Stacked Wasserstein Autoencoder

•A novel stacked Wasserstein autoencoder (SWAE) is proposed to approximate high-dimensional data distribution.•The transport is minimized at two stages to approximate the data space while learning the encoded latent distribution.•Experiments show that the SWAE model learns semantically meaningful la...

Full description

Bibliographic Details

Published in:	Neurocomputing (Amsterdam) Vol. 363; pp. 195 - 204
Main Authors:	Xu, Wenju, Keshmiri, Shawn, Wang, Guanghui
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 21.10.2019
Subjects:	artificial intelligence Generative adversarial network image analysis Latent space exploration learning Variational autoencoder Variational autoencoder Latent space exploration Generative adversarial network
ISSN:	0925-2312, 1872-8286
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!