View : 116 Download: 0

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

Title
Learning feature alignment and dual correlation for few-shot image classification
Authors
HuangXilangChoiSeon Han
Ewha Authors
최선한
SCOPUS Author ID
최선한scopus
Issue Date
2024
Journal Title
CAAI Transactions on Intelligence Technology
ISSN
2468-6557JCR Link
Citation
CAAI Transactions on Intelligence Technology vol. 9, no. 2, pp. 303 - 318
Keywords
image classificationmachine learningmetric learning
Publisher
John Wiley and Sons Inc
Indexed
SCIE; SCOPUS scopus
Document Type
Article
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 methods use the feature mean as the class prototype and calculate the correlation between prototype and unlabelled features to learn an alignment strategy. However, mean prototypes tend to degenerate informative features because spatial features at the same position may not be equally important for the final classification, leading to inaccurate correlation calculations. Therefore, the authors propose an effective intraclass FA strategy that aggregates semantically similar spatial features from an adaptive reference prototype in low-dimensional feature space to obtain an informative prototype feature map for precise correlation computation. Moreover, a dual correlation module to learn the hard and soft correlations was developed by the authors. This module combines the correlation information between the prototype and unlabelled features in both the original and learnable feature spaces, aiming to produce a comprehensive cross-correlation between the prototypes and unlabelled features. Using both FA and cross-attention modules, our model can maintain informative class features and capture important shared features for classification. Experimental results on three few-shot classification benchmarks show that the proposed method outperformed related methods and resulted in a 3% performance boost in the 1-shot setting by inserting the proposed module into the related methods. © 2023 The Authors. CAAI Transactions on Intelligence Technology published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology and Chongqing University of Technology.
DOI
10.1049/cit2.12273
Appears in Collections:
공과대학 > 전자전기공학전공 > Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

BROWSE