A Transductive Maximum Margin Classifier for Few-Shot Learning
This addresses the challenge of training classifiers with limited labeled data, which is incremental as it builds on existing maximum margin methods.
The paper tackles the problem of few-shot learning by introducing a transductive maximum margin classifier (FS-TMMC) that leverages unlabeled query examples to adjust the hyperplane, achieving state-of-the-art performance on benchmarks like miniImagenet, tieredImagenet, and CUB.
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.