Abstract
Person re-identification is a challenging problem in computer vision, aiming to accurately match and recognize the same individual across different viewpoints and cameras. Due to significant variations in appearance under different scenes, person re-identification requires highly discriminative features. Wavelet features contain richer phase and amplitude information as well as rotational invariance, demonstrating good performance in various visual tasks. However, through our observations and validations, we have found that the vertical component within wavelet features exhibits stronger adaptability and discriminability in person re-identification. It better captures the body contour and detailed information of pedestrians, which is particularly helpful in distinguishing differences among individuals. Based on this observation, we propose a vertical wavelet spatial attention only with the vertical component in the high frequency specifically designed for feature extraction and matching in person re-identification. To enhance spatial semantic consistency and facilitate the transfer of knowledge between different layers of wavelet attention in the neural network, we introduce a self-distillation enhancement method to constrain shallow and deep spatial attention. Experimental results on Market-1501 and DukeMTMC-reID datasets validate the effectiveness of our model.
Y. Zhang and H. Tan—Co-first authors of the article.
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
Matsukawa, T., Okabe, T., Suzuki, E., Sato, Y.: Hierarchical Gaussian descriptor for person re-identification. In: 2016 IEEE CVPR, pp. 1363–1372 (2016)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline) (2018). http://arxiv.org/abs/1711.09349
Liu, J., Zha, Z.-J., Chen, D., Hong, R., Wang, M.: Adaptive transfer network for cross-domain person re-identification. In: 2019 IEEE/CVF CVPR, pp. 7195–7204 (2019)
Qin, Z., Zhang, P., Wu, F., Li, X.: FcaNet: frequency channel attention networks. In: 2021 IEEE/CVF International Conference on Computer Vision, pp. 763–772 (2021)
Wang, H., Wu, X., Huang, Z., Xing, E.P.: High frequency component helps explain the generalization of convolutional neural networks, http://arxiv.org/abs/1905.13545 (2020)
Li, Q., Shen, L., Guo, S., Lai, Z.: Wavelet integrated CNNs for noise-robust image classification. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7243–7252 (2020)
Alaba, S.Y., Ball, J.E.: WCNN3D: wavelet convolutional neural network-based 3D object detection for autonomous driving. Sensors 22, 7010 (2022)
Li, Q., Shen, L.: WaveSNet: wavelet integrated deep networks for image segmentation. http://arxiv.org/abs/2005.14461 (2020)
Tong, H., Li, M., Zhang, H., Zhang, C.: Blur detection for digital images using wavelet transform. In: 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763), pp. 17–20. IEEE, Taipei, Taiwan (2004)
Luo, X., Zhang, J., Hong, M., Qu, Y., Xie, Y., Li, C.: Deep wavelet network with domain adaptation for single image demoireing. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1687–1694 (2020)
Leterme, H., Polisano, K., Perrier, V., Alahari, K.: On the shift invariance of max pooling feature maps in convolutional neural networks. http://arxiv.org/abs/2209.11740 (2022)
Song, C., Huang, Y., Ouyang, W., Wang, L.: Mask-guided contrastive attention model for person re-identification. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1179–1188. IEEE, Salt Lake City, UT (2018)
Yu, R., Zhou, Z., Bai, S., Bai, X.: Divide and fuse: a re-ranking approach for person re-identification. In: Proceedings of the British Machine Vision Conference 2017, p. 135. British Machine Vision Association, London, UK (2017). https://doi.org/10.5244/C.31.135
Jiao, S., Wang, J., Hu, G., Pan, Z., Du, L., Zhang, J.: Joint attention mechanism for person re-identification. IEEE Access 7, 90497–90506 (2019)
Li, W., et al.: Collaborative attention network for person re-identification. J. Phys. Conf. Ser. 1848, 012074 (2021). https://doi.org/10.1088/1742-6596/1848/1/012074
Zhang, G., Chen, Y., Lin, W., Chandran, A., Jing, X.: Low resolution information also matters: learning multi-resolution representations for person re-identification. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, pp. 1295–1301, (2021)
Fujieda, S., Takayama, K., Hachisuka, T.: Wavelet convolutional neural networks, http://arxiv.org/abs/1805.08620 (2018)
Huang, H., Yu, A., Chai, Z., He, R., Tan, T.: Selective wavelet attention learning for single image deraining. Int. J. Comput. Vis. 129, 1282–1300 (2021)
Zou, W., Jiang, M., Zhang, Y., Chen, L., Lu, Z., Wu, Y.: SDWNet: a straight dilated network with wavelet transformation for image deblurring. In: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 1895–1904 (2021)
Yang, Y., et al.: Dual wavelet attention networks for image classification. IEEE Trans. Circuits Syst. Video Technol. 1 (2022)
Mallat, S.G.: A Wavelet Tour of Signal Processing: The Sparse Way. Elsevier/Academic Press, Amsterdam, Boston (2009)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network, http://arxiv.org/abs/1503.02531 (2015)
Zhang, L., Song, J., Gao, A., Chen, J., Bao, C., Ma, K.: Be your own teacher: improve the performance of convolutional neural networks via self distillation, http://arxiv.org/abs/1905.08094 (2019)
Xu, T.-B., Liu, C.-L.: Data-distortion guided self-distillation for deep neural networks. AAAI 33, 5565–5572 (2019). https://doi.org/10.1609/aaai.v33i01.33015565
Li, G., Togo, R., Ogawa, T., Haseyama, M.: Self-knowledge distillation based self-supervised learning for Covid-19 detection from chest X-ray images. In: ICASSP 2022, pp. 1371–1375 (2022)
Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1487–1495. IEEE, Long Beach, CA, USA (2019)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable Person re-identification: a benchmark. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1116–1124. IEEE, Santiago, Chile (2015)
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro, http://arxiv.org/abs/1701.07717 (2017)
Yang, W., Huang, H., Zhang, Z., Chen, X., Huang, K., Zhang, S.: Towards rich feature discovery with class activation maps augmentation for person re-identification. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1389–1398. IEEE, Long Beach, CA, USA (2019)
Jin, X., Lan, C., Zeng, W., Chen, Z., Zhang, L.: Style normalization and restitution for generalizable person re-identification. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3140–3149. IEEE, Seattle, WA, USA (2020). https://doi.org/10.1109/CVPR42600.2020.00321
He, L., Liu, W.: Guided saliency feature learning for person re-identification in crowded scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 357–373. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58604-1_22
Wu, G., Zhu, X., Gong, S.: Learning hybrid ranking representation for person re-identification. Pattern Recogn. 121, 108239 (2022)
Acknowledgment
This work was supported by: The Self networks (CNNs). Furthermore, the Transformer has also-directed Project of State Key Laboratory of High Performance Computing: 202101-18.
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 Switzerland AG
About this paper
Cite this paper
Zhang, Y., Tan, H., Lan, L., Teng, X., Ren, J., Zhang, Y. (2024). Self-distillation Enhanced Vertical Wavelet Spatial Attention for Person Re-identification. In: Rudinac, S., et al. MultiMedia Modeling. MMM 2024. Lecture Notes in Computer Science, vol 14555. Springer, Cham. https://doi.org/10.1007/978-3-031-53308-2_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-53308-2_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53307-5
Online ISBN: 978-3-031-53308-2
eBook Packages: Computer ScienceComputer Science (R0)