Prototype Rectification Few-Shot Classification Model with Dual-Path Cooperation

In the learning process of the metric-based meta-learning, there are some problems, such as the lack of prior knowledge acquired due to the distribution of scarce data, the interference of weakly related or unrelated features extracted from a single-view sample, and the deviations of representative...

Fuld beskrivelse

Bibliografiske detaljer

Hovedforfatter:	LYU Jia, ZENG Mengyao, DONG Baosen
Format:	Artigo
Sprog:	Chinês
Udgivet:	Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2024-03-01
Serier:	Jisuanji kexue yu tansuo
Fag:	few-shot learning; meta-learning; metric learning; adaptive dual-path cooperation learning; prototype rectification
Online adgang:	http://fcst.ceaj.org/fileup/1673-9418/PDF/2301070.pdf
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!