A Survey on Generative Adversarial Networks: Variants, Applications, and Training

TL;DR

This survey reviews the development, applications, and training challenges of Generative Adversarial Networks (GANs), highlighting solutions for stable training and future research directions.

Contribution

It provides a comprehensive overview of GAN variants, their applications, and recent training stabilization techniques, offering insights into ongoing challenges and future research.

Findings

Analysis of classical and modified GAN models

Survey of GAN applications across domains

Discussion of training obstacles and stabilization methods

Abstract

The Generative Models have gained considerable attention in the field of unsupervised learning via a new and practical framework called Generative Adversarial Networks (GAN) due to its outstanding data generation capability. Many models of GAN have proposed, and several practical applications emerged in various domains of computer vision and machine learning. Despite GAN's excellent success, there are still obstacles to stable training. The problems are due to Nash-equilibrium, internal covariate shift, mode collapse, vanishing gradient, and lack of proper evaluation metrics. Therefore, stable training is a crucial issue in different applications for the success of GAN. Herein, we survey several training solutions proposed by different researchers to stabilize GAN training. We survey, (I) the original GAN model and its modified classical versions, (II) detail analysis of various GAN applications in different domains, (III) detail study about the various GAN training obstacles as well as training solutions. Finally, we discuss several new issues as well as research outlines to the topic.