CASIA OpenIR
Mutual Component Convolutional Neural Networks for Heterogeneous Face Recognition
Deng, Zhongying1,2; Peng, Xiaojiang3; Li, Zhifeng4; Qiao, Yu2,5
Source PublicationIEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN1057-7149
2019-06-01
Volume28Issue:6Pages:3102-3114
Corresponding AuthorQiao, Yu(yu.qiao@siat.ac.cn)
AbstractHeterogeneous face recognition (HFR) aims to identify a person from different facial modalities, such as visible and near-infrared images. The main challenges of HFR lie in the large modality discrepancy and insufficient training samples. In this paper, we propose the mutual component convolutional neural network (MC-CNN), a modal-invariant deep learning framework, to tackle these two issues simultaneously. Our MC-CNN incorporates a generative module, i.e., the mutual component analysis (MCA), into modern deep CNNs by viewing MCA as a special fully connected (FC) layer. Based on deep features, this FC layer is designed to extract modal-independent hidden factors and is updated according to maximum likelihood analytic formulation instead of back propagation which prevents overfitting from limited data naturally. In addition, we develop an MCA loss to update the network for modal-invariant feature learning. Extensive experiments show that our MC-CNN outperforms several fine-tuned baseline models significantly. Our methods achieve the state-of-the-art performance on the CASIA NIR-VIS 2.0, CUHK NIR-VIS, and IIIT-D Sketch datasets.
KeywordHeterogeneous face recognition mutual component analysis mutual component convolutional neural network
DOI10.1109/TIP.2019.2894272
WOS KeywordDISCRIMINANT-ANALYSIS ; REPRESENTATION ; IMAGES
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[U1613211] ; National Natural Science Foundation of China[U1813218] ; Shenzhen Research Program[JCYJ20170818164704758] ; Shenzhen Research Program[JCYJ20150925163005055] ; Tencent AI Lab Rhino-Bird Joint Research Program[JR201807]
Funding OrganizationNational Natural Science Foundation of China ; Shenzhen Research Program ; Tencent AI Lab Rhino-Bird Joint Research Program
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000467079800003
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/24594
Collection中国科学院自动化研究所
Corresponding AuthorQiao, Yu
Affiliation1.Univ Chinese Acad Sci, Shenzhen Coll Adv Technol, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Comp Vis & Pattern Recognit, Shenzhen 518000, Peoples R China
3.Chinese Acad Sci, Shenzhen Inst Adv Technol, Guangdong Prov Key Lab Comp Vis & Virtual Real, Shenzhen 518000, Peoples R China
4.Tencent AI Lab, Shenzhen 518000, Peoples R China
5.Chinese Acad Sci, SIAT SenseTime Joint Lab, Shenzhen 518000, Peoples R China
Recommended Citation
GB/T 7714
Deng, Zhongying,Peng, Xiaojiang,Li, Zhifeng,et al. Mutual Component Convolutional Neural Networks for Heterogeneous Face Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(6):3102-3114.
APA Deng, Zhongying,Peng, Xiaojiang,Li, Zhifeng,&Qiao, Yu.(2019).Mutual Component Convolutional Neural Networks for Heterogeneous Face Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(6),3102-3114.
MLA Deng, Zhongying,et al."Mutual Component Convolutional Neural Networks for Heterogeneous Face Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.6(2019):3102-3114.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Deng, Zhongying]'s Articles
[Peng, Xiaojiang]'s Articles
[Li, Zhifeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Deng, Zhongying]'s Articles
[Peng, Xiaojiang]'s Articles
[Li, Zhifeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Deng, Zhongying]'s Articles
[Peng, Xiaojiang]'s Articles
[Li, Zhifeng]'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.