Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition (2201.07394v2)

Published 19 Jan 2022 in cs.CV

Abstract: Feature learning is a widely used method employed for large-scale face recognition. Recently, large-margin softmax loss methods have demonstrated significant enhancements on deep face recognition. These methods propose fixed positive margins in order to enforce intra-class compactness and inter-class diversity. However, the majority of the proposed methods do not consider the class imbalance issue, which is a major challenge in practice for developing deep face recognition models. We hypothesize that it significantly affects the generalization ability of the deep face models. Inspired by this observation, we introduce a novel adaptive strategy, called KappaFace, to modulate the relative importance based on class difficultness and imbalance. With the support of the von Mises-Fisher distribution, our proposed KappaFace loss can intensify the margin's magnitude for hard learning or low concentration classes while relaxing it for counter classes. Experiments conducted on popular facial benchmarks demonstrate that our proposed method achieves superior performance to the state-of-the-art.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. F. Wang, X. Xiang, J. Cheng, and A. L. Yuille, “Normface: L2 hypersphere embedding for face verification,” in Proceedings of the 25th ACM international conference on Multimedia, 2017, pp. 1041–1049.
  2. F. Schroff, D. Kalenichenko, and J. Philbin, “Facenet: A unified embedding for face recognition and clustering,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 815–823.
  3. Y. Wen, K. Zhang, Z. Li, and Y. Qiao, “A discriminative feature learning approach for deep face recognition,” in European conference on computer vision.   Springer, 2016, pp. 499–515.
  4. J. Deng, J. Guo, N. Xue, and S. Zafeiriou, “Arcface: Additive angular margin loss for deep face recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4690–4699.
  5. H. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, Z. Li, and W. Liu, “Cosface: Large margin cosine loss for deep face recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 5265–5274.
  6. W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song, “Sphereface: Deep hypersphere embedding for face recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 212–220.
  7. Y. Huang, Y. Wang, Y. Tai, X. Liu, P. Shen, S. Li, J. Li, and F. Huang, “Curricularface: adaptive curriculum learning loss for deep face recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 5901–5910.
  8. B. Liu, W. Deng, Y. Zhong, M. Wang, J. Hu, X. Tao, and Y. Huang, “Fair loss: Margin-aware reinforcement learning for deep face recognition,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 10 052–10 061.
  9. G. B. Huang, M. Mattar, T. Berg, and E. Learned-Miller, “Labeled faces in the wild: A database forstudying face recognition in unconstrained environments,” in Workshop on faces in’Real-Life’Images: detection, alignment, and recognition, 2008.
  10. S. Sengupta, J.-C. Chen, C. Castillo, V. M. Patel, R. Chellappa, and D. W. Jacobs, “Frontal to profile face verification in the wild,” in 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).   IEEE, 2016, pp. 1–9.
  11. T. Zheng and W. Deng, “Cross-pose lfw: A database for studying cross-pose face recognition in unconstrained environments,” Beijing University of Posts and Telecommunications, Tech. Rep, vol. 5, p. 7, 2018.
  12. S. Moschoglou, A. Papaioannou, C. Sagonas, J. Deng, I. Kotsia, and S. Zafeiriou, “Agedb: the first manually collected, in-the-wild age database,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp. 51–59.
  13. T. Zheng, W. Deng, and J. Hu, “Cross-age lfw: A database for studying cross-age face recognition in unconstrained environments,” arXiv preprint arXiv:1708.08197, 2017.
  14. C. Whitelam, E. Taborsky, A. Blanton, B. Maze, J. Adams, T. Miller, N. Kalka, A. K. Jain, J. A. Duncan, K. Allen et al., “Iarpa janus benchmark-b face dataset,” in proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2017, pp. 90–98.
  15. B. Maze, J. Adams, J. A. Duncan, N. Kalka, T. Miller, C. Otto, A. K. Jain, W. T. Niggel, J. Anderson, J. Cheney et al., “Iarpa janus benchmark-c: Face dataset and protocol,” in 2018 International Conference on Biometrics (ICB).   IEEE, 2018, pp. 158–165.
