A Transductive Maximum Margin Classifier for Few-Shot Learning

TL;DR

This paper introduces FS-TMMC, a transductive maximum margin classifier for few-shot learning that utilizes unlabeled query data to improve classification, achieving state-of-the-art results on standard benchmarks.

Contribution

It proposes a novel transductive classifier that leverages unlabeled query data to enhance few-shot learning performance, optimized with an L-BFGS algorithm.

Findings

Achieves state-of-the-art results on miniImagenet, tieredImagenet, and CUB.

Effectively leverages unlabeled query data for better generalization.

Outperforms existing methods in few-shot classification tasks.

Abstract

Few-shot learning aims to train a classifier that can generalize well when just a small number of labeled examples per class are given. We introduce a transductive maximum margin classifier for few-shot learning (FS-TMMC). The basic idea of the classical maximum margin classifier is to solve an optimal prediction function so that the training data can be correctly classified by the resulting classifer with the largest geometric margin. In few-shot learning, it is challenging to find such classifiers with good generalization ability due to the insufficiency of training data in the support set. FS-TMMC leverages the unlabeled query examples to adjust the separating hyperplane of the maximum margin classifier such that the prediction function is optimal on both the support and query sets. Furthermore, we use an efficient and effective quasi-Newton algorithm, the L-BFGS method for optimization. Experimental results on three standard few-shot learning benchmarks including miniImagenet, tieredImagenet and CUB show that our method achieves state-of-the-art performance.