Similarity-Difference Relation Network for Few-Shot Learning

Abstract

Few-shot learning aims to build a classification model by training a small amount of labeled sample data, which can be well adapted to new domains. The key point of few-shot learning is that a small amount of sample data cannot reflect the true data distribution. Training on a small amount of sample data will lead to over-fitting of the deep neural network model. The differences between different categories are ignored when using similarity measures for classification. This paper proposes a novel few-shot learning method based on similarity-difference relation network, which uses shallow wide residual network to extract the features of the training dataset and fuses them into a category prototype. Meanwhile, SDRN pays attention to the characterization of similarities and differences between positive and negative samples. This paper verifies the effectiveness of the similarity-difference relational network on the Mini-ImageNet and Tiered-ImageNet datasets. The experimental results show that the similarity-difference two-way relational network further improves image classification accuracy in the few-shot learning task.