AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Computational Visual Media Article
PDF (9.7 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Joint training with local soft attention and dual cross-neighbor label smoothing for unsupervised person re-identification

School of Mathematics and Computer Sciences, Nanchang University, Nanchang 330031, China
Institute of Metaverse, Nanchang University, Nanchang 330031, China.
Jiangxi Key Laboratory of Smart City, Nanchang 330031, China.
Show Author Information

Graphical Abstract

Abstract

Existing unsupervised person re-identificationapproaches fail to fully capture the fine-grained features of local regions, which can result in people with similar appearances and different identities being assigned the same label after clustering. The identity-independent information contained in different local regions leads to different levels of local noise. To address these challenges, joint training with local soft attention and dual cross-neighbor label smoothing (DCLS) is proposed in this study. First, the joint training is divided into global and local parts, whereby a soft attention mechanism is proposed for the local branch to accurately capture the subtle differences in local regions, which improves the ability of the re-identification model in identifying a person’s local significant features. Second, DCLS is designed to progressively mitigate label noise in different local regions. The DCLS uses global and local similarity metrics to semantically align the global and local regions of the person and further determines the proximity association between local regions through the cross information of neighboring regions, thereby achieving label smoothing of the global and local regions throughout the training process. In extensive experiments, the proposed method outperformed existing methods under unsupervised settings on several standard person re-identification datasets.

Keywords

person re-identification (Re-ID)unsupervised learning (USL)local soft attentionjoint trainingdual cross-neighbor label smoothing (DCLS)

