Abstract
To improve the accuracy of face recognition when there are wrong-labeled samples, a new deep face recognition model with cosine boundary loss is proposed in this paper. First, the proposed model uses the cosine similarity to determine the boundary that divides training samples into easy samples, semi-hard samples and harder samples, which play different roles during the training process. Then, an adaptive weighted piecewise loss function is developed to emphasize semi-hard samples and suppress wrong-labeled samples in harder samples by assigning different weights to related types of samples during different training stages. Compared with the state-of-the-art face recognition methods, i.e., CosFace, CurricularFace, and EnhanceFace, experimental results on CFP_FF, CFP_FP, AgeDB, LFW, CALFW, CPLFW, VGG2_FP datasets demonstrate that the proposed method can effectively reduce the impact of the wrong-labeled samples and provide a better accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Shan, X., Lu, Y., Li, Q., Wen, Y.: Model-based transfer learning and sparse coding for partial face recognition. IEEE Trans. Circuits Syst. Video Technol. 31(11), 4347–4356 (2021)
Wang, M., Deng, W.: Deep face recognition: a survey. Neurocomputing 429, 215–244 (2021)
Deng, J., Zhou, Y., Zafeiriou, S.: Marginal loss for deep face recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Hawaii, pp. 2006–2014 (2017)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, pp. 815–823 (2015)
Wu, Y., Liu, H., Li, J., Fu, Y.: Deep face recognition with center invariant loss. In: Proceedings of the on Thematic Workshops of ACM Multimedia 2017 (Thematic Workshops 2017), pp. 408–414. Association for Computing Machinery, New York (2017)
Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: deep hypersphere embedding for face recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, pp. 6738–6746 (2017)
Wang, H., et al.: Cosface: large margin cosine loss for deep face recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, pp. 5265–5274 (2018)
Deng, J., Guo, J., Yang, J., Xue, N., Kotsia, I., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, pp. 4690–4699 (2019)
Huang, Y., et al.: Curricularface: adaptive curriculum learning loss for deep face recognition. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, pp. 5900–5909 (2020)
Hu, W., Huang, Y., Zhang, F., Li, R.: Noise-tolerant paradigm for training face recognition CNNs. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, pp. 11879–11888 (2019)
Wang, J., Zheng, C., Yang, X., Yang, L.: Enhanceface: adaptive weighted softmax loss for deep face recognition. IEEE Signal Process. Lett. 29, 65–69 (2022)
Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch (2014). https://arxiv.org/pdf/1411.7923.pdf
Bansal, A., Nanduri, A., Castillo, C.D., Ranjan, R., Chellappa, R.: Umdfaces: an annotated face dataset for training deep networks. In: 2017 IEEE International Joint Conference on Biometrics (IJCB), pp. 464–473 (2017)
Huang, G., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Tech. rep. University of Massachusetts (2007)
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), Lake Placid, pp. 1–9 (2016)
Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: Agedb: the first manually collected, in-the-wild age database. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, pp. 1997–2005 (2017)
Zheng, T., Deng, W.: Cross-pose IFW: a database for studying cross-pose face recognition in unconstrained environments. arXiv preprint arXiv:1708.08197(2017)
Zheng, T., Deng, W., Hu, J.: Cross-age IFW: a database for studying cross-age face recognition in unconstrained environments. Tech. rep. Beijing University of Posts and Telecommunications (2018)
Cao, Q., Shen, L., Xie, W., Parkhi, O.M., Zisserman, A.: Vggface2: a dataset for recognising faces across pose and age. In: IEEE International Conference on Automatic Face and Gesture Recognition, Xi’an, pp. 67–74 (2018)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)
Acknowledgements
This study was supported by National Natural Science Foundation of China under Grant 41771375, Grant 31860182, and Grant 41961053, Natural Science Foundation of Henan under Grant 232300421071, Scientific and Technological Innovation Talent in Universities of Henan Province under Grant 22HASTIT015, and Youth key Teacher of Henan under Grant 2020GGJS030.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zheng, C., Chen, Y., Li, J., Wang, Y., Wang, L. (2024). Deep Face Recognition with Cosine Boundary Softmax Loss. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14429. Springer, Singapore. https://doi.org/10.1007/978-981-99-8469-5_24
Download citation
DOI: https://doi.org/10.1007/978-981-99-8469-5_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8468-8
Online ISBN: 978-981-99-8469-5
eBook Packages: Computer ScienceComputer Science (R0)