Abstract
To explore discriminative information fully and keep consistence of labels, an unsupervised person re-identification algorithm based on soft multi-label and compound attention model was proposed in this study. Based on learning of reference agent labels, soft multi-label was built by constructing a mapping model of targets and reference datasets. Later, soft multi-label was added into initial samples through deep convolutional network training to realize accurate labeling of targets and fine-grain classification of features under multi-camera scenes. In the training stage of the deep network, a compound attention mechanism is added between the convolution blocks to fuse the complementary information of the multiple channels features and the spaces domain features, therefore the potential discriminative information is explored. In addition, a weight fusion of distance loss function, label consistency loss function, and reference agent loss function was performed to distinguish hard negative pair set and realize matching of multi-camera labels. Since learning rate is the key influencing factor against the improvement of identification precision and training speed, a rectified adaptive moment estimation was adopted to achieve adaptive control of learning rate, accelerate training convergence of network and increase the robustness of the proposed algorithm. The proposed algorithm is proved by an experiment that it can increase identification precision significantly. The rank-1 of the proposed algorithm is at least 3.9% higher, and its mean average precision (mAP) is at least 4.7% higher compared to those of similar representative algorithms.
Similar content being viewed by others
References
Cheng D, Gong Y, Zhou S et al (2016) Person re-identification by multi-channel parts-based cnn with improved triplet loss function. Proc IEEE Conf Comput Vis Pattern Recognit:1335–1344
Deng W, Zheng L, Ye Q et al (2018) Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. Proc IEEE Conf Comput Vis Pattern Recognit:994–1003
Fan H, Zheng L, Yan C et al (2018) Unsupervised person re-identification: Clustering and fine-tuning. ACM Trans Multimedia Comput Commun Appl (TOMM) 14(4):83
Fu Y, Wei Y, Wang G, et al. (2019) Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification. Proceedings of the IEEE International Conference on Computer Vision, 6112–6121
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. Proc IEEE Conf Comput Vis Pattern Recognit:770–778
He R, Wu X, Sun Z, Tan T (2018) Wasserstein cnn: learning invariant features for nir-Vis face recognition. IEEE Trans Pattern Anal Mach Intell 41(7):1761–1773
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. Proc IEEE Conf Comput Vis Pattern Recognit:7132–7141
Li G, Yu Y (2016) Visual saliency detection based on multiscale deep CNN features. IEEE Trans Image Process 25(11):5012–5024
Li Y J, Yang F E, Liu Y C, et al. (2018) Adaptation and re-identification network: An unsupervised deep transfer learning approach to person re-identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 172–178
Li W, Zhu X, Gong S (2018) Harmonious attention network for person re-identification. Proc IEEE Conf Comput Vis Pattern Recognit:2285–2294
Li M, Zhu X, Gong S (2019) Unsupervised Tracklet person re-identification. IEEE Trans Pattern Anal Mach Intell 42(7):1770–1782
Li Y J, Lin C S, Lin Y B, et al. (2019) Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. Proceedings of the IEEE International Conference on Computer Vision, 7919–7929
Lin S, Li H, Li CT et al (2018) Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. arXiv preprint arXiv:1807.01440
Lin Y, Zheng L, Zheng Z, Wu Y, Hu Z, Yan C, Yang Y (2019) Improving person re-identification by attribute and identity learning. Pattern Recogn 95:151–161
Lin Y, Dong X, Zheng L, Yan Y, Yang Y (2019) A bottom-up clustering approach to unsupervised person re-identification. Proc AAAI Conf Artif Intell 33:8738–8745
Liu C, Gong S, Loy C C, et al. (2012) Person re-identification: what features are important? European Conference on Computer Vision. Springer Berlin: Heidelberg, 391–401
Liu L, Jiang H, He P et al (2019) On the variance of the adaptive learning rate and beyond. arXiv preprint arXiv:1908.03265
Song C, Huang Y, Ouyang W, et al. (2018) Mask-guided contrastive attention model for person re-identification. Comput Vis Pattern Recognit, 1179–1188
Song L, Wang C, Zhang L, du B, Zhang Q, Huang C, Wang X (2020) Unsupervised domain adaptive re-identification: theory and practice. Pattern Recogn 102:107173
