Abstract
Person re-identification (ReID) is a challenging computer vision problem where the objective is to retrieve a person of interest from a gallery of images. Conventional person ReID methods struggle to generalize across different domains, leading to inferior cross-domain performance. To address this, domain generalization (DG) person re-id methods are proposed. The majority of DG studies focus on designing more robust models that are trained on source datasets in an offline setting with explicit components or training mechanisms for domain generalization. Moreover, these frameworks do not take into consideration that in the real world the environment is in continual change resulting in the degradation of the discriminative feature extraction. To tackle these problems, we propose a new problem formulation of Test-time adaption for ReID (TTA ReID). Our TTA ReID takes a pre-trained model that was not designed for domain generalization from source domain, and aims in inference to adapt it to the current target domain in an unsupervised setting. To this end, we propose Anchor ReID, a framework designed to adapt a pre-trained model without altering its network architecture and make it robust to domain shift. Comprehensive experiments on CUHK03, Duke-mtmc, and Market 1501 datasets demonstrate the benefits of the proposed approach. The proposed Anchor ReID framework can improve a pre-trained model (that was not designed for domain generalization) and achieves an absolute gain of mAP 10 in the CUHK03 dataset.
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 subscriptionsReferences
Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification (2019)
Wieczorek, M., Rychalska, B., Dabrowski, J.: On the unreasonable effectiveness of centroids in image retrieval (2021)
Yang, S., Kang, B., Lee, Y.: Sampling agnostic feature representation for long-term person re-identification. IEEE Trans. Image Process. 31, 6412–6423 (2022)
Wang, H., Shen, J., Liu, Y., Gao, Y., Gavves, E.: NFormer: robust person re-identification with neighbor transformer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7297–7307, June 2022
He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: TransReID: transformer-based object re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 15013–15022, October 2021
Ge, Y., Chen, D., Li, H.: Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification (2020)
Ge, Y., Zhu, F., Chen, D., Zhao, R., Li, H.: Self-paced contrastive learning with hybrid memory for domain adaptive object re-id (2020)
Hu, Z., Zhu, C., He, G.: Hard-sample guided hybrid contrast learning for unsupervised person re-identification. arXiv preprint arXiv:2109.12333 (2021)
Dai, Y., Liu, J., Sun, Y., Tong, Z., Zhang, C., Duan, L.-Y.: IDM: an intermediate domain module for domain adaptive person re-id (2021)
Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Invariance matters: exemplar memory for domain adaptive person re-identification (2019)
Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Learning to adapt invariance in memory for person re-identification (2019)
Choi, S., Kim, T., Jeong, M., Park, H., Kim, C.: Meta batch-instance normalization for generalizable person re-identification (2020)
Jia, J., Ruan, Q., Hospedales, T.M.: Frustratingly easy person re-identification: generalizing person re-id in practice (2019)
Jin, X., Lan, C., Zeng, W., Chen, Z., Zhang, L.: Style normalization and restitution for generalizable person re-identification (2020)
Liao, S., Shao, L.: Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 456–474. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_27
Iwasawa, Y., Matsuo, Y.: Test-time classifier adjustment module for model-agnostic domain generalization. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 2427–2440. Curran Associates Inc. (2021)
Zheng, K., Lan, C., Zeng, W., Zhang, Z., Zha, Z.: Exploiting sample uncertainty for domain adaptive person re-identification. CoRR, vol. abs/2012.08733 (2020)
Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: fully test-time adaptation by entropy minimization (2020)
Liu, Y., Kothari, P., van Delft, B., Bellot-Gurlet, B., Mordan, T., Alahi, A.: TTT++: when does self-supervised test-time training fail or thrive? In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 21808–21820. Curran Associates Inc. (2021)
Wang, Q., Fink, O., Van Gool, L., Dai, D.: Continual test-time domain adaptation (2022)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A Kernel two-sample test. J. Mach. Learn. Res. 13(25), 723–773 (2012)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: IEEE International Conference on Computer Vision (2015)
Li, W., Zhao, R., Xiao, T., Wang, X.: DeepReID: deep filter pairing neural network for person re-identification. In: CVPR (2014)
Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17–35. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48881-3_2
Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via IBN-Net (2018)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision (2015)
Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: ICCV (2019)
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 Switzerland AG
About this paper
Cite this paper
Almansoori, M., Fiaz, M., Cholakkal, H. (2023). Anchor-ReID: A Test Time Adaptation for Person Re-identification. In: Gade, R., Felsberg, M., Kämäräinen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13886. Springer, Cham. https://doi.org/10.1007/978-3-031-31438-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-31438-4_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31437-7
Online ISBN: 978-3-031-31438-4
eBook Packages: Computer ScienceComputer Science (R0)