Abstract
Recently, large deep models have achieved significant progress on gait recognition in the wild. However, such models come with a high cost of runtime and computational resource consumption. In this paper, we investigate knowledge distillation (KD) for gait recognition, which trains compact student networks by using a cumbersome teacher network. We propose a novel scheme, named Frame Correlation KD (FCKD), to transfer the frame correlation map (FCM) from the teacher network to the student network. Since the teacher network usually learns more frame correlations, transferring such FCM from teacher to student makes the student more informative and mimic the teacher better, thus improving the recognition accuracy. Extensive experiments demonstrate the effectiveness of our approach in improving the performance of compact networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
DG2D represents DeepGaitV2-2D and DG3D represents DeepGaitV2-3D. (16) represents that the number of first-stage channels is 16.
- 2.
We only consider the backbone for all experiments.
References
Nixon, M.S., Carter, J.N.: Automatic recognition by gait. Proc. IEEE 94(11), 2013–2024 (2006)
Chao, H., He, Y., Zhang, J., Feng, J.: GaitSet: regarding gait as a set for cross-view gait recognition. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 8126–8133 (2019)
Fan, C., et al.: GaitPart: temporal Part-based Model for Gait Recognition. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14225–14233 (2020)
Huang, X., et al.: Context-sensitive temporal feature learning for gait recognition. In: IEEE/CVF International Conference on Computer Vision, pp. 12909–12918 (2021)
Lin, B., Zhang, S., Yu, X.: Gait recognition via effective global-local feature representation and local temporal aggregation. In: IEEE/CVF International Conference on Computer Vision, pp. 14648–14656 (2021)
Chai, T., Li, A., Zhang, S., Li, Z., Wang, Y.: Lagrange motion analysis and view embeddings for improved gait recognition. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 20249–20258 (2022)
Fan, C., Liang, J., Shen, C., Hou, S., Huang, Y., Yu, S.: OpenGait: revisiting gait recognition towards better practicality. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9707–9716 (2023)
Fan, C., Hou, S., Huang, Y., Yu, S.: Exploring deep models for practical gait recognition. arXiv preprint arXiv:2303.03301 (2023)
Zheng, J., Liu, X., Liu, W., He, L., Yan, C., Mei, T.: Gait recognition in the wild with dense 3d representations and a benchmark. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20228–20237 (2022)
Zhu, Z., et al.: Gait recognition in the wild: a benchmark. In: IEEE/CVF International Conference on Computer Vision, pp. 14789–14799 (2021)
Yu, S., Tan, D., Tan, T.: A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: International Conference on Pattern Recognition, vol. 4, pp. 441–444. IEEE (2006)
Takemura, N., Makihara, Y., Muramatsu, D., Echigo, T., Yagi, Y.: Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition. IPSJ Trans. Comput. Vis. Appl. 10, 1–14 (2018)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Guo, G., Han, L., Wang, L., Zhang, D., Han, J.: Semantic-aware knowledge distillation with parameter-free feature uniformization. Visual Intell. 1, 6 (2023)
Shu, C., Liu, Y., Gao, J., Yan, Z., Shen, C.: Channel-wise knowledge distillation for dense prediction. In: IEEE/CVF International Conference on Computer Vision, pp. 5311–5320 (2021)
Porrello, A., Bergamini, L., Calderara, S.: Robust re-identification by multiple views knowledge distillation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 93–110. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58607-2_6
Wang, P., Wang, F., Li, H.: Image-to-video re-identification via mutual discriminative knowledge transfer. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2125–2129. IEEE (2022)
Shang, L., Yin, D., Hu, B.: GaitPVD: part-based view distillation network for cross-view gait recognition. In: International Conference on Computer Science and Application Engineering, pp. 1–6 (2021)
Fu, Y., et al.: Horizontal pyramid matching for person re-identification. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 8295–8302 (2019)
Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)
Ma, K., Fu, Y., Zheng, D., Cao, C., Hu, X., Huang, Y.: Dynamic aggregated network for gait recognition. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 22076–22085 (2023)
Dou, H., Zhang, P., Su, W., Yu, Y., Lin, Y., Li, X.: GaitGCI: generative counterfactual intervention for gait recognition. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5578–5588 (2023)
Acknowledgement
This work was supported by the Key Program of National Natural Science Foundation of China (Grant No. U20B2069).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Peng, G., Zhang, S., Zhao, Y., Li, A., Wang, Y. (2023). Frame Correlation Knowledge Distillation for Gait Recognition in the Wild. In: Jia, W., et al. Biometric Recognition. CCBR 2023. Lecture Notes in Computer Science, vol 14463. Springer, Singapore. https://doi.org/10.1007/978-981-99-8565-4_27
Download citation
DOI: https://doi.org/10.1007/978-981-99-8565-4_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8564-7
Online ISBN: 978-981-99-8565-4
eBook Packages: Computer ScienceComputer Science (R0)