Adaptive prototype few-shot image classification method based on feature pyramid

PeerJ Comput Sci. 2024 Oct 1:10:e2322. doi: 10.7717/peerj-cs.2322. eCollection 2024.

Abstract

Few-shot learning aims to enable machines to recognize unseen novel classes using limited samples akin to human capabilities. Metric learning is a crucial approach to addressing this challenge, with its performance primarily dependent on the effectiveness of feature extraction and prototype computation. This article introduces an Adaptive Prototype few-shot image classification method based on Feature Pyramid (APFP). APFP employs a novel feature extraction method called FResNet, which builds upon the ResNet architecture and leverages a feature pyramid structure to retain finer details. In the 5-shot scenario, traditional methods for computing average prototypes exhibit limitations due to the typically diverse and uneven distribution of samples, where simple means may inadequately reflect such diversity. To address this issue, APFP proposes an Adaptive Prototype method (AP) that dynamically computes class prototypes of the support set based on the similarity between support set samples and query samples. Experimental results demonstrate that APFP achieves 67.98% and 85.32% accuracy in the 5-way 1-shot and 5-way 5-shot scenarios on the MiniImageNet dataset, respectively, and 84.02% and 94.44% accuracy on the CUB dataset. These results indicate that the proposed APFP method addresses the few-shot learning problem.

Keywords: Few-shot learning; Image classification; Metric learning; Prototype network.

Associated data

  • figshare/10.6084/m9.figshare.26340226.v1

Grants and funding

This work was funded by the Key Research and Development Program of Heilongjiang Province under Grant No. 2022ZX01A19, and by the Fundamental Research Funds for the Central Universities under Grant No. 3072022TS0604. There was no additional external funding received for this study. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.