Mutual Component Convolutional Neural Networks for Heterogeneous Face Recognition

doi:10.1109/TIP.2019.2894272

	Mutual Component Convolutional Neural Networks for Heterogeneous Face Recognition
	Deng, Zhongying 1,2; Peng, Xiaojiang 3; Li, Zhifeng 4; Qiao, Yu 2,5
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2019-06-01
卷号	28 期号:6 页码:3102-3114
关键词	Heterogeneous face recognition mutual component analysis mutual component convolutional neural network
ISSN号	1057-7149
DOI	10.1109/TIP.2019.2894272
通讯作者	Qiao, Yu(yu.qiao@siat.ac.cn)
英文摘要	Heterogeneous 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.
资助项目	National 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]
WOS关键词	DISCRIMINANT-ANALYSIS ; REPRESENTATION ; IMAGES
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000467079800003
资助机构	National Natural Science Foundation of China ; Shenzhen Research Program ; Tencent AI Lab Rhino-Bird Joint Research Program
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24593]
专题	中国科学院自动化研究所
通讯作者	Qiao, Yu
作者单位	1.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
推荐引用方式 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.