, there is few comprehensive study explaining the connections among different GANs variants, and how they have evolved. In this paper, we attempt to provide a review on various GANs methods from the perspectives of algorithms, theory, and applications. Firstly, the motivations, mathematical representations, and structure of most GANs algorithms are introduced in details. Furthermore, GANs have been combined with other machine learning algorithms for specific applications, such as semi-supervised learning, transfer learning, and reinforcement learning. This paper compares the commonalities and differences of these GANs methods. Secondly, theoretical issues related to GANs are investigated. Thirdly, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, medical field, and data science are illustrated. Finally, the future open research problems for GANs are pointed out.