Abstract
To solve the two challenges of the high cost of manual labeling data and significant degradation of cross-domain performance in person re-identification (re-ID), we propose an unsupervised domain adaptation (UDA) person re-ID method combining style translation and unsupervised clustering method. Our model framework is divided into two stages: 1) In the style translation stage, we can get the labeled source image with the style of the target domain; 2) In the UDA person re-ID stage, we use Wasserstein distance as the evaluation index of the distribution difference between domains. In addition, to solve the problem of source domain ID labels information loss in the process of style translation, a feedback mechanism is designed to feedback the results of person re-ID to the style translation network, to improve the quality of image style translation and the accuracy of ID labels and make the style translation and person re-ID converge to the best state through closed-loop training. The test results on Market-1501, DukeMTMC, and MSMT17 show that the proposed method is more efficient and robust.
Supported by Guangxi Key Lab of Multi-source Information Mining & Security, Guangxi Normal University.
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
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein gan (2017)
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)
Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification (2018)
Ester, M., Kriegel, H.P., Sander, J., Xu, X., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD, vol. 96, pp. 226–231 (1996)
Fu, Y., Wei, Y., Wang, G., Zhou, Y., Shi, H., Huang, T.S.: Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)
Geng, B., Tao, D., Xu, C.: DAML: domain adaptation metric learning. IEEE Trans. Image Process. 20(10), 2980–2989 (2011). https://doi.org/10.1109/TIP.2011.2134107
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of Wasserstein GANs (2017)
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)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks (2016)
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
Song, L., et al.: Unsupervised domain adaptive re-identification: theory and practice. Pattern Recognit. 102, 107173 (2020)
Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation (2016)
Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Yang, F., et al.: Asymmetric co-teaching for unsupervised cross domain person re-identification (2019)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)
Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: Invariance matters: exemplar memory for domain adaptive person re-identification. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zhong, Z., Zheng, L., Li, S., Yang, Y.: Generalizing a person retrieval model hetero- and homogeneously. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 176–192. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_11
Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camstyle: a novel data augmentation method for person re-identification. IEEE Trans. Image Process. 28(3), 1176–1190 (2019). https://doi.org/10.1109/TIP.2018.2874313
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (Nos. 61866004, 61966004, 61962007), the Guangxi Natural Science Foundation (Nos. 2018GXNSFDA281009, 2019GXNSFDA245018, 2018GXNSFDA294001), Research Fund of Guangxi Key Lab of Multi-source Information Mining & Security (No.20-A-03-01), Guangxi “Bagui Scholar” Teams for Innovation and Research Project, and Innovation Project of Guangxi Graduate Education(JXXYYJSCXXM-2021-007).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wei, P., Zhang, C., Li, Z., Tang, Y., Wang, Z. (2021). Domain-Adaptation Person Re-Identification via Style Translation and Clustering. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13108. Springer, Cham. https://doi.org/10.1007/978-3-030-92185-9_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-92185-9_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92184-2
Online ISBN: 978-3-030-92185-9
eBook Packages: Computer ScienceComputer Science (R0)