A Survey on Generative Adversarial Networks: Variants, Applications, and Training
Preprint
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.Keywords
All Related Versions
This publication has 47 references indexed in Scilit:
- Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN2022
- DRIT++: Diverse Image-to-Image Translation via Disentangled RepresentationsInternational Journal of Computer Vision, 2020
- GlyphGAN: Style-consistent font generation based on generative adversarial networksKnowledge-Based Systems, 2019
- Loss-Sensitive Generative Adversarial Networks on Lipschitz DensitiesInternational Journal of Computer Vision, 2019
- Can adversarial networks hallucinate occluded people with a plausible aspect?Computer Vision and Image Understanding, 2019
- Auto-painter: Cartoon image generation from sketch by using conditional Wasserstein generative adversarial networksNeurocomputing, 2018
- Zero-day malware detection using transferred generative adversarial networks based on deep autoencodersInformation Sciences, 2018
- SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image SegmentationNeuroinformatics, 2018
- Guiding InfoGAN with Semi-supervision2017
- Multi-scale multi-class conditional generative adversarial network for handwritten character generationThe Journal of Supercomputing, 2017