中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 生物识别与安全技术研究中心
Consistent Sub-Decision Network for Low-Quality Masked Face Recognition

文献类型：期刊论文

作者Zhao, Weisong5,6; Zhu, Xiangyu2,3; Shi, Haichao4; Zhang, Xiao-Yu4; Lei, Zhen1,2,3
刊名IEEE SIGNAL PROCESSING LETTERS
出版日期2022
卷号29页码:1147-1151
关键词Face recognition Faces Feature extraction Facial features Training Knowledge engineering Drives COVID-19 masked face recognition low-quality
ISSN号1070-9908
DOI10.1109/LSP.2022.3170246
通讯作者Lei, Zhen(zlei@nlpr.ia.ac.cn)
英文摘要The COVID-19 pandemic makes wearing masks mandatory in supermarkets, pharmacies, public transport, etc. Existing facial recognition systems encounter severe performance degradation as the masks occlude key facial regions. Recently, simulation-based methods are proposed to generate masked faces from unmasked faces. However, among simulated faces, there are low-quality samples with negative occlusion, which leads to ambiguous or absent facial features. In this paper, we propose a consistent sub-decision network to obtain sub-decisions that correspond to different facial regions and constrain sub-decisions by weighted bidirectional KL divergence to make the network concentrate on the upper faces without occlusion. In addition, we perform knowledge distillation to drive the masked face embeddings towards an approximation of the original data distribution to mitigate the information loss. Experiments show that the proposed method performs better than the baseline on public masked face recognition datasets, i.e., RMFD, MFR2, and MLFW.
资助项目National Key Research & Development Program[2020YFC2003901] ; National Natural Science Foundation of China[61871378] ; National Natural Science Foundation of China[U2003111] ; National Natural Science Foundation of China[61876178] ; National Natural Science Foundation of China[61872367] ; National Natural Science Foundation of China[62176256] ; National Natural Science Foundation of China[62106264] ; National Natural Science Foundation of China[61976229] ; Youth Innovation Promotion Association CAS[Y2021131] ; InnoHK Program
WOS研究方向Engineering
语种英语
WOS记录号WOS:000793787300005
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research & Development Program ; National Natural Science Foundation of China ; Youth Innovation Promotion Association CAS ; InnoHK Program
源URL[http://ir.ia.ac.cn/handle/173211/49368]  
专题自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
通讯作者Lei, Zhen
作者单位1.Chinese Acad Sci, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong, Peoples R China
2.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Inst Automat, CBSR NLPR, Beijing, Peoples R China
4.Chinese Acad Sci, Inst Informat Engn, Beijing 100093, Peoples R China
5.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 100049, Peoples R China
6.Chinese Acad Sci, Inst Informat Engn, Beijing 100093, Peoples R China
推荐引用方式
GB/T 7714		 Zhao, Weisong,Zhu, Xiangyu,Shi, Haichao,et al. Consistent Sub-Decision Network for Low-Quality Masked Face Recognition[J]. IEEE SIGNAL PROCESSING LETTERS,2022,29:1147-1151.
APA Zhao, Weisong,Zhu, Xiangyu,Shi, Haichao,Zhang, Xiao-Yu,&Lei, Zhen.(2022).Consistent Sub-Decision Network for Low-Quality Masked Face Recognition.IEEE SIGNAL PROCESSING LETTERS,29,1147-1151.
MLA Zhao, Weisong,et al."Consistent Sub-Decision Network for Low-Quality Masked Face Recognition".IEEE SIGNAL PROCESSING LETTERS 29(2022):1147-1151.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。