Deformable face net for pose invariant face recognition

doi:10.1016/j.patcog.2019.107113

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Deformable face net for pose invariant face recognition
	He, Mingjie 1,2; Zhang, Jie 2; Shan, Shiguang 1,2,3; Kan, Meina 2; Chen, Xilin 1,2
刊名	PATTERN RECOGNITION
	2020-04-01
卷号	100 页码:11
关键词	Pose-invariant face recognition Displacement consistency loss Pose-triplet loss
ISSN号	0031-3203
DOI	10.1016/j.patcog.2019.107113
英文摘要	Unconstrained face recognition still remains a challenging task due to various factors such as pose, expression, illumination, partial occlusion, etc. In particular, the most significant appearance variations are stemmed from poses which leads to severe performance degeneration. In this paper, we propose a novel Deformable Face Net (DFN) to handle the pose variations for face recognition. The deformable convolution module attempts to simultaneously learn face recognition oriented alignment and identity-preserving feature extraction. The displacement consistency loss (DCL) is proposed as a regularization term to enforce the learnt displacement fields for aligning faces to be locally consistent both in the orientation and amplitude since faces possess strong structure. Moreover, the identity consistency loss (ICL) and the pose-triplet loss (PTL) are designed to minimize the intra-class feature variation caused by different poses and maximize the inter-class feature distance under the same poses. The proposed DFN can effectively handle pose invariant face recognition (PIFR). Extensive experiments show that the proposed DFN outperforms the state-of-the-art methods, especially on the datasets with large poses. (C) 2019 Published by Elsevier Ltd.
资助项目	National Key R&D Program of China[2017YFA070080 0] ; Natural Science Foundation of China[61806188 and61772496]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000533530800016
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/15361]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shan, Shiguang
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Chinese Acad Sci CAS, Beijing 100190, Peoples R China 3.Peng Cheng Lab, Shenzhen 518055, Peoples R China
推荐引用方式 GB/T 7714	He, Mingjie,Zhang, Jie,Shan, Shiguang,et al. Deformable face net for pose invariant face recognition[J]. PATTERN RECOGNITION,2020,100:11.
APA	He, Mingjie,Zhang, Jie,Shan, Shiguang,Kan, Meina,&Chen, Xilin.(2020).Deformable face net for pose invariant face recognition.PATTERN RECOGNITION,100,11.
MLA	He, Mingjie,et al."Deformable face net for pose invariant face recognition".PATTERN RECOGNITION 100(2020):11.