Towards NIR-VIS Masked Face Recognition

被引:32
作者
Du, Hang [1 ]
Shi, Hailin [2 ]
Liu, Yinglu [2 ]
Zeng, Dan [1 ]
Mei, Tao [2 ]
机构
[1] Shanghai Univ, Shanghai Inst Adv Commun, Joint Int Res Lab Specialty Fiber Opt & Adv Commu, Key Lab Specialty Fiber Opt & Opt Access Networks, Shanghai 200444, Peoples R China
[2] JD AI Res, Beijing 100029, Peoples R China
基金
国家重点研发计划;
关键词
Face recognition; Training; Faces; Prototypes; Probes; Mutual information; COVID-19; Heterogeneous; NIR-VIS; cross modality; masked face recognition;
D O I
10.1109/LSP.2021.3071663
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Near-infrared to visible (NIR-VIS) face recognition is the most common case in heterogeneous face recognition, which aims to match a pair of face images captured from two different modalities. Existing deep learning based methods have made remarkable progress in NIR-VIS face recognition, while it encounters certain newly-emerged difficulties during the pandemic of COVID-19, since people are supposed to wear facial masks to cut off the spread of the virus. We define this task as NIR-VIS masked face recognition, and find it problematic with the masked face in the NIR probe image. First, the lack of masked face data is a challenging issue for the network training. Second, most of the facial parts (cheeks, mouth, nose etc.) are fully occluded by the mask, which leads to a large amount of loss of information. Third, the domain gap still exists in the remaining facial parts. In such scenario, the existing methods suffer from significant performance degradation caused by the above issues. In this paper, we aim to address the challenge of NIR-VIS masked face recognition from the perspectives of training data and training method. Specifically, we propose a novel heterogeneous training method to maximize the mutual information shared by the face representation of two domains with the help of semi-siamese networks. In addition, a 3D face reconstruction based approach is employed to synthesize masked face from the existing NIR image. Resorting to these practices, our solution provides the domain-invariant face representation which is also robust to the mask occlusion. Extensive experiments on three NIR-VIS face datasets demonstrate the effectiveness and cross-dataset-generalization capacity of our method.
引用
收藏
页码:768 / 772
页数:5
相关论文
共 27 条
[1]  
Chen J, 2009, PROC CVPR IEEE, P156, DOI 10.1109/CVPRW.2009.5206832
[2]   MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices [J].
Chen, Sheng ;
Liu, Yang ;
Gao, Xiang ;
Han, Zhen .
BIOMETRIC RECOGNITION, CCBR 2018, 2018, 10996 :428-438
[3]   ArcFace: Additive Angular Margin Loss for Deep Face Recognition [J].
Deng, Jiankang ;
Guo, Jia ;
Xue, Niannan ;
Zafeiriou, Stefanos .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :4685-4694
[4]   Polarimetric Thermal to Visible Face Verification via Self-Attention Guided Synthesis [J].
Di, Xing ;
Riggan, Benjamin S. ;
Hu, Shuowen ;
Short, Nathaniel J. ;
Patel, Vishal M. .
2019 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB), 2019,
[5]   Masked Face Recognition with Latent Part Detection [J].
Ding, Feifei ;
Peng, Peixi ;
Huang, Yangru ;
Geng, Mengyue ;
Tian, Yonghong .
MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, :2281-2289
[6]   Semi-Siamese Training for Shallow Face Learning [J].
Du, Hang ;
Shi, Hailin ;
Liu, Yuchi ;
Wang, Jun ;
Lei, Zhen ;
Zeng, Dan ;
Mei, Tao .
COMPUTER VISION - ECCV 2020, PT IV, 2020, 12349 :36-53
[7]   Cross-Spectral Face Hallucination via Disentangling Independent Factors [J].
Duan, Boyan ;
Fu, Chaoyou ;
Li, Yi ;
Song, Xingguang ;
He, Ran .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :7927-7935
[8]   Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network [J].
Feng, Yao ;
Wu, Fan ;
Shao, Xiaohu ;
Wang, Yanfeng ;
Zhou, Xi .
COMPUTER VISION - ECCV 2018, PT XIV, 2018, 11218 :557-574
[9]   Masked Face Recognition with Generative Data Augmentation and Domain Constrained Ranking [J].
Geng, Mengyue ;
Peng, Peixi ;
Huang, Yangru ;
Tian, Yonghong .
MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, :2246-2254
[10]   PaSTRI: Error-Bounded Lossy Compression for Two-Electron Integrals in Quantum Chemistry [J].
Gok, Ali Murat ;
Di, Sheng ;
Alexeev, Yuri ;
Tao, Dingwen ;
Mironov, Vladimir ;
Liang, Xin ;
Cappello, Franck .
2018 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING (CLUSTER), 2018, :1-11