Deep InterBoost networks for small-sample image classification

doi:10.1016/j.neucom.2020.06.135

CORC > 兰州理工大学 > 兰州理工大学

	Deep InterBoost networks for small-sample image classification
	Li, Xiaoxu 1,2; Chang, Dongliang 1; Ma, Zhanyu 1; Tan, Zheng-Hua 3; Xue, Jing-Hao 4; Cao, Jie 2; Guo, Jun 1
刊名	NEUROCOMPUTING
	2021-10-07
卷号	456 页码:492-503
关键词	Ensemble learning Deep neural network Small-sample image classification Overfitting
ISSN号	0925-2312
DOI	10.1016/j.neucom.2020.06.135
英文摘要	Deep neural networks have recently shown excellent performance on numerous image classification tasks. These networks often need to estimate a large number of parameters and require much training data. When the amount of training data is small, however, a network with high flexibility quickly overfits the training data, resulting in a large model variance and poor generalization. To address this problem, we propose a new, simple yet effective ensemble method called InterBoost for small-sample image classifi-cation. In the training phase, InterBoost first randomly generates two sets of complementary weights for training data, which are used for separately training two base networks of the same structure, and then the two sets of complementary weights are updated for refining the training of the networks through interaction between the two base networks previously trained. This interactive training process contin-ues iteratively until a stop criterion is met. In the testing phase, the outputs of the two networks are com-bined to obtain one final score for classification. Experimental results on four small-sample datasets, UIUC-Sports, LabelMe, 15Scenes and Caltech101, demonstrate that the proposed ensemble method out-performs existing ones. Moreover, results from the Wilcoxon signed-rank tests show that our method is statistically significantly better than the methods compared. Detailed analysis is also provided for an in-depth understanding of the proposed method. (c) 2020 Elsevier B.V. All rights reserved.
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000687472700009
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/148529]
专题	兰州理工大学
作者单位	1.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Pattern Recognit & Intelligent Syst Lab, Beijing 100876, Peoples R China; 2.Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou 730050, Peoples R China; 3.Aalborg Univ, Dept Elect Syst, Aalborg, Denmark; 4.UCL, Dept Stat Sci, London WC1E 6BT, England
推荐引用方式 GB/T 7714	Li, Xiaoxu,Chang, Dongliang,Ma, Zhanyu,et al. Deep InterBoost networks for small-sample image classification[J]. NEUROCOMPUTING,2021,456:492-503.
APA	Li, Xiaoxu.,Chang, Dongliang.,Ma, Zhanyu.,Tan, Zheng-Hua.,Xue, Jing-Hao.,...&Guo, Jun.(2021).Deep InterBoost networks for small-sample image classification.NEUROCOMPUTING,456,492-503.
MLA	Li, Xiaoxu,et al."Deep InterBoost networks for small-sample image classification".NEUROCOMPUTING 456(2021):492-503.