Abstract
Person re-identification (ReID), aiming at retrieving persons of the same identity across non-overlap** cameras, holds immense practical significance for security and surveillance applications. In pursuit of a more general and practical solution, recent research attention has gradually shifted from the traditional single-domain ReID to the domain generalizable person re-identification (DG-ReID). However, the DG-ReID landscape lacks a meticulously designed and all-encompassing benchmark to provide a common ground for competing approaches. To this end, in this paper, we first delve into the intricate challenges of DG-ReID and introduce a comprehensive and large-scale benchmark with enhanced distributional variety and shifts to facilitate the research progress. Furthermore, in response to the highlighted challenges, a novel DG-ReID framework based on diverse feature space learning with domain factorization is proposed to effectively learn rich domain-adaptive discriminative features through the two designed blocks with fairly limited additional cost in both memory and computation. Firstly, the feature diversification block promotes a diverse feature space capable of learning domain-specific characteristics under the rich distributional variety. Secondly, the domain-adaptive shielding block applies channel-wise shielding operations based on subspace-based domain factorization in order to prevent the model from prediction bias caused by distributional shifts. Our extensive experiments demonstrate the effectiveness of the proposed framework, surpassing the performance of current state-of-the-art methods under various evaluation protocols.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig2_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11263-024-02124-5/MediaObjects/11263_2024_2124_Fig10_HTML.png)
Similar content being viewed by others
References
Barbosa, I. B., Cristani, M., Caputo, B., Rognhaugen, A., & Theoharis, T. (2018). Looking beyond appearances: Synthetic training data for deep CNNs in re-identification. Computer Vision and Image Understanding, 167, 50–62.
Bialkowski, A., Denman, S., Sridharan, S., Fookes, C., & Lucey, P. (2012). A database for person re-identification in multi-camera surveillance networks. In International conference on digital image computing techniques and applications (DICTA) (pp. 1–8). IEEE.
Bini, D. A., Higham, N. J., & Meini, B. (2005). Algorithms for the matrix p-th root. Numerical Algorithms, 39(4), 349–378.
Cai, Y., Takala, V., & Pietikainen, M. (2010). Matching groups of people by covariance descriptor. In 20th International conference on pattern recognition (pp. 2744–2747). IEEE.
Chang, W. G., You, T., Seo, S., Kwak, S., & Han, B. (2019). Domain-specific batch normalization for unsupervised domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 7354–7362).
Chavdarova, T., Baqué, P., Bouquet, S., Maksai, A., Jose, C., Bagautdinov, T., Lettry, L., Fua, P., Van Gool, L., & Fleuret, F. (2018). Wildtrack: A multi-camera hd dataset for dense unscripted pedestrian detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 5030–5039).
Chen, P., Dai, P., Liu, J., Zheng, F., Xu, M., Tian, Q., & Ji, R. (2021). Dual distribution alignment network for generalizable person re-identification. In Proceedings of the AAAI conference on artificial intelligence (pp. 1054–1062).
Chen, W., Xu, X., Jia, J., Luo, H., Wang, Y., Wang, F., **, R., & Sun, X. (2023). Beyond appearance: A semantic controllable self-supervised learning framework for human-centric visual tasks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 15050–15061).
Cho, W., Choi, S., Park, D. K., Shin, I., & Choo, J. (2019). Image-to-image translation via group-wise deep whitening-and-coloring transformation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 10639–10647).
Cho, Y., Cho, H., Kim, Y., & Kim, J. (2021). Improving generalization of batch whitening by convolutional unit optimization. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 5321–5329).
Choi, S., Kim, T., Jeong, M., Park, H., & Kim, C. (2021). Meta batch-instance normalization for generalizable person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 3425–3435).
Dai, Y., Li, X., Liu, J., Tong, Z., & Duan, L. Y. (2021). Generalizable person re-identification with relevance-aware mixture of experts. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 16145–16154).
Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 248–255).
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S, Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations.
Edelman, A., Arias, T. A., & Smith, S. T. (1998). The geometry of algorithms with orthogonality constraints. SIAM Journal on Matrix Analysis and Applications, 20(2), 303–353.
Fu, D., Chen, D., Bao, J., Yang, H., Yuan, L., Zhang, L., Li, H., & Chen, D. (2021). Unsupervised pre-training for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 14750–14759).
Gou, M., Wu, Z., Rates-Borras, A., Camps, O., & Radke, R. J. (2018). A systematic evaluation and benchmark for person re-identification: Features, metrics, and datasets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(3), 523–536.
Gray, D., & Tao, H. (2008). Viewpoint invariant pedestrian recognition with an ensemble of localized features. In European conference on computer vision (pp. 262–275). Springer.
