Abstract
Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention similarity knowledge distillation approach, which transfers attention maps obtained from a high resolution (HR) network as a teacher into an LR network as a student to boost LR recognition performance. Inspired by humans being able to approximate an object’s region from an LR image based on prior knowledge obtained from HR images, we designed the knowledge distillation loss using the cosine similarity to make the student network’s attention resemble the teacher network’s attention. Experiments on various LR face related benchmarks confirmed the proposed method generally improved recognition performances on LR settings, outperforming state-of-the-art results by simply transferring well-constructed attention maps. The code and pretrained models are publicly available in the https://github.com/gist-ailab/teaching-where-to-look.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cheng, Z., Zhu, X., Gong, S.: Low-resolution face recognition. In: ACCV (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009). https://doi.org/10.1109/CVPR.2009.5206848
Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2019, pp. 4685–4694, January 2018. http://arxiv.org/abs/1801.07698
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38, 295–307 (2016)
Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 391–407. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_25
Flusser, J., Farokhi, S., Höschl, C., Suk, T., Zitová, B., Pedone, M.: Recognition of images degraded by Gaussian blur. IEEE Trans. Image Process. 25(2), 790–806 (2016). https://doi.org/10.1109/TIP.2015.2512108
Fookes, C., Lin, F., Chandran, V., Sridharan, S.: Evaluation of image resolution and super-resolution on face recognition performance. J. Vis. Commun. Image Represent. 23(1), 75–93 (2012). https://doi.org/10.1016/j.jvcir.2011.06.004
Ge, S., et al.: Look one and more: distilling hybrid order relational knowledge for cross-resolution image recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 10845–10852 (2020)
Gunturk, B.K., Batur, A.U., Altunbasak, Y., Hayes, M.H., Mersereau, R.M.: Eigenface-domain super-resolution for face recognition. IEEE Trans. Image Process. 12(5), 597–606 (2003). https://doi.org/10.1109/TIP.2003.811513
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
Hennings-Yeomans, P.H., Baker, S., Kumar, B.V.: Simultaneous super-resolution and feature extraction for recognition of low-resolution faces. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2008). https://doi.org/10.1109/CVPR.2008.4587810
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015). http://arxiv.org/abs/1503.02531
Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2011–2023 (2020)
Huang, G.B., Mattar, M.A., Berg, T.L., Learned-Miller, E.: Labeled faces in the wild: A database for studying face recognition in unconstrained environments (2008)
Kemelmacher-Shlizerman, I., Seitz, S.M., Miller, D., Brossard, E.: The MegaFace benchmark: 1 million faces for recognition at scale. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4873–4882 (2016). https://doi.org/10.1109/CVPR.2016.527
Kong, H., Zhao, J., Tu, X., Xing, J., Shen, S., Feng, J.: Cross-resolution face recognition via prior-aided face hallucination and residual knowledge distillation. arXiv, May 2019. http://arxiv.org/abs/1905.10777
Köstinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 2144–2151 (2011)
Kumar, A., Chellappa, R.: S2ld: Semi-supervised landmark detection in low resolution images and impact on face verification. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 3275–3283 (2020)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 105–114 (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), pp. 6738–6746 (2017)
Lui, Y.M., Bolme, D., Draper, B.A., Beveridge, J.R., Givens, G., Phillips, P.J.: A meta-analysis of face recognition covariates. In: Proceedings of the 3rd IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009, pp. 139–146. IEEE Press (2009)
Massoli, F.V., Amato, G., Falchi, F.: Cross-resolution learning for face recognition. Image Vis. Comput. 99, 103927 (2020). https://doi.org/10.1016/j.imavis.2020.103927
Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: AgeDB: the first manually collected, in-the-wild age database, pp. 1997–2005 (2017). https://doi.org/10.1109/CVPRW.2017.250
Park, J., Woo, S., Lee, J.Y., Kweon, I.S.: BAM: bottleneck attention module. In: BMVC (2018)
Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2019, pp. 3962–3971, January 2020. http://arxiv.org/abs/1904.05068
Pei, Y., Huang, Y., Zou, Q., Zhang, X., Wang, S.: Effects of image degradation and degradation removal to CNN-based image classification. IEEE Trans. Pattern Anal. Mach. Intell. 43(4), 1239–1253 (2021). https://doi.org/10.1109/TPAMI.2019.2950923
Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. CoRR abs/1412.6550 (2015)
Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: Proceedings of 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, January 2017, pp. 1283–1292. Institute of Electrical and Electronics Engineers Inc., November 2017. https://doi.org/10.1109/CVPR.2017.141
Wang, H., Wang, Y., Zhou, Z., Ji, X., Li, Z., Gong, D., Zhou, J., Liu, W.: CosFace: large margin cosine loss for deep face recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5265–5274 (2018)
Wilman, W.W.Z., Yuen, P.C.: Very low resolution face recognition problem. In: 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS), pp. 1–6 (2010). https://doi.org/10.1109/BTAS.2010.5634490
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1. http://arxiv.org/abs/1807.06521
Yang, S., Luo, P., Loy, C.C., Tang, X.: WIDER FACE: a face detection benchmark. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5525–5533 (2016). https://doi.org/10.1109/CVPR.2016.596
Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from Scratch, November 2014. http://arxiv.org/abs/1411.7923
Yim, J., Joo, D., Bae, J.H., Kim, J.: A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7130–7138 (2017)
Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings, December 2016
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multi-task cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016). https://doi.org/10.1109/LSP.2016.2603342. http://arxiv.org/abs/1604.02878
Zhu, M., Han, K., Zhang, C., Lin, J., Wang, Y.: Low-resolution visual recognition via deep feature distillation. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3762–3766 (2019). https://doi.org/10.1109/ICASSP.2019.8682926
Zhu, Y., Cai, H., Zhang, S., Wang, C., Xiong, Y.: TinaFace: strong but simple baseline for face detection. arXiv abs/2011.13183 (2020)
Acknowledgments
This work was supported by the ICT R &D program of MSIT/IITP[2020-0-00857, Development of Cloud Robot Intelligence Augmentation, Sharing and Framework Technology to Integrate and Enhance the Intelligence of Multiple Robots. And also, this work was partially supported by Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE) (No. 20202910100030) and supported by Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean government. [22ZR1100, A Study of Hyper-Connected Thinking Internet Technology by autonomous connecting, controlling and evolving ways].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shin, S., Lee, J., Lee, J., Yu, Y., Lee, K. (2022). Teaching Where to Look: Attention Similarity Knowledge Distillation for Low Resolution Face Recognition. 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_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-19775-8_37
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)