OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer

doi:10.1109/TIP.2020.2990277

CORC > 兰州理工大学 > 兰州理工大学

	OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
	Li, Xiaoxu 2; Chang, Dongliang 3; Ma, Zhanyu 3; Tan, Zheng-Hua 4; Xue, Jing-Hao 2; Cao, Jie 5; Yu, Jingyi 2; Guo, Jun 1
	2020
关键词	Benchmarking Deep neural networks Large dataset TestingBenchmark datasets Discriminative features Function spaces Generalization error bounds Nonlinear layers Number of class Rademacher complexity Small sample datum
卷号	29
DOI	10.1109/TIP.2020.2990277
页码	6482-6495
英文摘要	A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting in small-sample classification, learning more discriminative features from small-sample data is becoming a new trend. To this end, this paper aims to find a subspace of neural networks that can facilitate a large decision margin. Specifically, we propose the Orthogonal Softmax Layer (OSL), which makes the weight vectors in the classification layer remain orthogonal during both the training and test processes. The Rademacher complexity of a network using the OSL is only 1 K, where K is the number of classes, of that of a network using the fully connected classification layer, leading to a tighter generalization error bound. Experimental results demonstrate that the proposed OSL has better performance than the methods used for comparison on four small-sample benchmark datasets, as well as its applicability to large-sample datasets. Codes are available at: https://github.com/dongliangchang/OSLNet. © 1992-2012 IEEE.
会议录	IEEE Transactions on Image Processing
会议录出版者	Institute of Electrical and Electronics Engineers Inc.
语种	英语
ISSN号	10577149
WOS研究方向	Computer Science ; Engineering
WOS记录号	WOS:000545079400008
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/132673]
专题	兰州理工大学
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai; W1T 7PJ, China 2.School of Computer and Communication, Lanzhou University of Technology, Lanzhou; 730050, China; 3.Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing; 730050, China; 4.Department of Electronic Systems, Aalborg University, Aalborg; 100876, Denmark; 5.Department of Statistical Science, University College London, London; 9220, United Kingdom;
推荐引用方式 GB/T 7714	Li, Xiaoxu,Chang, Dongliang,Ma, Zhanyu,et al. OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer[C]. 见:.