Next Article in Journal
Crack Propagation on the Surface of the Bottleneck of a Pressure Vessel Considering the Initial Crack Angle
Previous Article in Journal
Exploring the Strategy of Fusing Sucrose Synthase to Glycosyltransferase UGT76G1 in Enzymatic Biotransformation
 
 
Article

Express Construction for GANs from Latent Representation to Data Distribution

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editors: Andrea Prati, Luis Javier García Villalba and Vincent A. Cicirello
Appl. Sci. 2022, 12(8), 3910; https://doi.org/10.3390/app12083910
Received: 14 March 2022 / Revised: 7 April 2022 / Accepted: 10 April 2022 / Published: 13 April 2022
(This article belongs to the Topic Machine and Deep Learning)
Generative Adversarial Networks (GANs) are powerful generative models for numerous tasks and datasets. However, most of the existing models suffer from mode collapse. The most recent research indicates that the reason for it is that the optimal transportation map from random noise to the data distribution is discontinuous, but deep neural networks (DNNs) can only approximate continuous ones. Instead, the latent representation is a better raw material used to construct a transportation map point to the data distribution than random noise. Because it is a low-dimensional mapping related to the data distribution, the construction procedure seems more like expansion rather than starting all over. Besides, we can also search for more transportation maps in this way with smoother transformation. Thus, we have proposed a new training methodology for GANs in this paper to search for more transportation maps and speed the training up, named Express Construction. The key idea is to train GANs with two independent phases for successively yielding latent representation and data distribution. To this end, an Auto-Encoder is trained to map the real data into the latent space, and two couples of generators and discriminators are used to produce them. To the best of our knowledge, we are the first to decompose the training procedure of GAN models into two more uncomplicated phases, thus tackling the mode collapse problem without much more computational cost. We also provide theoretical steps toward understanding the training dynamics of this procedure and prove assumptions. No extra hyper-parameters have been used in the proposed method, which indicates that Express Construction can be used to train any GAN models. Extensive experiments are conducted to verify the performance of realistic image generation and the resistance to mode collapse. The results show that the proposed method is lightweight, effective, and less prone to mode collapse. View Full-Text
Keywords: generative adversarial networks; mode collapse; transportation maps; latent representation; express construction generative adversarial networks; mode collapse; transportation maps; latent representation; express construction
Show Figures

Figure 1

MDPI and ACS Style

Liu, M.; Deng, J.; Yang, M.; Cheng, X.; Xie, T.; Deng, P.; Wang, X.; Liu, M. Express Construction for GANs from Latent Representation to Data Distribution. Appl. Sci. 2022, 12, 3910. https://doi.org/10.3390/app12083910

AMA Style

Liu M, Deng J, Yang M, Cheng X, Xie T, Deng P, Wang X, Liu M. Express Construction for GANs from Latent Representation to Data Distribution. Applied Sciences. 2022; 12(8):3910. https://doi.org/10.3390/app12083910

Chicago/Turabian Style

Liu, Minghui, Jiali Deng, Meiyi Yang, Xuan Cheng, Tianshu Xie, Pan Deng, Xiaomin Wang, and Ming Liu. 2022. "Express Construction for GANs from Latent Representation to Data Distribution" Applied Sciences 12, no. 8: 3910. https://doi.org/10.3390/app12083910

Find Other Styles
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
Back to TopTop