Extensive review and comparison of CNN and GAN

Carlos Martinez 1, * and Nicole Robinson 2

1 Vision and Learning Lab, University of Texas at Austin, USA.
2 Department of Computer Science, Princeton University, USA.
 
Research Article
World Journal of Advanced Engineering Technology and Sciences, 2024, 13(02), 854-869.
Article DOI: 10.30574/wjaets.2024.13.2.0559
Publication history: 
Received on 08 October 2024; revised on 21 December 2024; accepted on 25 December 2024
 
Abstract: 
CNNs and GANs, together and separately, achieve groundbreaking developments in artificial intelligence while they play prominent roles as deep learning structures. This document is a rather extensive overview and side-by-side analysis of CNNs and GANs and their back-end architectures and workings, as well as their advantages and disadvantages and uses in practice. Convolutional Neural Networks (CNNs), known for their outstanding feature extraction capabilities, have greatly boosted up the scope of image classification, object detection, and medical diagnostics; Generative Adversarial Networks (GANs) have brought a new generalized approach to generative modelling, generating extremely realistic images, videos, and data. This analysis highlights significant differences in the training of CNNs and GANs, intricacy of the latter two’s architectures, and metrics used to measure performance, as well as recurrent challenges such as overfitting in CNNs and instability in GANs. Furthermore, the paper explores how these models can be coupled to form hybrid systems and perform better in such applications as data augmentation and image translation. This paper will attempt to provide an in-depth review of these models to give researchers and practitioners a clear spectacle to use these models across various applications and determine areas that future research can be directed.
 
Keywords: 
Convolutional Neural Networks (CNN); Generative Adversarial Networks (GAN); Deep Learning Architectures; Image Processing, Model Comparison; Artificial Intelligence Applications
 
Full text article in PDF: 

Click here

 
Copyright information: 
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0