Abstract
Although existing research has made considerable progress in person re-identification (re-id), it remains challenges due to intra-class variations across different cameras and the lack of cross-view paired training data. Recently, there are increasing studies focusing on using generative model to augment training samples. One of the main obstacles is how to use generated unlabeled samples. To address this issue, we propose a joint learning framework without label predictions, including re-id learning and data generation end-to-end. Each person encodes into a feature code and a structure code. The generative module is able to generate cross-id images by decoding structure code with switched feature code. For generated unlabeled data, we average re-id model weights instead of label predictions. Moreover, we expand the distance between inter-class feature code. Our approach improves the accuracy of the re-id model and the quality of the generated data. Experiments on several benchmark datasets shows that our method achieves competitive results with most state-of-the-art methods.
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
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)
Ge, Y., Li, Z., Zhao, H., Yin, G., Yi, S., et al.: FD-GAN: pose-guided feature distilling GAN for robust person re-identification. In: Advances in Neural Information Processing Systems, pp. 1222–1233 (2018)
Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
Hou, R., Ma, B., Chang, H., Gu, X., Shan, S., Chen, X.: Interaction-and-aggregation network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9317–9326 (2019)
Huang, Y., Xu, J., Wu, Q., Zheng, Z., et al.: Multi-pseudo regularized label for generated data in person re-identification. IEEE Trans. Image Process. 28(3), 1391–1403 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242 (2016)
Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. In: Advances in Neural Information Processing Systems, pp. 406–416 (2017)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
Qian, X., et al.: Pose-normalized image generation for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 661–678. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_40
Rasmus, A., Berglund, M., Honkala, M., Valpola, H., Raiko, T.: Semi-supervised learning with ladder networks. In: Advances in Neural Information Processing Systems, pp. 3546–3554 (2015)
Siarohin, A., Sangineto, E., Lathuiliere, S., Sebe, N.: Deformable GANs for pose-based human image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3408–3416 (2018)
Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K.M.: Part-aligned bilinear representations for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 418–437. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_25
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: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 501–518. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_30
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems (2017)
Wei, L., Zhang, S., Yao, H., Gao, W., Tian, Q.: GLAD: global-local-alignment descriptor for pedestrian retrieval. In: Proceedings of the 25th ACM International Conference on Multimedia (2017)
Zheng, M., Karanam, S., Wu, Z., Radke, R.J.: Re-identification with consistent attentive siamese networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5735–5744 (2019)
Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., Kautz, J.: Joint discriminative and generative learning for person re-identification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3754–3762 (2017)
Zheng, Z., Zheng, L., Yang, Y.: Pedestrian alignment network for large-scale person re-identification. IEEE Trans. Circuits Syst. Video Technol. 29(10), 3037–3045 (2018)
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
Su, D., Zhang, C., Wang, S. (2021). Joint Weights-Averaged and Feature-Separated Learning for Person Re-identification. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12894. Springer, Cham. https://doi.org/10.1007/978-3-030-86380-7_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-86380-7_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86379-1
Online ISBN: 978-3-030-86380-7
eBook Packages: Computer ScienceComputer Science (R0)