Article

BoundaryFace: A Mining Framework with Noise Label Self-correction for Face Recognition

Authors:

Xun GongAuthors Info & Claims

Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XIII

Pages 91 - 106

https://doi.org/10.1007/978-3-031-19778-9_6

Published: 23 October 2022 Publication History

Abstract

Face recognition has made tremendous progress in recent years due to the advances in loss functions and the explosive growth in training sets size. A properly designed loss is seen as key to extract discriminative features for classification. Several margin-based losses have been proposed as alternatives of softmax loss in face recognition. However, two issues remain to consider: 1) They overlook the importance of hard sample mining for discriminative learning. 2) Label noise ubiquitously exists in large-scale datasets, which can seriously damage the model’s performance. In this paper, starting from the perspective of decision boundary, we propose a novel mining framework that focuses on the relationship between a sample’s ground truth class center and its nearest negative class center. Specifically, a closed-set noise label self-correction module is put forward, making this framework work well on datasets containing a lot of label noise. The proposed method consistently outperforms SOTA methods in various face recognition benchmarks. Training code has been released at https://gitee.com/swjtugx/classmate/tree/master/OurGroup/BoundaryFace.

References

[1]

Cao, D., Zhu, X., Huang, X., Guo, J., Lei, Z.: Domain balancing: face recognition on long-tailed domains. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5671–5679 (2020)

[2]

Chen, B.: Angular visual hardness. In: International Conference on Machine Learning, pp. 1637–1648. PMLR (2020)

[3]

Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690–4699 (2019)

[4]

Deng W, Jiani H, Zhang N, Chen B, and Guo J Fine-grained face verification: FGLFW database, baselines, and human-DCMN partnership Pattern Recogn. 2017 66 63-73

[5]

Guo, J., Zhu, X., Zhao, C., Cao, D., Lei, Z., Li, S.Z.: Learning meta face recognition in unseen domains. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6163–6172 (2020)

[6]

He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

[7]

Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: Workshop on Faces in ‘Real-Life’ Images: Detection, Alignment, and Recognition (2008)

[8]

Huang Y et al. Vedaldi A, Bischof H, Brox T, Frahm J-M, et al. Improving face recognition from hard samples via distribution distillation loss Computer Vision – ECCV 2020 2020 Cham Springer 138-154

[9]

Huang, Y., et al.: CurricularFace: adaptive curriculum learning loss for deep face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5901–5910 (2020)

[10]

Kemelmacher-Shlizerman, I., Seitz, S.M., Miller, D., Brossard, E.: The MegaFace benchmark: 1 million faces for recognition at scale. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4873–4882 (2016)

[11]

Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

[12]

Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212–220 (2017)

[13]

Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: ICML, vol. 2, p. 7 (2016)

[14]

Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: AgeDB: the first manually collected, in-the-wild age database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 51–59 (2017)

[15]

Paszke, A., et al.: Automatic differentiation in PyTorch (2017)

[16]

Ranjan, R., Castillo, C.D., Chellappa, R.: L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507 (2017)

[17]

Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)

[18]

Sengupta, S., Chen, J.-C., Castillo, C., Patel, V.M., Chellappa, R., Jacobs, D.W.: Frontal to profile face verification in the wild. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–9. IEEE (2016)

[19]

Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 761–769 (2016)

[20]

Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Advances in Neural Information Processing Systems, pp. 1857–1865 (2016)

[21]

Sun, Y.: Deep learning face representation by joint identification-verification. The Chinese University of Hong Kong, Hong Kong (2015)

[22]

Tai, Y., et al.: Towards highly accurate and stable face alignment for high-resolution videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8893–8900 (2019)

[23]

Wang F et al. Ferrari V, Hebert M, Sminchisescu C, Weiss Y, et al. The devil of face recognition is in the noise Computer Vision – ECCV 2018 2018 Cham Springer 780-795

[24]

Wang F, Cheng J, Liu W, and Liu H Additive margin softmax for face verification IEEE Signal Process. Lett. 2018 25 7 926-930

[25]