References

[1]
Han, Q.; Liu, H.; Min, W.; Huang, T.; Lin, D.; Wang, Q.3D skeleton and two streams approach to person re-identification using optimized region matching. ACM Transactions on Multimedia Computing, Communications, and Applications Vol. 18, No. 2s, Article No. 129, 2022.
Crossref Google Scholar
[2]
Wang, Q.; Min, W.; Han, Q.; Yang, Z.; Xiong, X.; Zhu, M.; Zhao, H. Viewpoint adaptation learning with cross-view distance metric for robust vehicle re-identification. Information Sciences Vol. 564, 71–84, 2021.
Crossref Google Scholar
[3]
Wang, Q.; Min, W.; He, D.; Zou, S.; Huang, T.; Zhang, Y.; Liu, R. Discriminative fine-grained network for vehicle re-identification using two-stage re-ranking. Science China Information Sciences Vol. 63, No. 11, Article No. 212102, 2020.
Crossref Google Scholar
[4]
Bai, Y.; Wang, C.; Lou, Y.; Liu, J.; Duan, L. Y.Hierarchical connectivity-centered clustering forunsupervised domain adaptation on person re-identification. IEEE Transactions on Image Processing Vol. 30, 6715–6729, 2021.
Crossref Google Scholar
[5]
Li, Y.; Yao, H.; Xu, C. Intra-domain consistency enhancement for unsupervised person re-identification. IEEE Transactions on Multimedia Vol. 24, 415–425, 2022.
Crossref Google Scholar
[6]
Li, Y.; Yao, H.; Xu, C. TEST: Triplet ensemble student-teacher model for unsupervised person re-identification. IEEE Transactions on Image Processing Vol. 30, 7952–7963, 2021.
Crossref Google Scholar
[7]
Sun, J.; Li, Y.; Chen, H.; Peng, Y.; Zhu, J. Unsupervised cross domain person re-identification by multi-loss optimization learning. IEEE Transactions on Image Processing Vol. 30, 2935–2946, 2021.
Crossref Google Scholar
[8]
Li, M.; Zhu, X.; Gong, S. Unsupervised tracklet person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 42, No. 7, 1770–1782, 2020.
Crossref Google Scholar
[9]
Lin, Y.; Wu, Y.; Yan, C.; Xu, M.; Yang, Y. Unsupervised person re-identification via cross-camera similarity exploration. IEEE Transactions on Image Processing Vol. 29, 5481–5490, 2020.
Crossref Google Scholar
[10]
Ding, Y.; Fan, H.; Xu, M.; Yang, Y. Adaptive exploration for unsupervised person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications Vol. 16, No. 1, Article No. 3, 2020.
Crossref Google Scholar
[11]
Wang, Z.; Jiang, J.; Wu, Y.; Ye, M.; Bai, X.; Satoh, S. Learning sparse and identity-preserved hidden attributes for person re-identification. IEEE Transactions on Image Processing Vol. 29, 2013–2025, 2020.
Crossref Google Scholar
[12]
Fan, H.; Zheng, L.; Yan, C.; Yang, Y. Unsupervised person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications Vol. 14, No. 4, Article No. 83, 2018.
Crossref Google Scholar
[13]
Yu, H. X.; Wu, A.; Zheng, W. S. Cross-view asymmetric metric learning for unsupervised person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, 994–1002, 2017.
Crossref
[14]
Wu, J.; Liao, S.; Lei, Z.; Wang, X.; Yang, Y.; Li, S. Z. Clustering and dynamic sampling based unsupervised domain adaptation for person re-identification. In: Proceedings of the IEEE International Conference on Multimedia and Expo, 886–891, 2019.
Crossref
[15]
Fu, Y.; Wei, Y.; Wang, G.; Zhou, Y.; Shi, H.; Uiuc, U.; Huang, T. 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, 6111–6120, 2019.
Crossref
[16]
Yang, Q.; Yu, H. X.; Wu, A.; Zheng, W. S. Patch-based discriminative feature learning for unsupervised person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3628–3637, 2019.
Crossref
[17]
Lin, Y.; Xie, L.; Wu, Y.; Yan, C.; Tian, Q. Unsupervised person re-identification via softened similarity learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3387–3396, 2020.
Crossref
[18]
Lin, S.; Li, H.; Li, C. T.; Kot, A. C. Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. arXiv preprint arXiv:1807.01440, 2018.
Google Scholar
[19]
Huang, Y.; Peng, P.; Jin, Y.; Li, Y.; Xing, J. Domain adaptive attention learning for unsupervised person re-identification. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence, 11069–11076, 2020.
Crossref
[20]
Wei, L.; Zhang, S.; Gao, W.; Tian, Q. Person transfer GAN to bridge domain gap for person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 79–88, 2018.
Crossref
[21]
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. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 994–1003, 2018.
Crossref
[22]
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, 2242–2251, 2017.
Crossref
[23]
Chen, Y.; Zhu, X.; Gong, S. Instance-guided context rendering for cross-domain person re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 232–242, 2019.
Crossref
[24]
