Lanzhou University of Technology Institutional Repository (LUT_IR)
Remarnet: Conjoint relation and margin learning for small-sample image classification | |
Li, Xiaoxu1,2; Yu, Liyun1; Yang, Xiaochen3; Ma, Zhanyu2; Xue, Jing-Hao3; Cao, Jie1,2; Guo, Jun3 | |
2021-04 | |
发表期刊 | IEEE Transactions on Circuits and Systems for Video Technology |
ISSN | 1051-8215 |
卷号 | 31期号:4页码:1569-1579 |
摘要 | 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. 1051-8215 © 2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. |
关键词 | Deep learning Image classification Sampling Classification mechanism Competitive performance Discriminative features Discriminative power Fully connected networks Novel neural network State-of-the-art methods State-of-the-art performance |
DOI | 10.1109/TCSVT.2020.3005807 |
收录类别 | EI ; SCIE |
语种 | 英语 |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Electrical & Electronic |
WOS记录号 | WOS:000637537200026 |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
EI入藏号 | 20211510210275 |
EI主题词 | Learning systems |
来源库 | WOS |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | https://ir.lut.edu.cn/handle/2XXMBERH/148376 |
专题 | 兰州理工大学 |
通讯作者 | Ma, Zhanyu |
作者单位 | 1.Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou 730050, Peoples R China; 2.Beijing Univ Posts & Telecommun, Pattern Recognit & Intelligent Syst Lab, Sch Artificial Intelligence, Beijing 100876, Peoples R China; 3.UCL, Dept Stat Sci, London WC1E 6BT, England |
第一作者单位 | 兰州理工大学 |
第一作者的第一单位 | 兰州理工大学 |
推荐引用方式 GB/T 7714 | Li, Xiaoxu,Yu, Liyun,Yang, Xiaochen,et al. Remarnet: Conjoint relation and margin learning for small-sample image classification[J]. IEEE Transactions on Circuits and Systems for Video Technology,2021,31(4):1569-1579. |
APA | Li, Xiaoxu.,Yu, Liyun.,Yang, Xiaochen.,Ma, Zhanyu.,Xue, Jing-Hao.,...&Guo, Jun.(2021).Remarnet: Conjoint relation and margin learning for small-sample image classification.IEEE Transactions on Circuits and Systems for Video Technology,31(4),1569-1579. |
MLA | Li, Xiaoxu,et al."Remarnet: Conjoint relation and margin learning for small-sample image classification".IEEE Transactions on Circuits and Systems for Video Technology 31.4(2021):1569-1579. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论