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....
Na minha lista:
| Autor principal: | |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
MDPI AG
2020-09-01
|
| coleção: | Machine Learning and Knowledge Extraction |
| Assuntos: | |
| Acesso em linha: | https://www.mdpi.com/2504-4990/2/3/20 |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|