ReNAP: Relation network with adaptiveprototypical learning for few-shot classification

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 adap-tively 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. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

Traditional deep learning-based image classification methods often struggle with recognizing new classes with few samples. The proposed ReNAP method incorporates an adaptive prototypical learning module into RelationNet, enabling more accurate representation and superior classification performance. The results demonstrate its effectiveness on four benchmark datasets. (c) 2022 Elsevier B.V. All rights reserved.