Person Re-identification Method Based on Hybrid Real-Synthetic Data

Qi Lei; Ren Zihao; Liu Junxi; Geng Xin

doi:10.7544/issn1000-1239.202330718

Journal of Computer Research and Development > 2025 > 62(2): 418-431. > DOI: 10.7544/issn1000-1239.202330718 CSTR: 32373.14.issn1000-1239.202330718

Qi Lei, Ren Zihao, Liu Junxi, Geng Xin. Person Re-identification Method Based on Hybrid Real-Synthetic Data[J]. Journal of Computer Research and Development, 2025, 62(2): 418-431. DOI: 10.7544/issn1000-1239.202330718

Citation:

PDF (2425 KB)

Person Re-identification Method Based on Hybrid Real-Synthetic Data

Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189

Funds: This work was supported by the National Natural Science Foundation of China (62206052, 62125602, 62076063) , the Natural Science Foundation of Jiangsu Province (BK20210224), the China Postdoctoral Science Foundation (2024M750424), the Postdoctoral Fellowship Program of CPSF (GZC20240252), and the Jiangsu Funding Program for Excellent Postdoctoral Talent (2024ZB242).

More Information

Author Bio:
Qi Lei: born in 1989. PhD, assistant researcher. Member of CCF. His main research interests include pattern recognition and computer vision

Ren Zihao: born in 2000. Master candidate. His main research interests include pattern recognition and computer vision

Liu Junxi: born in 1998. Master. Her main research interests include pattern recognition and computer vision

Geng Xin: born in 1978. PhD, professor. Member of CCF. His main research interests include machine learning and computer vision
Received Date: September 05, 2023
Revised Date: December 05, 2023
Available Online: May 16, 2024

Graphical Abstract

Abstract

Abstract

In recent years, the rapid urbanization and development of the social economy have led to a growing focus on public safety issues. Governments across the world are increasingly promoting the construction of smart cities and intelligent security systems to safeguard the lives and property of citizens and maintain social stability. Person re-identification (ReID) is an essential technology for building smart cities, with significant implications for security monitoring and criminal investigation applications. The goal of person re-identification is to accurately identify specific individuals captured under different cameras. However, due to intra-class differences resulting from various factors such as illumination, viewpoint, occlusion, and pose, person re-identification remains a challenging task in the field of computer vision. Although existing fully supervised person re-identification methods have made significant progress, the scarcity of data and labels poses a bottleneck for further improving model performance. To address this challenge, we introduce a more complex and diverse synthetic dataset with easy-to-obtain labels for auxiliary training, and propose a novel camera-aware asymmetric adversarial learning (CAAL) method that overcomes intra-class variation among multiple cameras and the domain-shift between real data and synthetic data, enabling the learning of camera-invariant feature representations from diverse data sources. Furthermore, to mitigate the impact of misleading information carried by synthetic datasets and prevent the model from overfitting to synthetic data during adversarial training, we propose using an auxiliary network trained on real-world data to constrain the training of the backbone network. Finally, we conduct extensive experiments on two public datasets to demonstrate the effectiveness of the proposed method.
- person re-identification,
- adversarial learning,
- knowledge distillation,
- image retrieval,
- computer vision

FullText(HTML)

References (52)

