Li, X., Yang, X. , Ma, Z. and Xue, J.-H. (2023) Deep metric learning for few-shot image classification: a review of recent developments. Pattern Recognition, 138, 109381. (doi: 10.1016/j.patcog.2023.109381)
Text
291768.pdf - Accepted Version Available under License Creative Commons Attribution Non-commercial No Derivatives. 767kB |
Abstract
Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images. One main solution to few-shot image classification is deep metric learning. These methods, by classifying unseen samples according to their distances to few seen samples in an embedding space learned by powerful deep neural networks, can avoid overfitting to few training images in few-shot image classification and have achieved the state-of-the-art performance. In this paper, we provide an up-to-date review of deep metric learning methods for few-shot image classification from 2018 to 2022 and categorize them into three groups according to three stages of metric learning, namely learning feature embeddings, learning class representations, and learning distance measures. Under this taxonomy, we identify the trends of transitioning from learning task-agnostic features to task-specific features, from simple computation of prototypes to computing task-dependent prototypes or learning prototypes, from using analytical distance or similarity measures to learning similarities through convolutional or graph neural networks. Finally, we discuss the current challenges and future directions of few-shot deep metric learning from the perspectives of effectiveness, optimization and applicability, and summarize their applications to real-world computer vision tasks.
Item Type: | Articles |
---|---|
Additional Information: | This work was supported in part by the Beijing Natural Science Foundation under Grant Z200002, the Royal Society under International Exchanges Award IEC\NSFC\201071, the National Natural Science Foundation of China (NSFC) under Grant 62111530146, 62176110, 61906080, 61922015, U19B2036, 62225601, Young Doctoral Fund of Education Department of Gansu Province under Grant 2021QB-038, and Hong-liu Distinguished Young Talents Foundation of Lanzhou University of Technology. |
Status: | Published |
Refereed: | Yes |
Glasgow Author(s) Enlighten ID: | Yang, Dr Xiaochen |
Authors: | Li, X., Yang, X., Ma, Z., and Xue, J.-H. |
College/School: | College of Science and Engineering > School of Mathematics and Statistics > Statistics |
Journal Name: | Pattern Recognition |
Publisher: | Elsevier |
ISSN: | 0031-3203 |
ISSN (Online): | 1873-5142 |
Published Online: | 02 February 2023 |
Copyright Holders: | Copyright © 2023 Elsevier |
First Published: | First published in Pattern Recognition 138:109381 |
Publisher Policy: | Reproduced in accordance with the copyright policy of the publisher |
University Staff: Request a correction | Enlighten Editors: Update this record