Comparative Study on Generative Adversarial Networks

TL;DR

This paper provides a comparative analysis of the original Generative Adversarial Network model and its recent modifications, highlighting advancements in generative models for computer vision.

Contribution

It offers a systematic comparison of GAN variants, summarizing their differences and performance improvements over the original framework.

Findings

Original GAN and variants analyzed

Performance differences summarized

Guidelines for selecting GAN models provided

Abstract

In recent years, there have been tremendous advancements in the field of machine learning. These advancements have been made through both academic as well as industrial research. Lately, a fair amount of research has been dedicated to the usage of generative models in the field of computer vision and image classification. These generative models have been popularized through a new framework called Generative Adversarial Networks. Moreover, many modified versions of this framework have been proposed in the last two years. We study the original model proposed by Goodfellow et al. as well as modifications over the original model and provide a comparative analysis of these models.