Cross-Domain Person Re-identification Combining Feature Concatenation and Attention
DOI:
https://doi.org/10.54097/hset.v56i.10099Keywords:
cross-domain person re-identification, feature concatenation, position attention module, domain generalizationAbstract
To improve the insufficient generalization and poor cross-domain capability of the existing direct cross-dataset person re-identification methods, a cross-domain person re-identification method combining feature concatenation and attention (FCANet) is proposed. The deep features of the network are concatenated to complement the feature information and obtain discriminatively feature, and the position attention module is introduced to enhance the data feature representation capability of the cross-domain task, using the joint training network of label smooth cross-entropy loss and triplet loss, model training in the source domain, and directly deploy to the target domain for testing. To verify the performance of the proposed method, it was experimented on three public datasets of Market1501, DukeMTMC-reID and MSMT17, which mAP and Rank1can reach 51.4% and 62.7% on Market1501. The results show that the proposed method has good performance in improving the generalization of cross-domain tasks, and the recognition accuracy outperforms the domain generalization algorithms of comparison.
Downloads
References
Gheissari Niloofar, Thomas B. Sebastian, and Richard Hartley. "Person reidentification using spatiotemporal appearance," 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR'06). Vol. 2. IEEE, 2006, pp.1528-1535, doi:10. 1109/CVPR.2006.223.
Yang, Wenjie, Huang Houjing, Zhang Zhang, Chen Xiaotang, Huang Kaiqi and Zhang Shu. "Towards rich feature discovery with class activation maps augmentation for person re-identification," Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019, pp.1389-1398, doi:10.1109/CVPR.2019. 00148.
Fu Yang, Wei Yunchao, Zhou Yuqian, et al. "Horizontal pyramid matching for person re-identification," Proceedings of the AAAI conference on artificial intelligence. Vol. 33. No. 01. 2019, pp.8295-8302, doi:10.1609/aaai.v33i01.33018295.
Ge, Yixiao, Dapeng Chen, and Hongsheng Li. "Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification," arXiv preprint arXiv:2001.01526 (2020). doi:10.48550/arXiv.2001.01526.
Zhai Yunpeng, Lu Shijian, Ye Qixiang, et al. "AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) IEEE, 2020, pp.9021-9030, doi:10.1109/CVPR42600.2020.00904.
Deng Weijian, Zheng Liang, Ye Qixiang, Kang Guoliang, Yang Yi, and Jiao Jianbin."Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification," Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, pp. 994-1003, doi:10.48550/arXiv. 1711.07027.
Zhong Zhun, Zheng Liang, Cao Donglin, and Li Shaozi. "Re-ranking Person Re-identification with k-reciprocal Encoding," IEEE Computer Society IEEE Computer Society, 2017, pp. 1318-1327, doi:10.48550/arXiv.1701.08398.
Zhou Kaiyang, Yang Yongxin, Cavallaro Andrea, and Xiang Tao. "Omni-scale feature learning for person re-identification," Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019, pp.3702 - 3712, doi:10.1109/ICCV.2019.00380.
Zoph, Barret, and Quoc V. Le. "Neural architecture search with reinforcement learning," arXiv preprint arXiv:1611.01578 (2016). doi:10.48550/arXiv.1611.01578.
Fu Jun, Liu Jing, Tian Haijie, et al. "Dual attention network for scene segmentation." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019, pp.3146-3154, doi:10.1109/CVPR.2019.00326.
Wang Jingya, Zhu Xiatian, Gong Shaogang, and Li Wei. "Transferable joint attribute-identity deep learning for unsupervised person re-identification." Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE (2018), pp.2275 － 2284, doi:10.1109/CVPR.2018.00242.
Yang Qize, Yu Hongxing, Wu Ancong, and ZhengWeishi. "Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 3633-3642, doi:10.1109/CVPR.2019.00375.
Ren Chuanxian, Liang Bohua, Ge Pengfei, Zhai Yiming, Lei Zhen. "Domain adaptive person re-identification via camera style generation and label propagation." IEEE Transactions on Information Forensics and Security 15 (2019), pp.1290-1302, doi:10.1109/TIFS.2019. 2939750.
Jiang Kongzhu, Zhang Tianzhu, Zhang Yongdong, Wu Feng, Rui Yong. "Self-supervised agent learning for unsupervised cross-domain person re-identification." IEEE Transactions on Image Processing 29 (2020), p.8549-8560, doi:10.1109/TIP.2020.3016869.
Zhao, Yiru, and Hongtao Lu. "Neighbor similarity and soft-label adaptation for unsupervised cross-dataset person re-identification." Neurocomputing 388 (2020), pp. 246-254, doi:10.1016/j.neucom. 2019.12.115
Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang. "Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 598-607, doi:10.1109/CVPR.2019.00069.
Liao Shengcai, and Ling Shao. "Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting," European Conference on Computer Vision. Springer, Cham, 2020, pp.456-474, doi:10.1007/978-3-030-58621-8_27.
Chen Xiaodong, Liu Xinche, Liu Wu, Zhang Yongdong, Mei Tao. "Explainable Person Re-Identification with Attribute-guided Metric Distillation," Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021, pp.11813-11822, doi:10.1109/ICCV 48922.2021.01160.
LI Yunlong, Cheng Deqiang, LI Jiahan, Huang Ji, Zhang Jianying, Ma Haohui. "Cross-domain Person Re-identification based on Progressive Attention and Block Occlusion," Journal of Beijing University of Aeronautics and Astronautics. 2022, pp.1-13, doi:10.13700/j.bh.1001-5965.2022.0025.
Yang Ping, Wu Xiaohong, He Xiaohai, Chen Honggang, Liu Qiang. "Cross-Domain Person Re-identification Method Based on Point-by-Point Feature Matching," Pattern Recognition and Artificial Intelligence. 2022,35(06), pp.516-525.doi:10.16451/j.cnki.issn1003-6059. 202206004.
Wei Longhui, Zhang Shiliang, Gao Wen, Tian Qi. "Person transfer gan to bridge domain gap for person re-identification." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 79-88, doi:10.1109/CVPR.2018.00016.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
