Skip to main content

Rethinking Robust Representation Learning Under Fine-Grained Noisy Faces

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13672))

Included in the following conference series:

  • 1870 Accesses

Abstract

Learning robust feature representation from large-scale noisy faces stands out as one of the key challenges in high-performance face recognition. Recent attempts have been made to cope with this challenge by alleviating the intra-class conflict and inter-class conflict. However, the unconstrained noise type in each conflict still makes it difficult for these algorithms to perform well. To better understand this, we reformulate the noise type of each class in a more fine-grained manner as N-identities \(|\) K \(^C\) -clusters. Different types of noisy faces can be generated by adjusting the values of \(N\), \(K\), and \(C\). Based on this unified formulation, we found that the main barrier behind the noise-robust representation learning is the flexibility of the algorithm under different \(N\), \(K\), and \(C\). For this potential problem, we propose a new method, named Evolving Sub-centers Learning (ESL), to find optimal hyperplanes to accurately describe the latent space of massive noisy faces. More specifically, we initialize M sub-centers for each class and ESL encourages it to be automatically aligned to N-identities \(|\) K \(^C\) -clusters faces via producing, merging, and dropping operations. Images belonging to the same identity in noisy faces can effectively converge to the same sub-center and samples with different identities will be pushed away. We inspect its effectiveness with an elaborate ablation study on the synthetic noisy dataset with different \(N\), \(K\), and \(C\). Without any bells and whistles, ESL can achieve significant performance gains over state-of-the-art methods on large-scale noisy faces.

B. Ma and G. Song—Equal contributions.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. An, X., et al.: Partial FC: training 10 million identities on a single machine. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1445–1449 (2021)

    Google Scholar 

  2. Deng, J., Guo, J., Liu, T., Gong, M., Zafeiriou, S.: Sub-center ArcFace: boosting face recognition by large-scale noisy web faces. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 741–757. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_43

    Chapter  Google Scholar 

  3. Deng, J., Guo, J., Ververas, E., Kotsia, I., Zafeiriou, S.: RetinaFace: single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5203–5212 (2020)

    Google Scholar 

  4. 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)

    Google Scholar 

  5. Deng, J., Guo, J., Zhang, D., Deng, Y., Lu, X., Shi, S.: Lightweight face recognition challenge. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (2019)

    Google Scholar 

  6. Deng, J., Zhou, Y., Zafeiriou, S.: Marginal loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 60–68 (2017)

    Google Scholar 

  7. Du, H., Shi, H., Liu, Y., Wang, J., Lei, Z., Zeng, D., Mei, T.: Semi-Siamese training for shallow face learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 36–53. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_3

    Chapter  Google Scholar 

  8. Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87–102. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_6

    Chapter  Google Scholar 

  9. 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)

    Google Scholar 

  10. Hu, W., Huang, Y., Zhang, F., Li, R.: Noise-tolerant paradigm for training face recognition CNNs. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11887–11896 (2019)

    Google Scholar 

  11. 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)

    Google Scholar 

  12. 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)

    Google Scholar 

  13. Liu, B., Song, G., Zhang, M., You, H., Liu, Y.: Switchable k-class hyperplanes for noise-robust representation learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3019–3028 (2021)

    Google Scholar 

  14. 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)

    Google Scholar 

  15. Liu, Yu., Song, G., Shao, J., Jin, X., Wang, X.: Transductive centroid projection for semi-supervised large-scale recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 72–89. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_5

    Chapter  Google Scholar 

  16. Liu, Y., et al.: Towards flops-constrained face recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (2019)

    Google Scholar 

  17. Maze, B., et al.: IARPA Janus benchmark-C: face dataset and protocol. In: 2018 International Conference on Biometrics (ICB), pp. 158–165. IEEE (2018)

    Google Scholar 

  18. 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)

    Google Scholar 

  19. Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32 (2019)

    Google Scholar 

  20. 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)

    Google Scholar 

  21. 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)

    Google Scholar 

  22. Song, G., Leng, B., Liu, Y., Hetang, C., Cai, S.: Region-based quality estimation network for large-scale person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)

    Google Scholar 

  23. Song, G., Liu, Y., Jiang, M., Wang, Y., Yan, J., Leng, B.: Beyond trade-off: accelerate FCN-based face detector with higher accuracy. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7756–7764 (2018)

    Google Scholar 

  24. Song, G., Liu, Y., Wang, X.: Revisiting the sibling head in object detector. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11563–11572 (2020)

    Google Scholar 

  25. Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1891–1898 (2014)

    Google Scholar 

  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)

    Google Scholar 

  27. Wang, X., Wang, S., Wang, J., Shi, H., Mei, T.: Co-mining: deep face recognition with noisy labels. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9358–9367 (2019)

    Google Scholar 

  28. Wang, X., Zhang, S., Wang, S., Fu, T., 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)

    Google Scholar 

  29. Whitelam, C., et al.: IARPA Janus benchmark-B face dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 90–98 (2017)

    Google Scholar 

  30. Zhang, M., Song, G., Zhou, H., Liu, Yu.: Discriminability distillation in group representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 1–19. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58607-2_1

    Chapter  Google Scholar 

  31. 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)

    Google Scholar 

  32. Zhong, Y., et al.: Unequal-training for deep face recognition with long-tailed noisy data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7812–7821 (2019)

    Google Scholar 

  33. Zhu, M., Martínez, A.M.: Optimal subclass discovery for discriminant analysis. In: 2004 Conference on Computer Vision and Pattern Recognition Workshop. IEEE (2004)

    Google Scholar 

  34. Zhu, M., Martinez, A.M.: Subclass discriminant analysis. IEEE Trans. Pattern Anal. Mach. Intell. 28(8), 1274–1286 (2006)

    Article  Google Scholar 

  35. Zhu, Z., et al.: WebFace260M: a benchmark unveiling the power of million-scale deep face recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10492–10502 (2021)

    Google Scholar 

Download references

Acknowledgments

The work was supported by the National Key R &D Program of China under Grant 2021ZD0201300.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Yu Liu .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 220 KB)

Rights and permissions

Reprints and permissions

Copyright information

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

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ma, B., Song, G., Liu, B., Liu, Y. (2022). Rethinking Robust Representation Learning Under Fine-Grained Noisy Faces. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13672. Springer, Cham. https://doi.org/10.1007/978-3-031-19775-8_36

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19775-8_36

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19774-1

  • Online ISBN: 978-3-031-19775-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics