Trainable Class Prototypes for Few-Shot Learning

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.

8 pages, 2 figures,and 3 Tables. arXiv admin note: substantial text overlap with arXiv:2008.09942

References in corpus (7)

• Semi-Supervised Classification with Graph Convolutional Networks
• Bootstrap your own latent: A new approach to self-supervised Learning
• Simplifying Graph Convolutional Networks
• LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning
• Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
• Unsupervised Few-shot Learning via Self-supervised Training
• Few-Shot Image Classification via Contrastive Self-Supervised Learning