Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy

TL;DR

This paper introduces local-level strategies for few-shot learning to address information loss and location bias, significantly improving performance and achieving state-of-the-art results.

Contribution

It proposes a local-agnostic training, a local-level similarity measure, and a knowledge transfer method to enhance few-shot learning performance.

Findings

Achieves 2.8%-7.2% performance improvement over baselines.

Significantly boosts accuracy across multiple benchmark datasets.

Introduces novel local-level strategies for better feature comparison.

Abstract

Aiming at recognizing the samples from novel categories with few reference samples, few-shot learning (FSL) is a challenging problem. We found that the existing works often build their few-shot model based on the image-level feature by mixing all local-level features, which leads to the discriminative location bias and information loss in local details. To tackle the problem, this paper returns the perspective to the local-level feature and proposes a series of local-level strategies. Specifically, we present (a) a local-agnostic training strategy to avoid the discriminative location bias between the base and novel categories, (b) a novel local-level similarity measure to capture the accurate comparison between local-level features, and (c) a local-level knowledge transfer that can synthesize different knowledge transfers from the base category according to different location features. Extensive experiments justify that our proposed local-level strategies can significantly boost the performance and achieve 2.8%-7.2% improvements over the baseline across different benchmark datasets, which also achieves state-of-the-art accuracy.