Cooperative Bi-path Metric for Few-shot Learning

TL;DR

This paper introduces a cooperative bi-path metric for few-shot learning that leverages base class information to improve classification accuracy, establishing new state-of-the-art results.

Contribution

It proposes a simple baseline trained on base classes and a novel cooperative bi-path metric that utilizes correlations between base and novel classes.

Findings

Achieves comparable results to state-of-the-art with the baseline.

The cooperative bi-path metric improves accuracy over existing methods.

Establishes new state-of-the-art on benchmark datasets.

Abstract

Given base classes with sufficient labeled samples, the target of few-shot classification is to recognize unlabeled samples of novel classes with only a few labeled samples. Most existing methods only pay attention to the relationship between labeled and unlabeled samples of novel classes, which do not make full use of information within base classes. In this paper, we make two contributions to investigate the few-shot classification problem. First, we report a simple and effective baseline trained on base classes in the way of traditional supervised learning, which can achieve comparable results to the state of the art. Second, based on the baseline, we propose a cooperative bi-path metric for classification, which leverages the correlations between base classes and novel classes to further improve the accuracy. Experiments on two widely used benchmarks show that our method is a simple and effective framework, and a new state of the art is established in the few-shot classification field.