Wang, Q.; Min, W.; Han, Q.; Liu, Q.; Zha, C.; Zhao, H.; Wei, Z. Inter-domain adaptation label for data augmentation in vehicle re-identification. IEEE Transactions on Multimedia Vol. 24, 1031–1041, 2022.
Crossref Google Scholar
[25]
Ge, Y.; Chen, D.; Li, H. Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. In: Proceedings of the International Conference on Learning Representations, 2020.
[26]
Ge, Y.; Zhu, F.; Chen, D.; Zhao, R. Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, Article No. 949, 11309–11321, 2020.
[27]
Lin, Y.; Dong, X.; Zheng, L.; Yan, Y.; Yang, Y. A bottom-up clustering approach to unsupervised person re-identification. Proceedings of the AAAI Conference on Artificial Intelligence Vol. 33, No. 1, 8738–8745, 2019.
Crossref Google Scholar
[28]
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.
Crossref Google Scholar
[29]
Zeng, K.; Ning, M.; Wang, Y.; Guo, Y. Hierarchicalclustering with hard-batch triplet loss for person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13654–13662, 2020.
Crossref
[30]
Zheng, F.; Deng, C.; Sun, X.; Jiang, X.; Guo, X.; Yu, Z.; Huang, F.; Ji, R. Pyramidal person re-identification via multi-loss dynamic training. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8506–8514, 2019.
Crossref
[31]
Wang, G.; Yuan, Y.; Chen, X.; Li, J.; Zhou, X. Learning discriminative features with multiple granularities for person re-identification. In: Proceedings of the 26th ACM International Conference on Multimedia, 274–282, 2018.
Crossref
[32]
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: Computer Vision – ECCV 2018. Lecture Notes in Computer Science, Vol. 11208. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 501–518, 2018.
Crossref
[33]
He, T.; Shen, L.; Guo, Y.; Ding, G.; Guo, Z. SECRET: Self-consistent pseudo label refinement for unsupervised domain adaptive person re-identification. Proceedings of the AAAI Conference on Artificial Intelligence Vol. 36, No. 1, 879–887, 2022.
Crossref Google Scholar
[34]
Ester, M.; Kriegel, H.; Sander, J.; Xu, X. A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, 226–231, 1996.
[35]
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, 770–778, 2016.
Crossref
[36]
Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818–2826, 2016.
Crossref
[37]
Komodakis, N.; Zagoruyko, S. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. In: Proceedings of the International Conference on Learning Representations, 2017.
[38]
Lukasik, M.; Bhojanapalli, S.; Menon, A. K.; Kumar, S. Does label smoothing mitigate label noise? In: Proceedings of the 37th International Conference on Machine Learning, 6448–6458, 2020.
[39]
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, 1116–1124, 2015.
Crossref
[40]
Ristani, E.; Solera, F.; Zou, R.; Cucchiara, R.; Tomasi, C. Performance measures and a data set for multi-target, multi-camera tracking. In: Computer Vision – ECCV 2016 Workshops. Lecture Notes in Computer Science, Vol. 9914. Hua, G.; Jégou, H. Eds. Springer Cham, 17–35, 2016.
Crossref
[41]
Zhong, Z.; Zheng, L.; Cao, D.; Li, S. Re-ranking person re-identification with k-Reciprocal encoding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3652–3661, 2017.
Crossref
[42]
Deng, J.; Dong, W.; Socher, R.; Li, L. J.; Li, K.; Li, F. F. ImageNet: A large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 248–255, 2009.
Crossref
[43]
Zhong, Z.; Zheng, L.; Kang, G.; Li, S.; Yang, Y. Random erasing data augmentation. Proceedings of the AAAI Conference on Artificial Intelligence Vol. 34, No. 7, 13001–13008, 2020.
Crossref Google Scholar
[44]
Kingma, D. P.; Ba, J. L. Adam: A method for stochastic optimization. In: Proceedings of the 3rd International Conference for Learning Representations, 2015.
[45]
Wang, D.; Zhang, S. Unsupervised person re-identificationvia multi-label classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10978–10987, 2020.
Crossref
[46]
Li, J.; Zhang, S. Joint visual and temporal consistency for unsupervised domain adaptive person re-identification. In: Computer Vision – ECCV 2020. Lecture Notes in Computer Science, Vol. 12369. Vedaldi, A.; Bischof, H.; Brox, T.; Frahm, J. M. Eds. Springer Cham, 483–499, 2020.
Crossref
[47]
Ji, H.; Wang, L.; Zhou, S.; Tang, W.; Zheng, N.; Hua, G. Meta pairwise relationship distillation for unsupervised person re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 3641–3650, 2021.
Crossref
[48]
Chen, H.; Wang, Y.; Lagadec, B.; Dantcheva, A.; Bremond, F. Joint generative and contrastive learning for unsupervised person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004–2013, 2021.
Crossref
[49]
Hu, Z.; Zhu, C.; He, G. Hard-sample guided hybrid contrast learning for unsupervised person re-identification. In: Proceedings of the 7th IEEE International Conference on Network Intelligence and Digital Content, 91–95, 2021.
