Cargando…

Feature augmentation based on information fusion rectification for few-shot image classification

In the issue of few-shot image classification, due to lack of sufficient data, directly training the model will lead to overfitting. In order to alleviate this problem, more and more methods focus on non-parametric data augmentation, which uses the information of known data to construct non-parametr...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Hang, Tian, Shengzhao, Fu, Yan, Zhou, Junlin, Liu, Jingfa, Chen, Duanbing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9984463/
https://www.ncbi.nlm.nih.gov/pubmed/36869163
http://dx.doi.org/10.1038/s41598-023-30398-1