An Improved Split-Attention Architecture Based on Circle Loss for Person Re-Identification
AbstractPerson re-identification aims to match pedestrian images across multiple surveillance camera views. It is still a challenging task due to the partial occlusion of pedestrian images, variations in the illumination of surveillance cameras, and similar appearances of pedestrians and so on. In order to improve the representation ability of pedestrian features extracted from the convolutional neural networks, in this paper, we proposed an improved split-attention architecture for person re-identification. Specifically, we first divide the feature map into two sub-groups and then split the features in each subgroup into three more fine-grained sub-feature maps. Moreover, in order to minimize the inter-class similarity and maximize the intra-class similarity, we use circle loss and identification loss to optimize our network together. Circle loss makes the similarity scores learn at different paces, which benefits deep feature learning. The circle loss not only makes the model have higher optimization flexibility but also makes the convergence target of the model more definite. Unlike many methods that use complex convolutional neural networks to represent pedestrian feature maps in a layer-wise manner, our proposed method improves the representation ability of pedestrian features at a more fine-grained level. We evaluated the performance of our proposed network on two large-scale person re-identification benchmark datasets Market-1501 and DukeMTMC-reID. Experimental results show that the proposed split-attention network outperforms the state-of-the-art methods on both datasets with only using pedestrian global features.
P. Chikontwe and H. J. Lee, "Deep multi-task network for learning person identity and attributes," IEEE Access, vol. 6, pp. 60801-60811, 2018, Doi: 10.1109/ACCESS.2018.2875783.
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE CVPR, USA, 2016, pp. 770-778.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," in Proc. IEEE CVPR, USA, 2015, pp. 1-9.
H. Zhang, C. Wu, Z. Zhang, Y. Zhu, Z. Zhang, H. Lin, Y. Sun, T. He, J. Mueller, and R. Manmatha, "Resnest: Split-attention networks," arXiv preprint arXiv:2004.08955, 2020. [Online]. Available: https://arxiv.org/abs/2004.08955
Y. Sun, C. Cheng, Y. Zhang, C. Zhang, L. Zheng, Z. Wang, and Y. Wei, "Circle loss: A unified perspective of pair similarity optimization," in Proc. IEEE CVPR, USA, 2020, pp. 6398-6407.
L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, "Scalable person re-identification: A benchmark," in Proc. IEEE ICCV, Chile, 2015, pp. 1116-1124.
E. Ristani, F. Solera, R. Zou, R. Cucchiara, and C. Tomasi, "Performance measures and a data set for multi-target, multi-camera tracking," in Proc. ECCV, Netherlands, 2016, pp. 17-35.
Z. Zheng, L. Zheng, and Y. Yang, "Unlabeled samples generated by gan improve the person re-identification baseline in vitro," in Proc. IEEE ICCV, Italy, 2017, pp. 3754-3762.
Z. Zheng, L. Zheng, and Y. Yang, "A discriminatively learned cnn embedding for person reidentification," ACM Trans. Multimed. Comput. Commun. Appl., vol. 14, no. 1, pp. 1-20, Jan. 2017, DOI:https://doi.org/10.1145/3159171.
Y. Sun, L. Zheng, Y. Yang, Q. Tian, and S. Wang, "Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline)," in Proc. ECCV, Germany, 2018, pp. 480-496.
H. Luo, Y. Gu, X. Liao, S. Lai, and W. Jiang, "Bag of tricks and a strong baseline for deep person re-identification," in Proc. CVPRW, USA, 2019, pp. 0-0.
A. Hermans, L. Beyer, and B. Leibe, "In defense of the triplet loss for person re-identification," arXiv preprint arXiv:1703.07737, 2017, [Online]. Available: https://arxiv.org/abs/1703.07737
Copyright (c) 2021 Zongjing Cao, Hyo Jong Lee
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.