Next Article in Journal
A Survey of Planning and Learning in Games
Previous Article in Journal
Vitamin D3 and Dental Mesenchymal Stromal Cells
Previous Article in Special Issue
Towards a Better Understanding of Transfer Learning for Medical Imaging: A Case Study
Open AccessArticle

Improvement of Learning Stability of Generative Adversarial Network Using Variational Learning

Department of Computer Science and Engineering, Dankook University, Yongin-si, Gyeonggi-do 16890, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(13), 4528; https://doi.org/10.3390/app10134528
Received: 14 May 2020 / Revised: 23 June 2020 / Accepted: 26 June 2020 / Published: 30 June 2020
(This article belongs to the Special Issue Deep Learning Applied to Image Processing)
In this paper, we propose a new network model using variational learning to improve the learning stability of generative adversarial networks (GAN). The proposed method can be easily applied to improve the learning stability of GAN-based models that were developed for various purposes, given that the variational autoencoder (VAE) is used as a secondary network while the basic GAN structure is maintained. When the gradient of the generator vanishes in the learning process of GAN, the proposed method receives gradient information from the decoder of the VAE that maintains gradient stably, so that the learning processes of the generator and discriminator are not halted. The experimental results of the MNIST and the CelebA datasets verify that the proposed method improves the learning stability of the networks by overcoming the vanishing gradient problem of the generator, and maintains the excellent data quality of the conventional GAN-based generative models. View Full-Text
Keywords: deep generative model; generative adversarial networks; variational learning; learning stability; variational autoencoder deep generative model; generative adversarial networks; variational learning; learning stability; variational autoencoder
Show Figures

Figure 1

MDPI and ACS Style

Lee, J.-Y.; Choi , S.-I. Improvement of Learning Stability of Generative Adversarial Network Using Variational Learning. Appl. Sci. 2020, 10, 4528.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop