Abstract
Most person re-identification (ReID) methods aim at retrieving people with unchanged clothes. Meanwhile, fewer studies work on the cloth-inconsistency problem, which is more challenging but useful in the real intelligent surveillance scenario. We propose a novel method, named Multi-View Geometry Distillation (MVGD), taking advantage of 3D priors to explore cloth-unrelated multi-view human information. Specifically, a 3D Grouping Geometry Graph Convolution Network (3DG\(^{3}\)) is proposed to extract ReID-specific geometry representation from the 3D reconstructed body mesh, which encodes shape, pose, and other geometry patterns from the 3D perspective. Then, we design a 3D-Guided Appearance Learning scheme to extract more accurate part features. Furthermore, we also adopt a Multi-View Interactive Learning module (MVIL) to fuse the different types of features together and extract high-level multi-view geometry representation. Finally, these discriminative features are treated as the teacher to guide the backbone by the distillation mechanism for better representations. Extensive experiments on three popular cloth-changing ReID datasets demonstrate the effectiveness of our method. The proposed method brings 9\(\%\) and 7.5\(\%\) gains in average in terms of rank-1 and mAP metrics against the baseline, respectively.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Our 13 joints include head, shoulders, elbows, wrists, hips, knees, and ankles.
References
Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: Openpose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172–186 (2019)
Chen, J., et al.: Learning 3D shape feature for texture-insensitive person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8146–8155 (2021)
Chen, J., Zheng, W.S., Yang, Q., Meng, J., Hong, R., Tian, Q.: Deep shape-aware person re-identification for overcoming moderate clothing changes. IEEE Trans. Multimedia (2021)
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. IEEE (2009)
Fan, L., Li, T., Fang, R., Hristov, R., Yuan, Y., Katabi, D.: Learning longterm representations for person re-identification using radio signals. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10699–10709 (2020)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059. PMLR (2016)
Gao, Z., Wei, H., Guan, W., Nie, W., Liu, M., Wang, M.: Multigranular visual-semantic embedding for cloth-changing person re-identification. arXiv preprint arXiv:2108.04527 (2021)
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)
Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
Hong, P., Wu, T., Wu, A., Han, X., Zheng, W.S.: Fine-grained shape-appearance mutual learning for cloth-changing person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10513–10522 (2021)
Huang, Y., Wu, Q., Xu, J., Zhong, Y., Zhang, Z.: Clothing status awareness for long-term person re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 11895–11904, October 2021
Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325–1339 (2013)
Jin, X., et al.: Cloth-changing person re-identification from a single image with gait prediction and regularization. arXiv preprint arXiv:2103.15537 (2021)
Kalayeh, M.M., Basaran, E., Gökmen, M., Kamasak, M.E., Shah, M.: Human semantic parsing for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1062–1071 (2018)
Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482–7491 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3d human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2252–2261 (2019)
Li, Y.J., Weng, X., Kitani, K.M.: Learning shape representations for person re-identification under clothing change. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2432–2441 (2021)
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1–16 (2015)
Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. arXiv preprint arXiv:1706.02413 (2017)
Qian, X., et al.: Long-term cloth-changing person re-identification. In: Proceedings of the Asian Conference on Computer Vision (2020)
Shi, W., Rajkumar, R.: Point-GNN: graph neural network for 3D object detection in a point cloud. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1711–1719 (2020)
Simonovsky, M., Komodakis, N.: Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3693–3702 (2017)
Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693–5703 (2019)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 480–496 (2018)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Wan, F., Wu, Y., Qian, X., Chen, Y., Fu, Y.: When person re-identification meets changing clothes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 830–831 (2020)
Wang, G., Yuan, Y., Chen, X., Li, J., Zhou, X.: Learning discriminative features with multiple granularities for person re-identification. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 274–282 (2018)
Yang, B., Luo, W., Urtasun, R.: Pixor: real-time 3D object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7652–7660 (2018)
Yang, Q., Wu, A., Zheng, W.S.: Person re-identification by contour sketch under moderate clothing change. IEEE Trans. Pattern Anal. Mach. Intell. 43(6), 2029–2046 (2019)
Zheng, L., Huang, Y., Lu, H., Yang, Y.: Pose-invariant embedding for deep person re-identification. IEEE Trans. Image Process. 28(9), 4500–4509 (2019)
Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13001–13008 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, H., Liu, B., Lu, Y., Chu, Q., Yu, N. (2022). Multi-view Geometry Distillation for Cloth-Changing Person ReID. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13534. Springer, Cham. https://doi.org/10.1007/978-3-031-18907-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-18907-4_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18906-7
Online ISBN: 978-3-031-18907-4
eBook Packages: Computer ScienceComputer Science (R0)