Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments

TL;DR

This paper reviews recent deep metric learning methods for few-shot image classification, highlighting their approaches, novelties, challenges, and future directions from 2018 to 2022.

Contribution

It provides a comprehensive taxonomy of deep metric learning techniques for few-shot classification, categorizing methods into three stages and analyzing their innovations and issues.

Findings

Deep metric learning achieves state-of-the-art results in few-shot classification.

Categorization into three stages clarifies the development of methods.

Discussion of challenges guides future research directions.

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. With this taxonomy, we identify the novelties of different methods and problems they face. We conclude this review with a discussion on current challenges and future trends in few-shot image classification.