  16. L. Zhang, Q. Duan, D. Zhang, W. Jia, and X. Wang, “Advkin: Adversarial convolutional network for kinship verification,” IEEE transactions on cybernetics, vol. 51, no. 12, pp. 5883–5896, 2020.
  17. F. Wang, J. Cheng, W. Liu, and H. Liu, “Additive margin softmax for face verification,” IEEE Signal Processing Letters, vol. 25, no. 7, pp. 926–930, 2018.
  18. J. Hu, J. Lu, and Y.-P. Tan, “Discriminative deep metric learning for face verification in the wild,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 1875–1882.
  19. X. Liu, B. Vijaya Kumar, J. You, and P. Jia, “Adaptive deep metric learning for identity-aware facial expression recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2017, pp. 20–29.
  20. M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of cognitive neuroscience, vol. 3, no. 1, pp. 71–86, 1991.
  21. P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, “Eigenfaces vs. fisherfaces: Recognition using class specific linear projection,” IEEE Transactions on pattern analysis and machine intelligence, vol. 19, no. 7, pp. 711–720, 1997.
  22. T. Ahonen, A. Hadid, and M. Pietikäinen, “Face recognition with local binary patterns,” in Computer Vision-ECCV 2004: 8th European Conference on Computer Vision, Prague, Czech Republic, May 11-14, 2004. Proceedings, Part I 8.   Springer, 2004, pp. 469–481.
  23. V. A. Saeed, “A framework for recognition of facial expression using hog features,” International Journal of Mathematics, Statistics, and Computer Science, vol. 2, pp. 1–8, 2024.
  24. O. S. Kareem et al., “Face mask detection using haar cascades classifier to reduce the risk of coved-19,” International Journal of Mathematics, Statistics, and Computer Science, vol. 2, pp. 19–27, 2024.
  25. Q. T. Ngo and S. Yoon, “Facial expression recognition based on weighted-cluster loss and deep transfer learning using a highly imbalanced dataset,” Sensors, vol. 20, no. 9, p. 2639, 2020.
  26. Y. Sun, C. Cheng, Y. Zhang, C. Zhang, L. Zheng, Z. Wang, and Y. Wei, “Circle loss: A unified perspective of pair similarity optimization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 6398–6407.
  27. W. Liu, Y. Wen, Z. Yu, and M. Yang, “Large-margin softmax loss for convolutional neural networks.” in ICML, vol. 2, no. 3, 2016, p. 7.
  28. K. Sohn, “Improved deep metric learning with multi-class n-pair loss objective,” in Advances in neural information processing systems, 2016, pp. 1857–1865.
  29. H. Li, N. Wang, X. Ding, X. Yang, and X. Gao, “Adaptively learning facial expression representation via cf labels and distillation,” IEEE Transactions on Image Processing, vol. 30, pp. 2016–2028, 2021.
  30. H. Li, N. Wang, X. Yang, and X. Gao, “Crs-cont: A well-trained general encoder for facial expression analysis,” IEEE Transactions on Image Processing, vol. 31, pp. 4637–4650, 2022.
  31. H. Li, N. Wang, X. Yang, X. Wang, and X. Gao, “Towards semi-supervised deep facial expression recognition with an adaptive confidence margin,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4166–4175.
  32. M. Hasnat, J. Bohné, J. Milgram, S. Gentric, L. Chen et al., “von mises-fisher mixture model-based deep learning: Application to face verification,” arXiv preprint arXiv:1706.04264, 2017.
  33. X. Zhe, S. Chen, and H. Yan, “Directional statistics-based deep metric learning for image classification and retrieval,” Pattern Recognition, vol. 93, pp. 113–123, 2019.
  34. S. Li, J. Xu, X. Xu, P. Shen, S. Li, and B. Hooi, “Spherical confidence learning for face recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15 629–15 637.
  35. H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE Transactions on knowledge and data engineering, vol. 21, no. 9, pp. 1263–1284, 2009.
  36. B. Krawczyk, M. Woźniak, and G. Schaefer, “Cost-sensitive decision tree ensembles for effective imbalanced classification,” Applied Soft Computing, vol. 14, pp. 554–562, 2014.
  37. Y. Tang, Y.-Q. Zhang, N. V. Chawla, and S. Krasser, “Svms modeling for highly imbalanced classification,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 39, no. 1, pp. 281–288, 2008.
