Cargando…

Cross Modal Few-Shot Contextual Transfer for Heterogenous Image Classification

Deep transfer learning aims at dealing with challenges in new tasks with insufficient samples. However, when it comes to few-shot learning scenarios, due to the low diversity of several known training samples, they are prone to be dominated by specificity, thus leading to one-sidedness local feature...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Zhikui, Zhang, Xu, Huang, Wei, Gao, Jing, Zhang, Suhua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8180855/
https://www.ncbi.nlm.nih.gov/pubmed/34108871
http://dx.doi.org/10.3389/fnbot.2021.654519

Ejemplares similares