References

[1]	Zheng Liang, Shen Liyue, Tian Lu, et al. Scalable person re-identification: A benchmark[C]//Proc of the 15th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2015: 1116−1124
[2]	Ristani E, Solera F, Zou R, et al. Performance measures and a data set for multi-target, multi-camera tracking[C]//Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 17−35
[3]	Zhang Xuan, Luo Hao, Fan Xing, et al. Alignedreid: Surpassing human-level performance in person re-identification[J]. arXiv preprint, arXiv: 1711.08184, 2017
[4]	Sun Yifan, Zheng Liang, Yang Yi, et al. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline)[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 480−496
[5]	Luo Hao, Jiang Wei, Gu Youzhi, et al. A strong baseline and batch normalization neck for deep person re-identification[J]. IEEE Transactions on Multimedia, 2019, 22(10): 2597−2609
[6]	Wang Guanshuo, Yuan Yufeng, Chen Xiong, et al. Learning discriminative features with multiple granularities for person re-identification[C]//Proc of the 26th ACM Int Conf on Multimedia. New York: ACM, 2018: 274−282
[7]	Li Hanjun, Wu Gaojie, Zheng Weishi. Combined depth space based architecture search for person re-identification[C]//Proc of the 34th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 6729−6738
[8]	Ganin Y, Ustinova E, Ajakan H, et al. Domain-adversarial training of neural networks[J]. The Journal of Machine Learning Research, 2016, 17(1): 2096−2030
[9]	Das A, Chakraborty A, Roy-Chowdhury A K. Consistent re-identification in a camera network[C]//Proc of the 13th European Conf on Computer Vision. Berlin: Springer, 2014: 330−345
[10]	Liao Shengcai, Hu Yang, Zhu Xiangyu, et al. Person re-identification by local maximal occurrence representation and metric learning[C]//Proc of the 28th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2015: 2197−2206
[11]	Li Zhen, Chang Shiyu, Liang Feng, et al. Learning locally-adaptive decision functions for person verification[C]//Procs of the 26th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2013: 3610−3617
[12]	Yang Yang, Yang Jimei, Yan Junjie, et al. Salient color names for person re-identification[C]//Proc of the 13th European Conf on Computer Vision. Berlin: Springer, 2014: 536−551
[13]	陈利文,叶锋,黄添强,等. 基于摄像头域内域间合并的无监督行人重识别方法[J]. 计算机研究与发展,2023,60(2):415−425 Chen Liwen, Ye Feng, Huang Tianqiang, et al. An unsupervised person re-identification method based on intra-/inter-camera merger[J]. Journal of Computer Research and Development. 2023, 60(2): 415−425 (in Chinese)
[14]	Varior R R, Shuai Bing, Lu Jiwen, et al. A siamese long short-term memory architecture for human re-identification[C]//Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 135−153
[15]	Wei Longhui, Zhang Shiliang, Yao Hantao, et al. Glad: Global-local-alignment descriptor for pedestrian retrieval[C]//Proc of the 25th ACM Int Conf on Multimedia. New York: ACM, 2017: 420−428
[16]	Zheng Feng, Deng Cheng, Sun Xing, et al. Pyramidal person re-identification via multi-loss dynamic training[C]//Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 8514−8522
[17]	Fang Pengfei, Zhou Jieming, Roy S K, et al. Bilinear attention networks for person retrieval[C]//Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 8030−8039
[18]	石跃祥,周玥. 基于阶梯型特征空间分割与局部注意力机制的行人重识别[J]. 电子与信息学报,2022,44(1):195−202 doi: 10.11999/JEIT201006 Shi Yuexiang, Zhou Yue. Person re-identification based on stepped feature space segmentation and local attention mechanism[J]. Journal of Electronics & Information Technology, 2022, 44(1): 195−202 (in Chinese) doi: 10.11999/JEIT201006
[19]	Li Wei, Zhu Xiatian, Gong Shaogang. Harmonious attention network for person re-identification[C]//Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 2285−2294
[20]	Zhao Liming, Li Xi, Zhuang Yueting, et al. Deeply-learned part-aligned representations for person re-identification[C]//Proc of the 16th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 3219-3228
[21]	Kim W, Goyal B, Chawla K, et al. Attention-based ensemble for deep metric learning[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 736−751
[22]	Li Dangwei, Chen Xiaotang, Zhang Zhang, et al. Learning deep context-aware features over body and latent parts for person re-identification[C]//Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 384−393
[23]	Kumar V, Namboodiri A, Paluri M, et al. Pose-aware person recognition[C]//Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 6223-6232
[24]	Su Chi, Li Jianning, Zhang Shiliang, et al. Pose-driven deep convolutional model for person re-identification[C]//Proc of the 16th IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 3960−3969
