Few-shot learning with improved local representations via bias rectify module

TL;DR

This paper introduces a Deep Bias Rectify Network that enhances few-shot learning by leveraging spatial information and a prototype augmentation mechanism, leading to improved classification performance on standard benchmarks.

Contribution

The paper proposes a novel bias rectify module and prototype augmentation mechanism to better utilize spatial features and intra-class variations in few-shot learning.

Findings

Outperforms state-of-the-art methods on popular benchmarks.

Effectively handles intra-class variations and spatial information.

Improves discriminative feature focus in few-shot classification.

Abstract

Recent approaches based on metric learning have achieved great progress in few-shot learning. However, most of them are limited to image-level representation manners, which fail to properly deal with the intra-class variations and spatial knowledge and thus produce undesirable performance. In this paper we propose a Deep Bias Rectify Network (DBRN) to fully exploit the spatial information that exists in the structure of the feature representations. We first employ a bias rectify module to alleviate the adverse impact caused by the intra-class variations. bias rectify module is able to focus on the features that are more discriminative for classification by given different weights. To make full use of the training data, we design a prototype augment mechanism that can make the prototypes generated from the support set to be more representative. To validate the effectiveness of our method, we conducted extensive experiments on various popular few-shot classification benchmarks and our methods can outperform state-of-the-art methods.