A Two-Stage Approach to Few-Shot Learning for Image Recognition

TL;DR

This paper introduces a two-stage neural network architecture for few-shot image recognition that leverages transferable knowledge and a novel distance metric, achieving competitive results on standard datasets.

Contribution

The paper presents a novel two-stage training framework that encodes transferable features and learns category-agnostic mappings, improving few-shot recognition performance.

Findings

Achieves competitive accuracy on four standard few-shot datasets.

Introduces Mahalanobis distance for better class discrimination.

Analyzes the impact of each component in the proposed framework.

Abstract

This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories. The proposed multi-layer neural network architecture encodes transferable knowledge extracted from a large annotated dataset of base categories. This architecture is then applied to novel categories containing only a few samples. The transfer of knowledge is carried out at the feature-extraction and the classification levels distributed across the two training stages. In the first-training stage, we introduce the relative feature to capture the structure of the data as well as obtain a low-dimensional discriminative space. Secondly, we account for the variable variance of different categories by using a network to predict the variance of each class. Classification is then performed by computing the Mahalanobis distance to the mean-class representation in contrast to previous approaches that used the Euclidean distance. In the second-training stage, a category-agnostic mapping is learned from the mean-sample representation to its corresponding class-prototype representation. This is because the mean-sample representation may not accurately represent the novel category prototype. Finally, we evaluate the proposed network structure on four standard few-shot image recognition datasets, where our proposed few-shot learning system produces competitive performance compared to previous work. We also extensively studied and analyzed the contribution of each component of our proposed framework.