Feature Aligning Few shot Learning Method Using Local Descriptors Weighted Rules

TL;DR

This paper introduces FAFD-LDWR, a novel few-shot learning method that uses local descriptor alignment and cross-normalization to improve classification accuracy and interpretability on benchmark datasets.

Contribution

It proposes a new feature aligning method with cross-normalization and local descriptor weighting to enhance few-shot image classification performance.

Findings

Outperforms state-of-the-art methods on three benchmark datasets.

Improves 1-shot and 5-shot classification accuracy.

Enhances interpretability through visualization experiments.

Abstract

Few-shot classification involves identifying new categories using a limited number of labeled samples. Current few-shot classification methods based on local descriptors primarily leverage underlying consistent features across visible and invisible classes, facing challenges including redundant neighboring information, noisy representations, and limited interpretability. This paper proposes a Feature Aligning Few-shot Learning Method Using Local Descriptors Weighted Rules (FAFD-LDWR). It innovatively introduces a cross-normalization method into few-shot image classification to preserve the discriminative information of local descriptors as much as possible; and enhances classification performance by aligning key local descriptors of support and query sets to remove background noise. FAFD-LDWR performs excellently on three benchmark datasets , outperforming state-of-the-art methods in both 1-shot and 5-shot settings. The designed visualization experiments also demonstrate FAFD-LDWR's improvement in prediction interpretability.