ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

TL;DR

This paper introduces ECKPN, a novel transductive few-shot learning model that explicitly propagates class-level knowledge to improve classification accuracy, outperforming existing methods on multiple benchmarks.

Contribution

The paper proposes ECKPN, which uniquely combines instance-level and class-level graph modules with explicit class knowledge calibration for enhanced few-shot learning.

Findings

ECKPN significantly outperforms state-of-the-art methods on four benchmarks.

Explicit class knowledge propagation improves classification accuracy.

The model effectively models relations between classes and samples.

Abstract

Recently, the transductive graph-based methods have achieved great success in the few-shot classification task. However, most existing methods ignore exploring the class-level knowledge that can be easily learned by humans from just a handful of samples. In this paper, we propose an Explicit Class Knowledge Propagation Network (ECKPN), which is composed of the comparison, squeeze and calibration modules, to address this problem. Specifically, we first employ the comparison module to explore the pairwise sample relations to learn rich sample representations in the instance-level graph. Then, we squeeze the instance-level graph to generate the class-level graph, which can help obtain the class-level visual knowledge and facilitate modeling the relations of different classes. Next, the calibration module is adopted to characterize the relations of the classes explicitly to obtain the more discriminative class-level knowledge representations. Finally, we combine the class-level knowledge with the instance-level sample representations to guide the inference of the query samples. We conduct extensive experiments on four few-shot classification benchmarks, and the experimental results show that the proposed ECKPN significantly outperforms the state-of-the-art methods.