Institute of Computing Technology, Chinese Academy IR
AMI-Net: Convolution Neural Networks With Affine Moment Invariants | |
Hao, You1,2; Li, Qi1,2; Mo, Hanlin1,2; Zhang, He1,2; Li, Hua1 | |
2018-07-01 | |
发表期刊 | IEEE SIGNAL PROCESSING LETTERS |
ISSN | 1070-9908 |
卷号 | 25期号:7页码:1064-1068 |
摘要 | Affine moment invariant (AMI) is a kind of hand-crafted image feature, which is invariant to affine transformations. This property is precisely what the standard convolution neural network (CNN) is difficult to achieve. In this letter, we present a kind of network architecture to introduce AMI into CNN, which is called AMI-Net. We achieved this by calculating AMI on the feature maps of the hidden layers. These AMIs will be concatenated with the standard CNN's FC layer to determine the network's final output. By calculating AMI on the feature maps, we can not only extend the dimension of AMIs, but also introduce affine transformation invariant into CNN. Two network architectures and training strategies of AMI-Net are illuminated, one is two-stage, and the other is end-to-end. To prove the effectiveness of the AMI-Net, several experiments have been conducted on common image datasets, MNIST, MNIST-rot, affNIST, SVHN, and CIFAR-10. By comparing with the corresponding standard CNN, respectively, we verify the validity of AMI-net. |
关键词 | Affine moment invariants (AMIs) convolution neural network (CNN) transformation invariant |
DOI | 10.1109/LSP.2018.2843296 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key R&D Program of China[2017YFB1002703] ; National Science Foundation of China[61379082] ; National Science Foundation of China[61227802] |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Electrical & Electronic |
WOS记录号 | WOS:000435520200008 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://119.78.100.204/handle/2XEOYT63/5202 |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Hao, You |
作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Hao, You,Li, Qi,Mo, Hanlin,et al. AMI-Net: Convolution Neural Networks With Affine Moment Invariants[J]. IEEE SIGNAL PROCESSING LETTERS,2018,25(7):1064-1068. |
APA | Hao, You,Li, Qi,Mo, Hanlin,Zhang, He,&Li, Hua.(2018).AMI-Net: Convolution Neural Networks With Affine Moment Invariants.IEEE SIGNAL PROCESSING LETTERS,25(7),1064-1068. |
MLA | Hao, You,et al."AMI-Net: Convolution Neural Networks With Affine Moment Invariants".IEEE SIGNAL PROCESSING LETTERS 25.7(2018):1064-1068. |
条目包含的文件 | 条目无相关文件。 |
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