Wang, F., Xiang, X., Cheng, J., Yuille, A.L.: NormFace: L2 hypersphere embedding for face verification. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1041–1049 (2017)

[26]

Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5265–5274 (2018)

[27]

Wang, M., Deng, W., Hu, J., Peng, J., Tao, X., Huang, Y.: Racial faces in-the-wild: reducing racial bias by deep unsupervised domain adaptation. arXiv preprint arXiv:1812.00194 (2018)

[28]

Wang, X., Zhang, S., Wang, S., Tianyu, F., Shi, H., Mei, T.: MIS-classified vector guided softmax loss for face recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12241–12248 (2020)

[29]

Wen Y, Zhang K, Li Z, and Qiao Yu Leibe B, Matas J, Sebe N, and Welling M A discriminative feature learning approach for deep face recognition Computer Vision – ECCV 2016 2016 Cham Springer 499-515

[30]

Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch. arXiv preprint arXiv:1411.7923 (2014)

[31]

Yuan, Y., Yang, K., Zhang, C.: Feature incay for representation regularization. arXiv preprint arXiv:1705.10284 (2017)

[32]

Zhang K, Zhang Z, Li Z, and Qiao Yu Joint face detection and alignment using multitask cascaded convolutional networks IEEE Signal Process. Lett. 2016 23 10 1499-1503

[33]

Zhang, X., Zhao, R., Qiao, Y., Wang, X., Li, H.: AdaCos: adaptively scaling cosine logits for effectively learning deep face representations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10823–10832 (2019)

[34]

Zheng, T., Deng, W.: Cross-pose LFW: a database for studying cross-pose face recognition in unconstrained environments. Beijing University of Posts and Telecommunications, Technical report, 5:7 (2018)

[35]

Zheng, T., Deng, W., Hu, J.: Cross-age LFW: a database for studying cross-age face recognition in unconstrained environments. arXiv preprint arXiv:1708.08197 (2017)

Cited By

Xin YZhou YJiang JCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)RobustFace: Adaptive Mining of Noise and Hard Samples for Robust Face RecognitionsProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681231(5065-5073)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681231

Index Terms

BoundaryFace: A Mining Framework with Noise Label Self-correction for Face Recognition
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
        Supervised learning by classification
    2. Machine learning approaches
      1. Classification and regression trees

Index terms have been assigned to the content through auto-classification.

Recommendations

RobustFace: Adaptive Mining of Noise and Hard Samples for Robust Face Recognitions
MM '24: Proceedings of the 32nd ACM International Conference on Multimedia

While margin-based deep face recognition models, such as ArcFace and AdaFace, have achieved remarkable successes over recent years, they may suffer from degraded performances when encountering training sets corrupted with noises. This is often inevitable ...
Self-paced Robust Deep Face Recognition with Label Noise
Advances in Knowledge Discovery and Data Mining
Abstract
Deep face recognition has achieved rapid development but still suffers from occlusions, illumination and pose variations, especially for face identification. The success of deep learning models in face recognition lies in large-scale high quality ...
A novel label learning algorithm for face recognition

Gaussian fields and harmonic functions (GFHF) and flexible manifold embedding (FME) provide effective means to label learning, by virtue of which we can evaluate labels of unknown samples (i.e. samples with unknown labels). When applied to face ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XIII

Oct 2022

803 pages

ISBN:978-3-031-19777-2

DOI:10.1007/978-3-031-19778-9

Editors:
Shai Avidan
Tel Aviv University, Tel Aviv, Israel
,
Gabriel Brostow
University College London, London, UK
,
Moustapha Cissé
Google AI, Accra, Ghana
,
Giovanni Maria Farinella
University of Catania, Catania, Italy
,
Tal Hassner
Facebook (United States), Menlo Park, CA, USA

© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 23 October 2022

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Xin YZhou YJiang JCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)RobustFace: Adaptive Mining of Noise and Hard Samples for Robust Face RecognitionsProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681231(5065-5073)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681231

View Options

View options

Media

Figures

Other

Tables

View Table of Contents