Trainable Class Prototypes for Few-Shot Learning

TL;DR

This paper introduces trainable prototypes and a non-episodic self-supervised meta-training approach for few-shot learning, significantly improving performance on visual classification tasks.

Contribution

It proposes a novel method combining trainable prototypes with self-supervised meta-training, avoiding episodic training disadvantages and enhancing few-shot learning accuracy.

Findings

Achieves state-of-the-art results on standard few-shot datasets.

About 20% performance increase over existing unsupervised methods.

Utilizes attention mechanisms in meta-training and task-training.

Abstract

Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the artificial ones within the meta-training and task-training framework. Also to avoid the disadvantages that the episodic meta-training brought, we adopt non-episodic meta-training based on self-supervised learning. Overall we solve the few-shot tasks in two phases: meta-training a transferable feature extractor via self-supervised learning and training the prototypes for metric classification. In addition, the simple attention mechanism is used in both meta-training and task-training. Our method achieves state-of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification dataset, with about 20% increase compared to the available unsupervised few-shot learning methods.