Image classification based on convolutional neural networks with cross-level strategy

doi:10.1007/s11042-016-3540-x

	Image classification based on convolutional neural networks with cross-level strategy
	Liu, Yu 1; Yin, Baocai 1; Yu, Jun 1; Wang, Zengfu1,2
	2017-04-01
发表期刊	MULTIMEDIA TOOLS AND APPLICATIONS
摘要	In the past few years, convolutional neural networks (CNNs) have exhibited great potential in the field of image classification. In this paper, we present a novel strategy named cross-level to improve the existing networks' architecture in which different levels of feature representation in a network are merely connected in series. The basic idea of cross-level is to establish a convolutional layer between two nonadjacent levels, aiming to extract more sufficient features with multiple scales at each feature representation level. The proposed cross-level strategy can be naturally integrated into an existing network without any change on its original architecture, which makes it very practical and convenient. Four popular convolutional networks for image classification are employed to illustrate its implementation in detail. Experimental results on the dataset adopted by the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) verify the effectiveness of the cross-level strategy on image classification. Furthermore, a new convolutional network with cross-level architecture is presented to demonstrate the potential of the proposed strategy in future network design.
文章类型	Article
关键词	Convolutional Neural Networks (Cnns) Image Classification Network Architecture Feature Representation Deep Learning
WOS标题词	Science & Technology ; Technology
DOI	10.1007/s11042-016-3540-x
关键词[WOS]	REPRESENTATION ; RECOGNITION ; FEATURES ; SCALE
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61472393 ; National Natural Science Foundation of China(61472393 ; National Natural Science Foundation of China(61472393 ; National Natural Science Foundation of China(61472393 ; National Natural Science Foundation of China(61472393 ; National Natural Science Foundation of China(61472393 ; National Natural Science Foundation of China(61472393 ; National Natural Science Foundation of China(61472393 ; National Science and Technology Major Project of the Ministry of Science and Technology of China(2012GB102007) ; National Science and Technology Major Project of the Ministry of Science and Technology of China(2012GB102007) ; National Science and Technology Major Project of the Ministry of Science and Technology of China(2012GB102007) ; National Science and Technology Major Project of the Ministry of Science and Technology of China(2012GB102007) ; National Science and Technology Major Project of the Ministry of Science and Technology of China(2012GB102007) ; National Science and Technology Major Project of the Ministry of Science and Technology of China(2012GB102007) ; National Science and Technology Major Project of the Ministry of Science and Technology of China(2012GB102007) ; National Science and Technology Major Project of the Ministry of Science and Technology of China(2012GB102007) ; Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization(13Z02008) ; Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization(13Z02008) ; Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization(13Z02008) ; Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization(13Z02008) ; Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization(13Z02008) ; Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization(13Z02008) ; Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization(13Z02008) ; Anhui Province Initiative Funds on Intelligent Speech Technology and Industrialization(13Z02008) ; IFLYTEK CO.,LTD. ; IFLYTEK CO.,LTD. ; IFLYTEK CO.,LTD. ; IFLYTEK CO.,LTD. ; IFLYTEK CO.,LTD. ; IFLYTEK CO.,LTD. ; IFLYTEK CO.,LTD. ; IFLYTEK CO.,LTD. ; 61303150) ; 61303150) ; 61303150) ; 61303150) ; 61303150) ; 61303150) ; 61303150) ; 61303150)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000400570400043
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.hfcas.ac.cn:8080/handle/334002/33471
专题	中科院合肥智能机械研究所
作者单位	1.Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China 2.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Peoples R China
推荐引用方式 GB/T 7714	Liu, Yu,Yin, Baocai,Yu, Jun,et al. Image classification based on convolutional neural networks with cross-level strategy[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2017,76(8):11065-11079.
APA	Liu, Yu,Yin, Baocai,Yu, Jun,&Wang, Zengfu.(2017).Image classification based on convolutional neural networks with cross-level strategy.MULTIMEDIA TOOLS AND APPLICATIONS,76(8),11065-11079.
MLA	Liu, Yu,et al."Image classification based on convolutional neural networks with cross-level strategy".MULTIMEDIA TOOLS AND APPLICATIONS 76.8(2017):11065-11079.