Convolution in Convolution for Network in Network | |
Pang, Yanwei1; Sun, Manli1; Jiang, Xiaoheng1; Li, Xuelong2; Pang, YW (reprint author), Tianjin Univ, Sch Elect & Informat Enginnering, Tianjin 300072, Peoples R China. | |
刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
2018-05-01 | |
卷号 | 29期号:5页码:1587-1597 |
关键词 | Convolution In Convolution (Cic) Convolutional Neural Networks (Cnns) Image Recognition Network In Network (nIn) |
ISSN号 | 2162-237X |
DOI | 10.1109/TNNLS.2017.2676130 |
产权排序 | 2 |
文献子类 | Article |
英文摘要 | Network in network (NiN) is an effective instance and an important extension of deep convolutional neural network consisting of alternating convolutional layers and pooling layers. Instead of using a linear filter for convolution, NiN utilizes shallow multilayer perceptron (MLP), a nonlinear function, to replace the linear filter. Because of the powerfulness of MLP and 1 x 1 convolutions in spatial domain, NiN has stronger ability of feature representation and hence results in better recognition performance. However, MLP itself consists of fully connected layers that give rise to a large number of parameters. In this paper, we propose to replace dense shallow MLP with sparse shallow MLP. One or more layers of the sparse shallow MLP are sparely connected in the channel dimension or channel-spatial domain. The proposed method is implemented by applying unshared convolution across the channel dimension and applying shared convolution across the spatial dimension in some computational layers. The proposed method is called convolution in convolution (CiC). The experimental results on the CIFAR10 data set, augmented CIFAR10 data set, and CIFAR100 data set demonstrate the effectiveness of the proposed CiC method. |
学科主题 | Computer Science, Artificial Intelligence |
WOS关键词 | Learning Deep ; Representation ; Recognition ; Images |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
WOS记录号 | WOS:000430729100016 |
资助机构 | National Basic Research Program of China (973 Program)(2014CB340400) ; National Natural Science Foundation of China(61632081) ; Hainan Tropical Ocean University(QYXB201501) |
内容类型 | 期刊论文 |
源URL | [http://ir.opt.ac.cn/handle/181661/30076] |
专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
通讯作者 | Pang, YW (reprint author), Tianjin Univ, Sch Elect & Informat Enginnering, Tianjin 300072, Peoples R China. |
作者单位 | 1.Tianjin Univ, Sch Elect & Informat Enginnering, Tianjin 300072, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr OPT IMagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China |
推荐引用方式 GB/T 7714 | Pang, Yanwei,Sun, Manli,Jiang, Xiaoheng,et al. Convolution in Convolution for Network in Network[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(5):1587-1597. |
APA | Pang, Yanwei,Sun, Manli,Jiang, Xiaoheng,Li, Xuelong,&Pang, YW .(2018).Convolution in Convolution for Network in Network.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(5),1587-1597. |
MLA | Pang, Yanwei,et al."Convolution in Convolution for Network in Network".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.5(2018):1587-1597. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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