Looking back to lower-level information in few-shot learning

TL;DR

This paper introduces Looking-Back, a novel method that leverages lower-level neural network features within a graph-based meta-learning framework to enhance few-shot classification accuracy, outperforming existing methods.

Contribution

It proposes utilizing hidden layer embeddings for label propagation in few-shot learning, a novel approach that improves upon current feature-only methods.

Findings

Improved classification accuracy on miniImageNet and tieredImageNet datasets.

Lower-level features contribute valuable information for few-shot learning.

State-of-the-art results achieved with the proposed method.

Abstract

Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify new examples. This challenging scenario is commonly known as few-shot learning. Few-shot learning has garnered increased attention in recent years due to its significance for many real-world problems. Recently, new methods relying on meta-learning paradigms combined with graph-based structures, which model the relationship between examples, have shown promising results on a variety of few-shot classification tasks. However, existing work on few-shot learning is only focused on the feature embeddings produced by the last layer of the neural network. In this work, we propose the utilization of lower-level, supporting information, namely the feature embeddings of the hidden neural network layers, to improve classifier accuracy. Based on a graph-based meta-learning framework, we develop a method called Looking-Back, where such lower-level information is used to construct additional graphs for label propagation in limited data settings. Our experiments on two popular few-shot learning datasets, miniImageNet and tieredImageNet, show that our method can utilize the lower-level information in the network to improve state-of-the-art classification performance.