OPT OpenIR  > 光学影像学习与分析中心
Cascaded Subpatch Networks for Effective CNNs
Jiang, Xiaoheng1; Pang, Yanwei1; Sun, Manli1; Li, Xuelong2; Pang, YW (reprint author), Tianjin Univ, Sch Elect & Informat Enginnering, Tianjin 300072, Peoples R China.
Department光学影像学习与分析中心
2018-07
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X
Volume29Issue:7Pages:2684-2694
Contribution Rank2
Abstract

Conventional convolutional neural networks use either a linear or a nonlinear filter to extract features from an image patch (region) of spatial size H x W (typically, H is small and is equal to W, e.g., H is 5 or 7). Generally, the size of the filter is equal to the size H x W of the input patch. We argue that the representational ability of equal-size strategy is not strong enough. To overcome the drawback, we propose to use subpatch filter whose spatial size h x w is smaller than H x W. The proposed subpatch filter consists of two subsequent filters. The first one is a linear filter of spatial size h x w and is aimed at extracting features from spatial domain. The second one is of spatial size 1 x 1 and is used for strengthening the connection between different input feature channels and for reducing the number of parameters. The subpatch filter convolves with the input patch and the resulting network is called a subpatch network. Taking the output of one subpatch network as input, we further repeat constructing subpatch networks until the output contains only one neuron in spatial domain. These subpatch networks form a new network called the cascaded subpatch network (CSNet). The feature layer generated by CSNet is called the csconv layer. For the whole input image, we construct a deep neural network by stacking a sequence of csconv layers. Experimental results on five benchmark data sets demonstrate the effectiveness and compactness of the proposed CSNet. For example, our CSNet reaches a test error of 5.68% on the CIFAR10 data set without model averaging. To the best of our knowledge, this is the best result ever obtained on the CIFAR10 data set.

KeywordCascaded Subpatch Networks (Csnet) Convolutional Neural Network (Cnn) Feature Extraction Subpatch Filter
Subject AreaComputer Science, Artificial Intelligence
DOI10.1109/TNNLS.2017.2689098
Indexed BySCI ; EI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS IDWOS:000436420400002
EI Accession Number20172003670735
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/30415
Collection光学影像学习与分析中心
Corresponding AuthorPang, YW (reprint author), Tianjin Univ, Sch Elect & Informat Enginnering, Tianjin 300072, Peoples R China.
Affiliation1.Tianjin Univ, Sch Elect & Informat Enginnering, Tianjin 300072, Peoples R China
2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning, Xian 710119, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Jiang, Xiaoheng,Pang, Yanwei,Sun, Manli,et al. Cascaded Subpatch Networks for Effective CNNs[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(7):2684-2694.
APA Jiang, Xiaoheng,Pang, Yanwei,Sun, Manli,Li, Xuelong,&Pang, YW .(2018).Cascaded Subpatch Networks for Effective CNNs.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(7),2684-2694.
MLA Jiang, Xiaoheng,et al."Cascaded Subpatch Networks for Effective CNNs".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.7(2018):2684-2694.
Files in This Item:
File Name/Size DocType Version Access License
Cascaded Subpatch Ne(2610KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jiang, Xiaoheng]'s Articles
[Pang, Yanwei]'s Articles
[Sun, Manli]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jiang, Xiaoheng]'s Articles
[Pang, Yanwei]'s Articles
[Sun, Manli]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jiang, Xiaoheng]'s Articles
[Pang, Yanwei]'s Articles
[Sun, Manli]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Cascaded Subpatch Networks for Effective CNNs.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.