Semi-Supervised Adversarial Variational Autoencoder

We present a method to improve the reconstruction and generation performance of a variational autoencoder (VAE) by injecting an adversarial learning. Instead of comparing the reconstructed with the original data to calculate the reconstruction loss, we use a consistency principle for deep features....

Full description

Bibliographic Details

Published in:	Machine learning and knowledge extraction Vol. 2; no. 3; pp. 361 - 378
Main Author:	Zemouri, Ryad
Format:	Journal Article
Language:	English
Published:	MDPI 01.09.2020 MDPI AG
Subjects:	adversarial learning Artificial Intelligence Computer Science data generation deep feature consistent Machine Learning variational autoencoder data generation adversarial learning variational autoencoder deep feature consistent
ISSN:	2504-4990, 2504-4990
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!