Harandi, M., Sanderson, C., Shen, C., & Lovell, B. C. (2013). Dictionary learning and sparse coding on Grassmann manifolds: An extrinsic solution. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 3120–3127).
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 770–778).
He, L., Liu, W., Liang, J., Zheng, K., Liao, X., Cheng, P., & Mei, T. (2021) Semi-supervised domain generalizable person re-identification. ar**v preprint ar**v:2108.05045
Hirzer, M., Beleznai, C., Roth, P. M., & Bischof, H. (2011). Person re-identification by descriptive and discriminative classification. In Image analysis: 17th Scandinavian conference, SCIA 2011, Ystad, Sweden, May 2011 (pp. 91–102). Proceedings 17, Springer.
Huang, L., Yang, D., Lang, B., & Deng, J. (2018). Decorrelated batch normalization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 791–800).
Huang, L., Zhou, Y., Zhu, F., Liu, L., & Shao, L. (2019). Iterative normalization: Beyond standardization towards efficient whitening. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 4874–4883).
Huang, Y., Wu, Q., Xu, J., Zhong, Y., & Zhang, Z. (2021). Unsupervised domain adaptation with background shift mitigating for person re-identification. International Journal of Computer Vision, 129(7), 2244–2263.
Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448–456). PMLR.
Jia, J., Ruan, Q., & Hospedales, T. M. (2019). Frustratingly easy person re-identification: Generalizing person re-id in practice. ar**v preprint ar**v:1905.03422
Jiao, B., Liu, L., Gao, L., Lin, G., Yang, L., Zhang, S., Wang, P., & Zhang, Y. (2022). Dynamically transformed instance normalization network for generalizable person re-identification. In European conference on computer vision (pp. 285–301). Springer.
**, X., Lan, C., Zeng, W., Chen, Z., & Zhang, L. (2020). Style normalization and restitution for generalizable person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 3143–3152).
Li, S., Ren, W., Wang, F., Araujo, I. B., Tokuda, E. K., Junior, R. H., Cesar-Jr, R. M., Wang, Z., & Cao, X. (2021). A comprehensive benchmark analysis of single image deraining: Current challenges and future perspectives. International Journal of Computer Vision, 129, 1301–1322.
Li, W., & Wang, X. (2013). Locally aligned feature transforms across views. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 3594–3601).
Li, W., Zhao, R., **ao, T., & Wang, X. (2014). Deepreid: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 152–159).
Liao, S., & Shao, L. (2020). Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting. In European conference on computer vision (pp. 456–474). Springer.
Liao, S., & Shao, L. (2021). Transmatcher: Deep image matching through transformers for generalizable person re-identification. Advances in Neural Information Processing Systems, 34, 1992–2003.
Lin, Y., Zheng, L., Zheng, Z., Wu, Y., Hu, Z., Yan, C., & Yang, Y. (2019). Improving person re-identification by attribute and identity learning. Pattern Recognition, 95, 151–161.
Liu, J., Zha, Z. J., Tian, Q. I., Liu, D., Yao, T., Ling, Q., & Mei, T. (2016). Multi-scale triplet CNN for person re-identification. In Proceedings of the 24th ACM international conference on multimedia (pp. 192–196).
Liu, J., Zha, Z. J., Chen, D., Hong, R., & Wang, M. (2019a) Adaptive transfer network for cross-domain person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR.2019.00737
Liu, J., Zha, Z. J., Hong, R., Wang, M., & Zhang, Y. (2019b). Deep adversarial graph attention convolution network for text-based person search. In Proceedings of the 27th ACM international conference on multimedia.
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision (ICCV).
Loy, C. C., Liu, C., & Gong, S. (2013). Person re-identification by manifold ranking. In IEEE international conference on image processing (pp. 3567–3571). IEEE.
Luo, H., Jiang, W., Gu, Y., Liu, F., Liao, X., Lai, S., & Gu, J. (2019). A strong baseline and batch normalization neck for deep person re-identification. IEEE Transactions on Multimedia, 22(10), 2597–2609.
Ma, L., Liu, H., Hu, L., Wang, C., & Sun, Q. (2016). Orientation driven bag of appearances for person re-identification. ar** network. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 719–728).
Su, C., Li, J., Zhang, S., **ng, J., Gao, W., & Tian, Q. (2017). Pose-driven deep convolutional model for person re-identification. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 3960–3969).
Sun, X., & Zheng, L. (2019). Dissecting person re-identification from the viewpoint of viewpoint. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 608–617).
