City Research Online

Abstract

Traditional deep learning-based image classification methods often fail to recognize a new class that does not exist in the training dataset, particularly when the new class only has a small number of samples. Such a challenging and new learning problem is referred to as few-shot learning. In few-shot learning, the relation network (RelationNet) is a powerful method. However, in RelationNet and its state-of-the-art variants, the prototype of each class is obtained by a simple summation or average over the labeled samples. These simple sample statistics cannot accurately capture the distinct characteristics of the diverse classes of real-world images. To address this problem, in this paper, we propose the Relation Network with Adaptive Prototypical Learning method (ReNAP), which can learn the class prototypes adaptively and provide more accurate representations of the classes. More specifically, ReNAP embeds an adaptive prototypical learning module constructed by a convolutional network into RelationNet. Our ReNAP achieves superior classification performances to RelationNet and other state-of-the-art methods on four widely used benchmark datasets, FC100, CUB-200-2011, Stanford-Cars, and Stanford-Dogs.

Publication Type:	Article
Publisher Keywords:	Few-shot learning, Relation network, Prototypical learning, Convolutional neural networks
Subjects:	H Social Sciences > HA Statistics Q Science > QA Mathematics > QA75 Electronic computers. Computer science R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
Departments:	Bayes Business School > Actuarial Science & Insurance

Export

Downloads