Trainable Class Prototypes for Few-Shot Learning
This work addresses the problem of improving few-shot learning accuracy for visual classification tasks, representing an incremental advancement in metric-based approaches.
The paper tackles few-shot learning by introducing trainable prototypes within a two-phase framework combining self-supervised meta-training and metric classification, achieving state-of-the-art performance with about a 20% increase over unsupervised methods on standard datasets.
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.