Tan, W., Ding, C., Wang, P., Gong, M., & Jia, K. (2023). Style interleaved learning for generalizable person re-identification. IEEE Transactions on Multimedia. https://doi.org/10.1109/TMM.2023.3283878
Tishby, N., & Zaslavsky, N. (2015). Deep learning and the information bottleneck principle. In 2015 IEEE information theory workshop (ITW) (pp. 1–5). IEEE.
Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2016). Instance normalization: The missing ingredient for fast stylization. ar**v preprint ar**v:1607.08022
Vinyals, O., Blundell, C., Lillicrap, T., & Wierstra, D. (2016). Matching networks for one shot learning. Advances in Neural Information Processing Systems, 29, 3630–3638.
Wang, H., Zhu, X., Gong, S., & **ang, T. (2018). Person re-identification in identity regression space. International Journal of Computer Vision, 126, 1288–1310.
Wang, X., Yu, F., Dunlap, L., Ma, Y. A., Wang, R., Mirhoseini, A., Darrell, T., & Gonzalez, J. E. (2020). Deep mixture of experts via shallow embedding. In R. P. Adams & V. Gogate (Eds.), Proceedings of the 35th uncertainty in artificial intelligence conference, proceedings of machine learning research (Vol. 115, pp. 552–562). PMLR. https://proceedings.mlr.press/v115/wang20d.html
Wei, L., Zhang, S., Gao, W., & Tian, Q. (2018). Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 79–88).
**ao, T., Li, S., Wang, B., Lin, L., & Wang, X. (2016). End-to-end deep learning for person search (vol. 2, no. 2, p. 4). ar**v preprint ar**v:1604.01850
Xu, B., Liang, J., He, L., & Sun, Z. (2022). Meta: Mimicking embedding via others’ aggregation for generalizable person re-identification. In European conference on computer vision (pp. 372–388).
Ye, M., Shen, J., Lin, G., **ang, T., Shao, L., & Hoi, S. C. (2021). Deep learning for person re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(6), 2872–2893.
Yin, J., Wu, A., & Zheng, W. S. (2020). Fine-grained person re-identification. International Journal of Computer Vision, 128, 1654–1672.
Zhang, J., Niu, L., & Zhang, L. (2020). Person re-identification with reinforced attribute attention selection. IEEE Transactions on Image Processing, 30, 603–616.
Zhang, P., Dou, H., Yu, Y., & Li, X. (2022). Adaptive cross-domain learning for generalizable person re-identification. In European conference on computer vision (pp. 215–232). Springer.
Zhang, S., Zhang, Q., Yang, Y., Wei, X., Wang, P., Jiao, B., & Zhang, Y. (2020). Person re-identification in aerial imagery. IEEE Transactions on Multimedia, 23, 281–291.
Zhang, T., **e, L., Wei, L., Zhuang, Z., Zhang, Y., Li, B., & Tian, Q. (2021). Unrealperson: An adaptive pipeline towards costless person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 11506–11515).
Zhang, X., He, Y., Xu, R., Yu, H., Shen, Z., & Cui, P. (2023). Nico++: Towards better benchmarking for domain generalization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 16036–16047).
Zhang, Z., Lan, C., Zeng, W., **, X., & Chen, Z. (2020c). Relation-aware global attention for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 3186–3195).
Zhao, Y., Zhong, Z., Yang, F., Luo, Z., Lin, Y., Li, S., & Sebe, N. (2021). Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 6277–6286).
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015a). Scalable person re-identification: A benchmark. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 1116–1124).
Zheng, W. S., Li, X., **ang, T., Liao, S., Lai, J., & Gong, S. (2015b). Partial person re-identification. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 4678–4686).
Zheng, Z., Zheng, L., & Yang, Y. (2017). Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 3754–3762).
Zhong, Z., Gao, Y., Zheng, Y., Zheng, B., & Sato, I. (2023). Real-world video deblurring: A benchmark dataset and an efficient recurrent neural network. International Journal of Computer Vision, 131(1), 284–301.
Zhu, X., Zhu, X., Li, M., Morerio, P., Murino, V., & Gong, S. (2021). Intra-camera supervised person re-identification. International Journal of Computer Vision, 129, 1580–1595.
Zhuang, Z., Wei, L., **e, L., Zhang, T., Zhang, H., Wu, H., Ai, H., & Tian, Q. (2020). Rethinking the distribution gap of person re-identification with camera-based batch normalization. In European conference on computer vision (pp. 140–157). Springer.
Funding
This work was supported by National Natural Science Foundation of China (NSFC) under Grants 62225207 and 62106245.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Zhun Zhong.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hu, B., Liu, J., Zheng, Y. et al. Exert Diversity and Mitigate Bias: Domain Generalizable Person Re-identification with a Comprehensive Benchmark. Int J Comput Vis (2024). https://doi.org/10.1007/s11263-024-02124-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11263-024-02124-5