Abstract
Person re-identification (ReID) is mainly aimed at establishing correct identity correspondence among moving person collected by multiple cameras. Extending labeled data sets with pseudo-labels is one of the common methods of ReID. However, single evaluation standards and fixed screening pseudo-label methods make pseudo-labels gradually weaken their update rate. Based on that, we propose a semi-supervised adaptive stepwise learning (SSAS) method for accelerating the update of pseudo-labels. Using the concept of Kullback–Leibler divergence, a more global pseudo-label update idea (GPLU) is proposed, an evaluation criterion of pseudo-labels is designed to satisfy two conditions: The first is to use simple tracklets as pseudo-label data in the early stage, and the second is to gradually add complex and diverse tracklets as pseudo-label data in the iterative process. Our proposed adaptive pseudo-label screening strategy steadily improves the recognition accuracy of ReID. In addition, we conduct extensive experiments on canonical data sets and the evaluation results suggest the superiority of our method.
Similar content being viewed by others
References
Ruiz I, Raducanu B, Mehta R, Amores J (2020) Optimizing speed/accuracytrade-off for person re-identification via knowledge distillation. Eng Appl Artif Intell 87:103309
McLaughlin N, Del Rincon JM, Miller P (2016) Recurrent convolutional network for video-based person re-identification. In: Proceedings of the IEEEconference on computer vision and pattern recognition, pp 1325–1334
Wu L, Shen C, Hengel Avd (2016) Deep recurrent convolutional networks for video-based person re-identification: An end-to-end approach. arXiv preprint arXiv:1606.01609
Xu S, Cheng Y, Gu K, Yang Y, Chang S, Zhou P (2017) Jointly attentive spatial-temporal pooling networks for video-based person re-identification.In: Proceedings of the IEEE international conference on computer vision, pp 4733–4742
Zhang W, Hu S, Liu K, Zha Z (2018) Learning compact appearance representation for video-based person re-identification. IEEE Trans. Circuits Syst Video Tech 29(8):2442
Zhong Z, Zheng L, Zheng Z, Li S, Yang Y (2018) Camera style adaptation for person re-identification. In: Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition, pp 5157–5166
Zhou Z, Huang Y, Wang W, Wang L, Tan T (2017) See the forest for the trees:Joint spatial and temporal recurrent neural networks for video-based personre-identification. In: Proceedings of the IEEE Conference on Computer Visionand Pattern Recognition, pp 4747–4756
Bak S, Carr P (2017) One-shot metric learning for person re-identification. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recog-nition, pp 2990–2999
Figueira D, Bazzani L, Minh HQ, Cristani M, Bernardino A, Murino V (2013) Semi-supervised multi-feature learning for person re-identification. In: 2013 10th IEEE international conference on advanced video and signal basedsurveillance, IEEE, pp 111–116
Liu X, Song M, Tao D, Zhou X, Chen C, Bu J (2014) Semi-supervised coupleddictionary learning for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3550–3557
Ma AJ, Li P (2014) Semi-supervised ranking for re-identification with few labeled image pairs. In: Asian Conference on Computer Vision, Springer, pp 598–613
Fan H, Zheng L, Yan C, Yang Y (2018) Unsupervised person re-identification: clustering and fine-tuning. ACM Transact Multimed Comput Commun Appl TOMM 14(4):1
Ye M, Ma AJ, Zheng L, Li J, Yuen PC (2017) Dynamic label graph matching for unsupervised video re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 5142–5150
Chapelle O, Scholkopf B, Zien A (2009) Semi-supervised learning (chapelle,o. et al., eds.; 2006)[book reviews]. IEEE Trans Neural Netw 20(3):542–542
Lee J, Kim E, Lee S, Lee J, Yoon S (2019) Ficklenet: Weakly and semi-supervised semantic image segmentation using stochastic inference. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5267–5276
Moon TK (1996) The expectation-maximization algorithm. IEEE Signal Process Mag 13(6):47
Ouali Y, Hudelot C, Tami M (2020) An overview of deep semi-supervised learning. arXiv preprint arXiv:2006.05278
Shi W, Gong Y, Ding C, MaXiaoyu Tao Z, Zheng N (2018) Transductive semi-supervised deep learning using min-max features. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 299
Iscen A, Tolias G, Avrithis Y, Chum O (2019) Label propagation for deep semi-supervised learning. In: Proceedings of the IEEE conference on computervision and pattern recognition, pp 5070–5079
Lee S, Kim D, Kim N, Jeong SG (2019) Drop to adapt: Learning discriminative features for unsupervised domain adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp 91–100
Li J, Socher R, Hoi SC (2020) Dividemix: Learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394
Li X, Sun Q, Liu Y, Zhou Q, Zheng S, Chua TS, Schiele B (2019) Learning to self-train for semi-supervised few-shot classification. In: Advances in Neural Information Processing Systems, pp 10276–10286
Berthelot D, Carlini N, Goodfellow I, Papernot N, Oliver A, Raffel CA (2019) Mixmatch: A holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems, pp 5049–5059
Song C, Huang Y, Ouyang W, Wang L (2019) Box-driven class-wise region masking and filling rate guided loss for weakly supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3136–3145
Deng W, Zheng L, Ye Q, Kang G, Yang Y, Jiao J (2018) Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 994–1003
Dong X, Huang J, Yang Y, Yan S (2017) More is less: A more complicated network with less inference complexity. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5840–5848
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Zheng L, Bie Z, Sun Y, Wang J, Su C, Wang S, Tian Q (2016) Mars: A video benchmark for large-scale person re-identification. In: European Conference on Computer Vision, Springer, pp 868–884
Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: European Conference on Computer Vision, Springer, pp 17–35
Zhong Z, Zheng L, Cao D, Li S (2017) Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1318–1327
Liu Z, Wang D, Lu H (2017) Stepwise metric promotion for unsupervised video person re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 2429–2438
Ye M, Lan X, Yuen PC (2018) Robust anchor embedding for unsupervised video person re-identification in the wild. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 170–186
Chen Y, Zhu X, Gong S (2018) Deep association learning for unsupervised video person re-identification. arXiv preprint arXiv:1808.07301
Wu Y, Lin Y, Dong X, Yan Y, Ouyang W, Yang Y (2018) Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5177–5186
Lin Y, Dong X, Zheng L, Yan Y, Yang Y (2019) A bottom-up clustering approach to unsupervised person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 33, pp 8738–8745
Acknowledgements
This work was supported by National Natural Science Foundation of China (Grant No. 61806206, 61772530), Natural Science Foundation of Jiangsu Province (Grant Nos. BK20180639, BK20201346).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ma, D., Zhou, Y., Zhao, J. et al. Video-based person re-identification by semi-supervised adaptive stepwise learning. Pattern Anal Applic 24, 1769–1776 (2021). https://doi.org/10.1007/s10044-021-01016-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-021-01016-5