Geometric Mean Improves Loss For Few-Shot Learning

TL;DR

This paper introduces a novel geometric mean-based loss function for few-shot learning that enhances discriminative feature metrics, leading to competitive classification performance with theoretical advantages over traditional methods.

Contribution

It proposes a new geometric mean-based loss for FSL that improves discriminative metrics and provides theoretical analysis of its benefits.

Findings

Achieves competitive results on few-shot image classification tasks.

Theoretically reveals advantages of geometric mean over arithmetic mean in loss formulation.

Enhances discriminative feature learning in deep metric-based models.

Abstract

Few-shot learning (FSL) is a challenging task in machine learning, demanding a model to render discriminative classification by using only a few labeled samples. In the literature of FSL, deep models are trained in a manner of metric learning to provide metric in a feature space which is well generalizable to classify samples of novel classes; in the space, even a few amount of labeled training examples can construct an effective classifier. In this paper, we propose a novel FSL loss based on \emph{geometric mean} to embed discriminative metric into deep features. In contrast to the other losses such as utilizing arithmetic mean in softmax-based formulation, the proposed method leverages geometric mean to aggregate pair-wise relationships among samples for enhancing discriminative metric across class categories. The proposed loss is not only formulated in a simple form but also is thoroughly analyzed in theoretical ways to reveal its favorable characteristics which are favorable for learning feature metric in FSL. In the experiments on few-shot image classification tasks, the method produces competitive performance in comparison to the other losses.