Crossref
[50]
Chen, H.; Lagadec, B.; Bremond, F. Ice: Inter-instance contrastive encoding for unsupervised person re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, 14940–14949, 2021.
Crossref
[51]
Luo, H.; Wang, P.; Xu, Y.; Ding, F.; Zhou, Y.; Wang, F.; Li, H.; Jin, R. Self-supervised pre-training for transformer-based person re-identification. arXiv preprint arXiv:2111.12084, 2021.
Google Scholar
[52]
Zhai, Y.; Lu, S.; Ye, Q.; Shan, X.; Chen, J.; Ji, R.; Tian, Y. AD-cluster: Augmented discriminative clustering for domain adaptive person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9018–9027, 2020.
Crossref
[53]
Zhang, M.; Liu, K.; Li, Y.; Guo, S.; Duan, H.; Long, Y.; Jin, Y. Unsupervised domain adaptation for person re-identification via heterogeneous graph alignment. Proceedings of the AAAI Conference on Artificial Intelligence Vol. 35, No. 4, 3360–3368, 2021.
Crossref Google Scholar
[54]
Luo, C.; Song, C.; Zhang, Z. Generalizing person re-identification by camera-aware invariance learning and cross-domain mixup. In: Computer Vision – ECCV 2020. Lecture Notes in Computer Science, Vol. 12360. Vedaldi, A.; Bischof, H.; Brox, T.; Frahm, J. M. Eds. Springer Cham, 224–241, 2020.
Crossref
[55]
Zhao, F.; Liao, S.; Xie, G. S.; Zhao, J.; Zhang, K.; Shao, L. Unsupervised domain adaptation with noise resistible mutual-training for person re-identification. In: Computer Vision – ECCV 2020. Lecture Notes in Computer Science, Vol. 12356. Vedaldi, A.; Bischof, H.; Brox, T.; Frahm, J. M. Eds. Springer Cham, 526–544, 2020.
Crossref
[56]
Chen, G.; Lu, Y.; Lu, J.; Zhou, J. Deep credible metric learning for unsupervised domain adaptation person re-identification. In: Computer Vision – ECCV 2020. Lecture Notes in Computer Science, Vol. 12353. Vedaldi, A.; Bischof, H.; Brox, T.; Frahm, J. M. Eds. Springer Cham, 643–659, 2020.
Crossref
[57]
Zhai, Y.; Ye, Q.; Lu, S.; Jia, M.; Ji, R.; Tian, Y. Multiple expert brainstorming for domain adaptive person re-identification. In: Computer Vision – ECCV 2020. Lecture Notes in Computer Science, Vol. 12352. Vedaldi, A.; Bischof, H.; Brox, T.; Frahm, J. M. Eds. Springer Cham, 594–611, 2020.
Crossref
[58]
Zheng, K.; Lan, C.; Zeng, W.; Zhang, Z.; Zha, Z. J. Exploiting sample uncertainty for domain adaptive person reidentification. Proceedings of the AAAI Conference on Artificial Intelligence Vol. 35, No. 4, 3538–3546, 2021.
Crossref Google Scholar
[59]
Zheng, K.; Liu, W.; He, L.; Mei, T.; Luo, J.; Zha, Z. J. Group-aware label transfer for domain adaptive person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5306–5315, 2021.
Crossref
[60]
Zhong, Z.; Zheng, L.; Luo, Z.; Li, S.; Yang, Y. Invariance matters: Exemplar memory for domain adaptive person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 598–607, 2019.
Crossref
[61]
Woo, S.; Park, J.; Lee, J. Y.; Kweon, I. S. CBAM: Convolutional block attention module. In: Computer Vision – ECCV 2018. Lecture Notes in Computer Science, Vol. 11211. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 3–19, 2018.
Crossref
[62]
Wang, Q.; Wu, B.; Zhu, P.; Li, P.; Zuo, W.; Hu, Q. ECA-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11531–11539, 2020.
Crossref
[63]
Hu, J.; Shen, L.; Sun, G. Squeeze-and-excitation networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7132–7141, 2018.
Crossref
[64]
Van der Maaten, L.; Hinton, G. Visualizing data using t-SNE. Journal of Machine Learning Research Vol. 9, No. 11, 2579–2605, 2008.
Google Scholar
[65]
Pan, X.; Luo, P.; Shi, J.; Tang, X. Two at once: Enhancing learning and generalization capacities via IBN-net. In: Computer Vision – ECCV 2018. Lecture Notes in Computer Science, Vol. 11208. Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. Eds. Springer Cham, 484–500, 2018.
Crossref
Computational Visual Media
Volume 10 Issue 3,
June 2024
Pages 543-558
DOI: 10.1007/s41095-023-0354-4
Cite this article:
Han Q, Li L, Min W, et al. Joint training with local soft attention and dual cross-neighbor label smoothing for unsupervised person re-identification. Computational Visual Media, 2024, 10(3): 543-558. https://doi.org/10.1007/s41095-023-0354-4

258

Views

3

Downloads

2

Crossref

1

Web of Science

2

Scopus

0

CSCD

Altmetrics
Received: 28 February 2023
Accepted: 26 April 2023
Published: 27 April 2024
© The Author(s) 2024.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduc-tion in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Other papers from this open access journal are available free of charge from http://www.springer.com/journal/41095. To submit a manuscript, please go to https://www.editorialmanager.com/cvmj.
Return