Abstract
In practical scenarios, person re-identification tasks often face the problem of insufficient available pedestrian images. In response to this problem, a few-shot person re-identification method based on hybrid pooling fusion and Gaussian relation metric is proposed. Firstly, a hybrid pooling fusion method is proposed. In this method, max pooling and average pooling layers are introduced after each feature extraction layer, and the adaptive weight allocation mechanism is introduced in the fusion of post-pooling and non-pooling features, which realizes more representative pedestrian feature extraction. Secondly, a composite metric method of Gaussian relation metric is proposed in the metric module. This method realizes the comprehensive metric of pedestrian features in kernel space and relation level and improves the reliability of pedestrian similarity measurement. Finally, experiments on three small datasets, Market-Tiny, Duke-Tiny, and MSMT17-Tiny, demonstrate the effectiveness of the proposed method.
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
Zou, G., Fu, G., Peng, X., Liu, Y., Gao, M., Liu, Z.: Person re-identification based on metric learning: a survey. Multimed. Tools Appl. 80(17), 26855–26888 (2021)
Liu, Z., Feng, C., Chen, S., Hu, J.: Knowledge-preserving continual person re-identification using graph attention network. Neural Netw. 161, 105–115 (2023)
Song, Y., Wang, T., Cai, P., Mondal, S.K., Sahoo, J.P.: A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities. ACM Comput. Surv. (2023)
Lv, J., Chen, W., Li, Q., Yang, C.: Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7948–7956 (2018)
Ding, G., Khan, S., Tang, Z., Zhang, J., Porikli, F.: Towards better validity: dispersion based clustering for unsupervised person re-identification. arXiv preprint arXiv:1906.01308 (2019)
Mehrotra, A., Dukkipati, A.: Generative adversarial residual pairwise networks for one shot learning. arXiv preprint arXiv:1703.08033 (2017)
Schwartz, E., et al.: Delta-encoder: an effective sample synthesis method for few-shot object recognition. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208 (2018)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135. PMLR (2017)
Lu, Y., Wang, Y., Wang, W.: Transformer-based few-shot and fine-grained image classification method. Comput. Eng. Appl. 1–11 (2022)
Meng, H., Tian, Y., Sun, Y., Li, T.: Few shot ship recognition based on universal attention relationnet. Chin. J. Sci. Instrum. 42(12), 220–227 (2021)
Wertheimer, D., Tang, L., Hariharan, B.: Few-shot classification with feature map reconstruction networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8012–8021 (2021)
Lee, S., Moon, W., Heo, J.-P.: Task discrepancy maximization for fine-grained few-shot classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5331–5340 (2022)
Li, X., Wu, J., Sun, Z., Ma, Z., Cao, J., Xue, J.-H.: BSNet: bi-similarity network for few-shot fine-grained image classification. IEEE Trans. Image Process. 30, 1318–1331 (2020)
Xie, J., Long, F., Lv, J., Wang, Q., Li, P.: Joint distribution matters: deep Brownian distance covariance for few-shot classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7972–7981 (2022)
Afrasiyabi, A., Larochelle, H., Lalonde, J.-F., Gagné, C.: Matching feature sets for few-shot image classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9014–9024 (2022)
Acknowledgments
This work is supported by the Shandong Provincial Natural Science Foundation (No. ZR2022MF307), and the National Natural Science Foundation of China (No. 61801272).
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 Singapore Pte Ltd.
About this paper
Cite this paper
Chen, G., Zou, G., Li, J., Zhang, X. (2023). Few-Shot Person Re-identification Based on Hybrid Pooling Fusion and Gaussian Relation Metric. In: Jia, W., et al. Biometric Recognition. CCBR 2023. Lecture Notes in Computer Science, vol 14463. Springer, Singapore. https://doi.org/10.1007/978-981-99-8565-4_24
Download citation
DOI: https://doi.org/10.1007/978-981-99-8565-4_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8564-7
Online ISBN: 978-981-99-8565-4
eBook Packages: Computer ScienceComputer Science (R0)