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....
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
MDPI AG
2020-09-01
|
| Serie: | Machine Learning and Knowledge Extraction |
| Soggetti: | |
| Accesso online: | https://www.mdpi.com/2504-4990/2/3/20 |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|