Learning feature alignment and dual correlation for few‐shot image classification

Learning feature alignment and dual correlation for few‐shot image classification

Abstract Few‐shot image classification is the task of classifying novel classes using extremely limited labelled samples. To perform classification using the limited samples, one solution is to learn the feature alignment (FA) information between the labelled and unlabelled sample features. Most FA...

Full description

Bibliographic Details
Main Authors: Xilang Huang, Seon Han Choi
Format: Article
Language:English
Published: Wiley 2024-04-01
Series:CAAI Transactions on Intelligence Technology
Subjects:
image classification
machine learning
metric learning
Online Access:https://doi.org/10.1049/cit2.12273

Internet

https://doi.org/10.1049/cit2.12273

Similar Items