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....

Celý popis

Podrobná bibliografia

Vydané v:	Machine learning and knowledge extraction Ročník 2; číslo 3; s. 361 - 378
Hlavný autor:	Zemouri, Ryad
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	MDPI 01.09.2020 MDPI AG
Predmet:	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
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!