Few-Shot Image Classification Based on Ensemble Metric Learning

Abstract

In the case of few labelled image data samples, image classification is a difficult challenge, which is called few-shot image classification. Recently, many methods based on metric learning have been proposed. Most of these methods mainly focus on the representations of global image-level features or local feature-level descriptors. However, these methods calculate similarity from a single metric learning perspective. Motivated by ensemble learning, a novel Ensemble Metric Learning (EML) method for few-shot image classification is proposed, which not only utilizes label propagation, but also considers image-level and local feature-level descriptor metrics. The experimental results show that the proposed method can effectively improve the classification accuracy by ensemble learning.