FocusFace: Multi-task Contrastive Learning for Masked Face Recognition

SARS-CoV-2 has presented direct and indirect challenges to the scientific community. One of the most prominent indirect challenges advents from the mandatory use of face masks in a large number of countries. Face recognition methods struggle to perform identity verification with similar accuracy on masked and unmasked individuals. It has been shown that the performance of these methods drops considerably in the presence of face masks, especially if the reference image is unmasked. We propose FocusFace, a multi-task architecture that uses contrastive learning to be able to accurately perform masked face recognition. The proposed architecture is designed to be trained from scratch or to work on top of state-of-the-art face recognition methods without sacrificing the capabilities of a existing models in conventional face recognition tasks. We also explore different approaches to design the contrastive learning module. Results are presented in terms of masked-masked (M-M) and unmasked-masked (U-M) face verification performance. For both settings, the results are on par with published methods, but for M-M specifically, the proposed method was able to outperform all the solutions that it was compared to. We further show that when using our method on top of already existing methods the training computational costs decrease significantly while retaining similar performances. The implementation and the trained models are available at GitHub.

[1]  G. C. Zacharias,et al.  An empirical study of the impact of masks on face recognition , 2022, Pattern Recognit..

[2]  Naser Damer,et al.  The Effect of Wearing a Face Mask on Face Image Quality , 2021, 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021).

[3]  Arjan Kuijper,et al.  ElasticFace: Elastic Margin Loss for Deep Face Recognition , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[4]  Naser Damer,et al.  My Eyes Are Up Here: Promoting Focus on Uncovered Regions in Masked Face Recognition , 2021, 2021 International Conference of the Biometrics Special Interest Group (BIOSIG).

[5]  Naser Damer,et al.  MixFaceNets: Extremely Efficient Face Recognition Networks , 2021, 2021 IEEE International Joint Conference on Biometrics (IJCB).

[6]  Shiguang Shan,et al.  MFR 2021: Masked Face Recognition Competition , 2021, 2021 IEEE International Joint Conference on Biometrics (IJCB).

[7]  Arjan Kuijper,et al.  Extended evaluation of the effect of real and simulated masks on face recognition performance , 2021, IET Biom..

[8]  P. Leskovský,et al.  Boosting Masked Face Recognition with Multi-Task ArcFace , 2021, 2022 16th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[9]  F. Zhou,et al.  MagFace: A Universal Representation for Face Recognition and Quality Assessment , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Arjan Kuijper,et al.  Self-restrained triplet loss for accurate masked face recognition , 2021, Pattern Recognit..

[11]  Arjan Kuijper,et al.  Real masks and spoof faces: On the masked face presentation attack detection , 2021, Pattern Recognition.

[12]  Naser Damer,et al.  Masked Face Recognition: Human vs. Machine , 2021, ArXiv.

[13]  A. Nautsch,et al.  Biometrics in the Era of COVID-19: Challenges and Opportunities , 2021, IEEE Transactions on Technology and Society.

[14]  Yonggang Lu,et al.  Cropping and attention based approach for masked face recognition , 2021, Applied Intelligence.

[15]  Patrick Grother,et al.  Ongoing Face Recognition Vendor Test (FRVT) Part 6B: Face recognition accuracy with face masks using post-COVID-19 algorithms , 2020 .

[16]  Debing Zhang,et al.  Partial FC: Training 10 Million Identities on a Single Machine , 2020, 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).

[17]  Arijit Raychowdhury,et al.  Masked Face Recognition for Secure Authentication , 2020, ArXiv.

[18]  Gunasekaran Manogaran,et al.  A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic , 2020, Measurement.

[19]  Naser Damer,et al.  The Effect of Wearing a Mask on Face Recognition Performance: an Exploratory Study , 2020, 2020 International Conference of the Biometrics Special Interest Group (BIOSIG).

[20]  Dongxiao Li,et al.  Identifying Facemask-Wearing Condition Using Image Super-Resolution with Classification Network to Prevent COVID-19 , 2020, Sensors.

[21]  Feiyue Huang,et al.  CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Yichen Wei,et al.  Circle Loss: A Unified Perspective of Pair Similarity Optimization , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[24]  Wei Liu,et al.  Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Jiwen Lu,et al.  UniformFace: Learning Deep Equidistributed Representation for Face Recognition , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Kayee K. Hanaoka,et al.  Ongoing Face Recognition Vendor Test (FRVT) part 6A: , 2018 .

[27]  S. Zafeiriou,et al.  ArcFace: Additive Angular Margin Loss for Deep Face Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Horst Possegger,et al.  Grid Loss: Detecting Occluded Faces , 2016, ECCV.

[29]  Yuxiao Hu,et al.  MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition , 2016, ECCV.

[30]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[31]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Dmitry O. Gorodnichy,et al.  Automated border control: Problem formalization , 2014, 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management (CIBIM).

[34]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[35]  Marc Roeschlin,et al.  Mobile Biometrics in Financial Services: A Five Factor Framework , 2017 .