Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier

TL;DR

This paper demonstrates that using a library of pre-trained feature extractors with a simple classifier can outperform complex meta-learning methods in few-shot image classification, especially across different domains.

Contribution

It introduces a straightforward approach leveraging pre-trained features and a simple classifier, challenging the necessity of complex meta-learning algorithms for few-shot tasks.

Findings

Pre-trained feature libraries improve few-shot classification accuracy.

The simple classifier outperforms several meta-learning algorithms.

Approach is effective across various cross-domain tasks.

Abstract

Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-trained feature extractors for few-shot image classification. We show experimentally that a library of pre-trained feature extractors combined with a simple feed-forward network learned with an L2-regularizer can be an excellent option for solving cross-domain few-shot image classification. Our experimental results suggest that this simpler sample-efficient approach far outperforms several well-established meta-learning algorithms on a variety of few-shot tasks.