Face Aging With Boundary Equilibrium Conditional Autoencoder

Since generative adversarial networks (GANs) were proposed in 2014, mode collapse has been a problem that affects many researchers when training GANs. With the reconstruction loss of an autoencoder, conditional adversarial autoencoder (CAAE) is free from mode collapse. However, its reconstruction lo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access Vol. 6; pp. 54834 - 54843
Main Authors: Chen, Longxiang, Hu, Xiaolong, Zhang, Zuping
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.01.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
autoencoder
boundary equilibrium
Coders
Face aging
generative adversarial networks
Image quality
Image reconstruction
non-convergence
Saturation
saturation problem
ISSN:2169-3536, 2169-3536
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Since generative adversarial networks (GANs) were proposed in 2014, mode collapse has been a problem that affects many researchers when training GANs. With the reconstruction loss of an autoencoder, conditional adversarial autoencoder (CAAE) is free from mode collapse. However, its reconstruction loss will bring a saturation problem, in which the encoder maps every input image into just one latent variable. Combining the CAAE with a boundary equilibrium generative adversarial network, we propose a boundary equilibrium conditional autoencoder (BECAE) focusing on the face aging task. Our model is the first GANs that renders images through a discriminator. We also introduce some statistics to measure the level of the saturation problem. The results show that the BECAE has successfully solved the saturation problem and can generate face images of the same quality as the images generated by the CAAE.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2018.2870150