Co-Training for Visual Object Recognition Based on Self-Supervised Models Using a Cross-Entropy Regularization

Automatic recognition of visual objects using a deep learning approach has been successfully applied to multiple areas. However, deep learning techniques require a large amount of labeled data, which is usually expensive to obtain. An alternative is to use semi-supervised models, such as co-training...

Descripción completa

Detalles Bibliográficos
Autores principales: Díaz, Gabriel, Peralta, Billy, Caro, Luis, Nicolis, Orietta
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8065686/
https://www.ncbi.nlm.nih.gov/pubmed/33916017
http://dx.doi.org/10.3390/e23040423

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8065686/
https://www.ncbi.nlm.nih.gov/pubmed/33916017
http://dx.doi.org/10.3390/e23040423

Ejemplares similares