Cargando…

Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy

Deep learning has been successfully applied to many classification problems including underwater challenges. However, a long-standing issue with deep learning is the need for large and consistently labeled datasets. Although current approaches in semi-supervised learning can decrease the required am...

Descripción completa

Detalles Bibliográficos
Autores principales: Schmarje, Lars, Brünger, Johannes, Santarossa, Monty, Schröder, Simon-Martin, Kiko, Rainer, Koch, Reinhard
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8512301/
https://www.ncbi.nlm.nih.gov/pubmed/34640981
http://dx.doi.org/10.3390/s21196661

Ejemplares similares