Autoencoder and Partially Impossible Reconstruction Losses

The generally unsupervised nature of autoencoder models implies that the main training metric is formulated as the error between input images and their corresponding reconstructions. Different reconstruction loss variations and latent space regularizations have been shown to improve model performanc...

Descripción completa

Detalles Bibliográficos
Autores principales: Dias Da Cruz, Steve, Taetz, Bertram, Stifter, Thomas, Stricker, Didier
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9268944/
https://www.ncbi.nlm.nih.gov/pubmed/35808357
http://dx.doi.org/10.3390/s22134862

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9268944/
https://www.ncbi.nlm.nih.gov/pubmed/35808357
http://dx.doi.org/10.3390/s22134862

Ejemplares similares