A Survey on Generative Adversarial Networks: Variants, Applications, and Training
By Abdul Jabbar, Xi Li, Bourahla Omar. ACM Computing Surveys, 2020
364 citations recorded by the source corpus.
The Generative Models have gained considerable attention in unsupervised learning via a new and practical framework called Generative Adversarial Networks (GAN) due to their outstanding data generation capability. Many GAN models have been proposed, and several practical applications have emerged in various domains of computer vision and machine learning. Despite GANs excellent success, there are still obstacles to stable training. The problems are 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 GANs. Herein, we survey several training solutions proposed by different researchers to stabilize GAN training. We discuss (I) the original GAN model and its modified versions, (II) a detailed analysis of various GAN applications in different domains, and (III) a detailed study about the various GAN training obstacles as well as training solutions. Finally, we reveal several issues as well as research outlines to the topic.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/d54d8c402785006faaf5de19e81f04eb484a3aa2
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Thinagaran Perumal
- Norwati Mustapha
- Divya Saxena
- Jiannong Cao
- In-So Kweon
- Chaoning Zhang
- Raihani Mohamed
- Chenshuang Zhang
In Computer Vision and Pattern Recognition
- Thinagaran Perumal
- Norwati Mustapha
- Divya Saxena
- Jiannong Cao
- In-So Kweon
- Chaoning Zhang
- Raihani Mohamed
- Chenshuang Zhang
Citations in the corpus
- Text-to-image Diffusion Models in Generative AI: A Survey (2023, background): “Despite the progress of GAN-based painting [106], they suffer from the unstable training and model collapse problem brought by GAN.”
- Generative Adversarial Networks (GANs) (2020, background): “References [21, 22], and [23] provided a brief overview of some GANs models and their applications.”
- A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU (2023, background): “The ultimate goal of generative models is to generate data samples that closely resemble real data distribution [47].”