Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions

doi:10.1109/TPAMI.2023.3298836

	Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions
	Ren, Min1 ; Wang, Yunlong2 ; Zhu, Yuhao 3; Zhang, Kunbo2 ; Sun, Zhenan2,4
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
	2023-12-01
卷号	45 期号:12 页码:15120-15136
通讯作者	Sun, Zhenan(znsun@nlpr.ia.ac.cn)
摘要	Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrating the merits of both CNNs and graph models to overcome occlusion problems in biometric recognition, called multiscale dynamic graph representation (MS-DGR). More specifically, a group of deep features reflected on certain subregions is recrafted into a feature graph (FG). Each node inside the FG is deemed to characterize a specific local region of the input sample, and the edges imply the co-occurrence of non-occluded regions. By analyzing the similarities of the node representations and measuring the topological structures stored in the adjacent matrix, the proposed framework leverages dynamic graph matching to judiciously discard the nodes corresponding to the occluded parts. The multiscale strategy is further incorporated to attain more diverse nodes representing regions of various sizes. Furthermore, the proposed framework exhibits a more illustrative and reasonable inference by showing the paired nodes. Extensive experiments demonstrate the superiority of the proposed framework, which boosts the accuracy in both natural and occlusion-simulated cases by a large margin compared with that of baseline methods.
关键词	Biometrics deep learning face recognition graph neural networks iris recognition
DOI	10.1109/TPAMI.2023.3298836
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2022YFC3310400] ; National Natural Science Foundation of China[62276025] ; National Natural Science Foundation of China[62276263] ; National Natural Science Foundation of China[62006225] ; National Natural Science Foundation of China[62071468] ; Shenzhen Technology Plan Program[KQTD20170331093217368]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Shenzhen Technology Plan Program
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001130146400066
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55534
专题	多模态人工智能系统全国重点实验室
通讯作者	Sun, Zhenan
作者单位	1.Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China 2.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.China Acad Railway Sci, Postgrad Dept, Beijing 100081, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Ren, Min,Wang, Yunlong,Zhu, Yuhao,et al. Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(12):15120-15136.
APA	Ren, Min,Wang, Yunlong,Zhu, Yuhao,Zhang, Kunbo,&Sun, Zhenan.(2023).Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(12),15120-15136.
MLA	Ren, Min,et al."Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.12(2023):15120-15136.