ReMarNet: conjoint relation and margin learning for small-sample image classification

Li, X., Yu, L., Yang, X. , Ma, Z., Xue, J.-H., Cao, J. and Guo, J. (2021) ReMarNet: conjoint relation and margin learning for small-sample image classification. IEEE Transactions on Circuits and Systems for Video Technology, 31(4), pp. 1569-1579. (doi: 10.1109/TCSVT.2020.3005807)

Abstract

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and- Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype; at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Code is available at https://github.com/liyunyu08/ReMarNet.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Yang, Dr Xiaochen
• Authors: Li, X., Yu, L., Yang, X., Ma, Z., Xue, J.-H., Cao, J., and Guo, J.
• College/School: College of Science and Engineering > School of Mathematics and Statistics > Statistics
• Journal Name: IEEE Transactions on Circuits and Systems for Video Technology
• Publisher: IEEE
• ISSN: 1051-8215
• ISSN (Online): 1558-2205
• Published Online: 29 June 2020
• Copyright Holders: Copyright © 2020 IEEE
• First Published: First published in IEEE Transactions on Circuits and Systems for Video Technology 31(4): 1569-1579
• Publisher Policy: Reproduced in accordance with the publisher copyright policy