How Generative Adversarial Networks and Their Variants Work: An Overview

TL;DR

This paper provides a comprehensive overview of Generative Adversarial Networks (GANs), explaining their operation, objective functions, variants, and applications across multiple fields for readers seeking a deeper understanding.

Contribution

It offers an in-depth explanation of GAN mechanisms, objective functions, and their variants, including how they integrate with autoencoders, for researchers and practitioners.

Findings

GANs can generate high-quality, real-like samples from complex data distributions.

Various GAN variants are applicable to diverse tasks and fields.

Understanding GAN fundamentals aids in effective application and development.

Abstract

Generative Adversarial Networks (GAN) have received wide attention in the machine learning field for their potential to learn high-dimensional, complex real data distribution. Specifically, they do not rely on any assumptions about the distribution and can generate real-like samples from latent space in a simple manner. This powerful property leads GAN to be applied to various applications such as image synthesis, image attribute editing, image translation, domain adaptation and other academic fields. In this paper, we aim to discuss the details of GAN for those readers who are familiar with, but do not comprehend GAN deeply or who wish to view GAN from various perspectives. In addition, we explain how GAN operates and the fundamental meaning of various objective functions that have been suggested recently. We then focus on how the GAN can be combined with an autoencoder framework. Finally, we enumerate the GAN variants that are applied to various tasks and other fields for those who are interested in exploiting GAN for their research.