Tan S, Zheng F, Liu L, Han J, Shao L (2016) Dense invariant feature-based support vector ranking for cross-camera person reidentification [J]. IEEE Trans Circ Sys Video Technol 28(2):356–363
Wang J, Zhu X, Gong S et al (2018) Transferable joint attribute-identity deep learning for unsupervised person re-identification. Proc IEEE Conf Comput Vis Pattern Recognit:2275–2284
Wei L, Zhang S, Gao W et al (2018) Person transfer Gan to bridge domain gap for person re-identification. Proc IEEE Conf Comput Vis Pattern Recognit:79–88
Woo S, Park J, Lee J Y, et al. (2018) CBAM: Convolutional block attention model. Proceedings of the European Conference on Computer Vision (ECCV), 3–19
Wu J, Yang Y, Liu H, et al. (2019) Unsupervised graph association for person re-identification. Proceedings of the IEEE International Conference on Computer Vision, 8321–8330
Wu A, Zheng W S, Lai J H (2019) Unsupervised person re-identification by camera-aware similarity consistency learning. Proceedings of the IEEE International Conference on Computer Vision, 6922–6931
Wu L, Hong R, Wang Y, Wang M (2019) Cross-entropy adversarial view adaptation for person re-identification. IEEE Trans Circ Syst Video Technol 30(7):2081–2092
Xiao T, Li H, Ouyang W et al (2016) Learning deep feature representations with domain guided dropout for person re-identification. Proc IEEE Conf Comput Vis Pattern Recognit:1249–1258
Xin X, Wang J, Xie R, Zhou S, Huang W, Zheng N (2019) Semi-supervised person re-identification using multi-view clustering. Pattern Recogn 88:285–297
Xu J, Zhao R, Zhu F, et al. (2018) Attention-aware compositional network for person re-identification. Comput Vis Pattern Recognit, 2119–2128
Yang Q, Yu H X, Wu A, et al. (2019) Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3633–3642.
Ye M, Li J, Ma AJ, Zheng L, Yuen PC (2019) Dynamic graph co-matching for unsupervised video-based person re-identification. IEEE Trans Image Process 28(6):2976–2990
Yu H X, Wu A, Zheng W S (2017) Cross-view asymmetric metric learning for unsupervised person re-identification. Proceedings of the IEEE International Conference on Computer Vision, 994–1002
Yu HX, Wu A, Zheng WS (2018) Unsupervised person re-identification by deep asymmetric metric embedding. IEEE Trans Pattern Anal Mach Intell 42(4):956–973
Yu H X, Zheng W S, Wu A, et al. (2019) Unsupervised Person Re-identification by Soft multi-label Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2148–2157
Zeiler M D, Fergus R (2014) Visualizing and understanding convolutional networks. European conference on computer vision. Springer: Cham, 818–833
Zhang X, Jing XY, Zhu X, Ma F (2020) Semi-supervised person re-identification by similarity-embedded cycle GANs [J]. Neural Comput & Applic 32:1–10
Zhao H, Tian M, Sun S et al (2017) Spindle net: person re-identification with human body region guided feature decomposition and fusion. Proc IEEE Conf Comput Vis Pattern Recognit:1077–1085
Zheng L, Shen L, Tian L, et al. (2015) Scalable person re-identification: a benchmark. Proceedings of the IEEE International Conference on Computer Vision, 1116–1124
Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984
Zheng Z, Zheng L, Yang Y (2017) Unlabeled samples generated by Gan improve the person re-identification baseline in vitro. Proceedings of the IEEE International Conference on Computer Vision, 3754–3762
Zhong Z, Zheng L, Cao D et al (2017) Re-ranking person re-identification with k-reciprocal encoding. Proc IEEE Conf Comput Vis Pattern Recognit:1318–1327
Zhong Z, Zheng L, Li S, et al. (2018) Generalizing a person retrieval model hetero-and homogeneously. Proceedings of the European Conference on Computer Vision (ECCV), 172–188.
Acknowledgments
The authors thank the anonymous reviewers and editors for the very constructive comments. This work was supported by the National Natural Science Foundation of China(61962046, 62001255, 61841204). Inner Mongolia Outstanding Youth Cultivation Fund(2018JQ02). Inner Mongolia Science and Technology Plan Project (Research and implementation of key technologies for intelligent analysis platform of traffic big data). Inner Mongolia Science and Technology Plan Project. Inner Mongolia Natural Science Foundation (2019MS06003).
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
Baohua, Z., Siyu, Z., Yufeng, Z. et al. A novel unsupervised person re-identification algorithm based on soft multi-label and compound attention model. Multimed Tools Appl 81, 24081–24098 (2022). https://doi.org/10.1007/s11042-022-12728-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12728-z