  38. Y. Cui, M. Jia, T.-Y. Lin, Y. Song, and S. Belongie, “Class-balanced loss based on effective number of samples,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 9268–9277.
  39. K. Cao, C. Wei, A. Gaidon, N. Arechiga, and T. Ma, “Learning imbalanced datasets with label-distribution-aware margin loss,” Advances in neural information processing systems, vol. 32, 2019.
  40. A. Banerjee, I. S. Dhillon, J. Ghosh, S. Sra, and G. Ridgeway, “Clustering on the unit hypersphere using von mises-fisher distributions.” Journal of Machine Learning Research, vol. 6, no. 9, 2005.
  41. B. Li, Y. Liu, and X. Wang, “Gradient harmonized single-stage detector,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, 2019, pp. 8577–8584.
  42. K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, “Momentum contrast for unsupervised visual representation learning,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 9729–9738.
  43. J.-B. Grill, F. Strub, F. Altché, C. Tallec, P. Richemond, E. Buchatskaya, C. Doersch, B. Avila Pires, Z. Guo, M. Gheshlaghi Azar et al., “Bootstrap your own latent-a new approach to self-supervised learning,” Advances in Neural Information Processing Systems, vol. 33, pp. 21 271–21 284, 2020.
  44. Q. Cao, L. Shen, W. Xie, O. M. Parkhi, and A. Zisserman, “Vggface2: A dataset for recognising faces across pose and age,” in 2018 13th IEEE International Conference on Automatic Face Gesture Recognition (FG 2018), 2018, pp. 67–74.
  45. J. Deng, S. Cheng, N. Xue, Y. Zhou, and S. Zafeiriou, “Uv-gan: Adversarial facial uv map completion for pose-invariant face recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7093–7102.
  46. Q. Meng, S. Zhao, Z. Huang, and F. Zhou, “Magface: A universal representation for face recognition and quality assessment,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14 225–14 234.
  47. W. Xie and A. Zisserman, “Multicolumn networks for face recognition,” arXiv preprint arXiv:1807.09192, 2018.
  48. X. Zhang, R. Zhao, J. Yan, M. Gao, Y. Qiao, X. Wang, and H. Li, “P2sgrad: Refined gradients for optimizing deep face models,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 9906–9914.
  49. X. Zhang, R. Zhao, Y. Qiao, X. Wang, and H. Li, “Adacos: Adaptively scaling cosine logits for effectively learning deep face representations,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10 823–10 832.
  50. H.-W. Ng and S. Winkler, “A data-driven approach to cleaning large face datasets,” in 2014 IEEE international conference on image processing (ICIP).   IEEE, 2014, pp. 343–347.
  51. H. Liu, X. Zhu, Z. Lei, and S. Z. Li, “Adaptiveface: Adaptive margin and sampling for face recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11 947–11 956.
  52. X. Wang, S. Zhang, S. Wang, T. Fu, H. Shi, and T. Mei, “Mis-classified vector guided softmax loss for face recognition,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, 2020, pp. 12 241–12 248.
  53. I. Kemelmacher-Shlizerman, S. M. Seitz, D. Miller, and E. Brossard, “The megaface benchmark: 1 million faces for recognition at scale,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 4873–4882.
  54. K. Zhang, Z. Zhang, Z. Li, and Y. Qiao, “Joint face detection and alignment using multitask cascaded convolutional networks,” IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499–1503, 2016.
  55. Y. Tai, Y. Liang, X. Liu, L. Duan, J. Li, C. Wang, F. Huang, and Y. Chen, “Towards highly accurate and stable face alignment for high-resolution videos,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, 2019, pp. 8893–8900.
  56. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, vol. 32, pp. 8026–8037, 2019.
  57. I. Community, “Insightface,” https://github.com/deepinsight/insightface, 2021, accessed: 2022-01-01.
  58. X. An, X. Zhu, Y. Xiao, L. Wu, M. Zhang, Y. Gao, B. Qin, D. Zhang, and F. Ying, “Partial fc: Training 10 million identities on a single machine,” in Arxiv 2010.05222, 2020.
  59. Y. Shi and A. K. Jain, “Probabilistic face embeddings,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 6902–6911.
Citations (115)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now