Abstract
Person re-identification (Re-ID) aims to find the person across non-overlapping camera views in public places. Existing methods are getting better and better at learning finer pedestrian details, but at the same time they all ignore the relations between these details, which makes some details that are critical to discrimination unable to play a key role in decision-making. To solve this problem, we propose a graph relation learning method for person re-identification. Firstly, we use graph structure to build the relation graph, and then use the weight operation to get the relation vertices that can receive suggestions from other details. Finally, by using the collaborative training scheme to train relation vertices and regional global average features, our model can learn the relation information. Extensive experiments show that the proposed method can effectively improve the discriminative ability of the model, enhance the role of neglected important clues in decision-making, and achieve state-of-the-arts performance on the more challenging CUHK03-NP dataset.
Similar content being viewed by others
References
Martin K, Martin H, Paul W, Peter MR, Horst B (2012) Large scale metric learning from equivalence constraints. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 2288–2295
Yang Y, Yang J, Yan J, Liao S, Yi D, Li SZ (2014) Salient color names for person re-identification. In: European conference on computer vision. Springer, pp 536–551
Chen Y, Shin H (2020) Multispectral image fusion based pedestrian detection using a multilayer fused deconvolutional single-shot detector. JOSA A 37(5):768–779
Zhang Y, Wang X, Bi X, Tao D (2018) A light dual-task neural network for haze removal. IEEE Signal Process Lett 25(8):1231–1235
Wan X, Zhao C (2017) Local receptive field constrained stacked sparse autoencoder for classification of hyperspectral images. JOSA A 34(6):1011–1020
Lyu J, Bi X, Ling SH (2020) Multi-level cross residual network for lung nodule classification. Sensors 20(10):2837
Jun Yu, Yang X, Gao F, Tao D (2016) Deep multimodal distance metric learning using click constraints for image ranking. IEEE Trans Cybern 47(12):4014–4024
Yu Z, Yu J, Fan J, Tao D (2017) Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE international conference on computer vision, pp 1821–1830
Jun Y, Tan M, Zhang H, Tao D, Rui Y (2019) Hierarchical deep click feature prediction for fine-grained image recognition. IEEE Trans Pattern Anal Mach Intell
Jun Y, Yao J, Zhang J, Zhou Y, Dacheng T (2020) Single-pixel reconstruction for one-stage instance segmentation. IEEE Transactions on Cybernetics, Sprnet
Yang F, Wei Y, Zhou Y, Shi H, Huang G, Wang X, Yao Z, Huang T (2019) Horizontal pyramid matching for person re-identification. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 8295–8302
Zhou S, Wang F, Huang Z, Wang J (2019) Discriminative feature learning with consistent attention regularization for person re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 8040–8049
Yang W, Huang H, Zhang Z, Chen X, Huang K, Zhang S (2019) Towards rich feature discovery with class activation maps augmentation for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1389–1398
Chen B, Deng W, Hu J (2019) Mixed high-order attention network for person re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 371–381
Zheng M, KaranamS, Wu Z, Radke RJ (2019) Re-identification with consistent attentive siamese networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5735–5744
Sun Y, Zheng L, Yang Y, Tian Q, Wang S (2018) Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European conference on computer vision (ECCV), pp 480–496
Wang Z, Jiang J, Yang W, Ye M, Bai X, Satoh S (2019) Learning sparse and identity-preserved hidden attributes for person re-identification. IEEE Trans Image Process 29(1):2013–2025
Qian X, Fu Y, Xiang T, Wang W, Qiu J, Wu Y, Jiang Y-G, Xue X (2018) Pose-normalized image generation for person re-identification. In: Proceedings of the European conference on computer vision (ECCV), pp 650–667
Liu J, Ni B, Yan Y, Zhou P, Cheng S, Hu J (2018) Pose transferrable person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4099–4108
Kalayeh MM, Basaran E, Gökmen M, Kamasak ME, Shah M (2018) Human semantic parsing for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1062–1071
Xu J, Zhao R, Zhu F, Wang H, Ouyang W (2018) Attention-aware compositional network for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2119–2128
Kang B-N, Kim Y, Jun B, Kim D (2019) Attentional feature-pair relation networks for accurate face recognition. In: Proceedings of the IEEE international conference on computer vision, pp 5472–5481
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
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Lin M, Chen Q, Yan S (2013) Network in network. arXiv preprint arXiv:1312.4400
Song G, Chai W (2018) Collaborative learning for deep neural networks. In: Advances in neural information processing systems, pp 1832–1841
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9
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
Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 152–159
Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: A benchmark. In: Proceedings of the IEEE international conference on computer vision, pp 1116–1124
Zheng Z, Zheng L, Yang Y (2017) 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
Wang X, Doretto G, Sebastian T, Rittscher J, Tu P (2007) Shape and appearance context modeling. In: 2007 IEEE 11th international conference on computer vision. IEEE, pp 1–8
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520
Ma N, Zhang X, Zheng H-T, Sun J (2018) Shufflenet v2: practical guidelines for efficient cnn architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116–131
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
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
Wang, H., Bi, X. Person Re-Identification Based on Graph Relation Learning. Neural Process Lett 53, 1401–1415 (2021). https://doi.org/10.1007/s11063-021-10446-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-021-10446-5