NSSC OpenIR  > 空间技术部
Template Matching Based on Geometric Invariance in Deep Neural Network
Cao, Yaming; Yang, Zhen; Wang, Haijiao; Peng, Xiaodong; Gao, Chen; Li, Yun
Department空间技术部
Source PublicationIEEE ACCESS
2019
Volume7Pages:82174-82182
DOI10.1109/ACCESS.2019.2923674
ISSN2169-3536
Language英语
KeywordDeep neural network geometric invariant interpretability template match adversarial example
AbstractMachine learning models, especially deep neural networks (DNNs), have achieved state of the art in computer vision and speech recognition. However, with wide applications of DNNs, some problems have appeared, such as lack of interpretability and vulnerable to adversarial examples. Whether the judgment of the model is consistent with that of human is a key to the wide application and development of neural networks. In this paper, we propose a novel and interpretable method to enable the model to make the same judgment as humans in the adversarial examples, which is based on the geometric invariance between images of the same category. Template matching is combined with convolution neural network during the training and testing stage. Moreover, we manage to give a theorical proof. The geometric invariance features got from the template matching are fused with the features extracted by the convolutional layers. The experimental results demonstrate the temp_model (network added the template matching) has a higher test accuracy both on benchmark sequences and adversarial examples, and we use a visual method to explain the reason why adding template can make the network perform better. The generality and convergence of the network improve without increasing the model size and training time after adding the template as common sense.
Indexed BySCI
Citation statistics
Document Type期刊论文
Identifierhttp://ir.nssc.ac.cn/handle/122/7065
Collection空间技术部
Recommended Citation
GB/T 7714
Cao, Yaming,Yang, Zhen,Wang, Haijiao,et al. Template Matching Based on Geometric Invariance in Deep Neural Network[J]. IEEE ACCESS,2019,7:82174-82182.
APA Cao, Yaming,Yang, Zhen,Wang, Haijiao,Peng, Xiaodong,Gao, Chen,&Li, Yun.(2019).Template Matching Based on Geometric Invariance in Deep Neural Network.IEEE ACCESS,7,82174-82182.
MLA Cao, Yaming,et al."Template Matching Based on Geometric Invariance in Deep Neural Network".IEEE ACCESS 7(2019):82174-82182.
Files in This Item:
File Name/Size DocType Version Access License
201982174-82182.pdf(8369KB)期刊论文出版稿开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cao, Yaming]'s Articles
[Yang, Zhen]'s Articles
[Wang, Haijiao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cao, Yaming]'s Articles
[Yang, Zhen]'s Articles
[Wang, Haijiao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cao, Yaming]'s Articles
[Yang, Zhen]'s Articles
[Wang, Haijiao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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