[25]	Zhong Zhun, Zheng Liang, Zheng Zhedong, et al. Camera style adaptation for person re-identification[C]//Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 5157−5166
[26]	Zhuang Zijie, Wei Longhui, Xie Lingxi, et al. Rethinking the distribution gap of person re-identification with camera-based batch normalization[C]//Proc of the 16th European Conf on Computer Vision. Berlin: Springer, 2020: 140−157
[27]	Zhong Zhun, Zheng Liang, Cao Donglin, et al. Re-ranking person re-identification with k-reciprocal encoding[C]//Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 1318−1327
[28]	Bai Song, Bai Xiang, Tian Qi. Scalable person re-identification on supervised smoothed manifold[C]//Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 2530−2539
[29]	Schumann A, Stiefelhagen R. Person re-identification by deep learning attribute-complementary information[C]//Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition Workshops. Piscataway, NJ: IEEE, 2017: 20−28
[30]	Zhong Zhun, Zheng Liang, Kang Guoliang, et al. Random erasing data augmentation[C]//Proc of the 34th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2020, 34(7): 13001−13008
[31]	DeVries T, Taylor G W. Improved regularization of convolutional neural networks with cutout[J]. arXiv preprint, arXiv: 1708.04552, 2017
[32]	Liu Jinxian, Ni Bingbing, Yan Yichao, et al. Pose transferrable person re-identification[C]//Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 4099−4108
[33]	Qian Xuelin, Fu Yanwei, Xiang Tao, et al. Pose-normalized image generation for person re-identification[C]//Proc of the 15th European Conf on Computer Vision. Berlin: Springer, 2018: 650−667
[34]	Wei Longhui, Zhang Shiliang, Gao Wen, et al. Person transfer GAN to bridge domain gap for person re-identification[C]//Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 79-88
[35]	Zheng Zhedong, Yang Xiaodong, Yu Zhiding, et al. Joint discriminative and generative learning for person re-identification[C]//Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 2138−2147
[36]	Yu Chaohui, Wang Jindong, Chen Yiqiang, et al. Transfer learning with dynamic adversarial adaptation network[C]//Proc of the 19th IEEE Int Conf on Data Mining. Piscataway, NJ: IEEE, 2019: 778−786
[37]	Qi Lei, Wang Lei, Huo Jing, et al. A novel unsupervised camera-aware domain adaptation framework for person re-identification[C]//Proc of the 32nd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 8080−8089
[38]	戴臣超,王洪元,倪彤光,等. 基于深度卷积生成对抗网络和拓展近邻重排序的行人重识别[J]. 计算机研究与发展,2019,56(8):1632−1641 doi: 10.7544/issn1000-1239.2019.20190195 Dai Chenchao, Wang Hongyuan, Ni Tongguang, et al. Person re-identification based on deep convolutional generative adversarial network and expanded neighbor reranking[J]. Journal of Computer Research and Development, 2019, 56(8): 1632−1641 (in Chinese) doi: 10.7544/issn1000-1239.2019.20190195
[39]	Wang Wenhao, Liao Shengcai, Zhao Fang, et al. Domainmix: Learning generalizable person re-identification without human annotations[J]. arXiv preprint, arXiv: 2011.11953, 2020
[40]	Zhang Ying, Xiang Tao, Hospedales T M, et al. Deep mutual learning[C]//Proc of the 31st IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 4320−4328
[41]	Hermans A, Beyer L, Leibe B. In defense of the triplet loss for person re-identification[J]. arXiv preprint, arXiv: 1703.07737, 2017
[42]	Müller R, Kornblith S, Hinton G E. When does label smoothing help[J]. Advances in Neural Information Processing Systems, 2019, 32: 4694−4703
[43]	Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[J]. arXiv preprint, arXiv: 1503.02531, 2015
[44]	Allen-Zhu Z, Li Yuanzhi. Towards understanding ensemble, knowledge distillation and self-distillation in deep learning[J]. arXiv preprint, arXiv: 2012.09816, 2020
[45]	Wang Yanan, Liao Shengcai, Shao Ling. Surpassing real-world source training data: Random 3D characters for generalizable person re-identification[C]//Proc of the 28th ACM Int Conf on Multimedia. New York: ACM, 2020: 3422−3430
[46]	Li Wei, Zhao Rui, Xiao Tong, et al. Deepreid: Deep filter pairing neural network for person re-identification[C]//Proc of the 27th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2014: 152−159
[47]	He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]//Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2016: 770−778
[48]	Deng Jia, Dong Wei, Socher R, et al. ImageNet: A large-scale hierarchical image database[C]//Proc of the 22nd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2009: 248−255
[49]	Ren Pengyuan, Li Jianmin. Factorized distillation: Training holistic person re-identification model by distilling an ensemble of partial ReID models[J]. arXiv preprint, arXiv: 1811.08073, 2018
[50]	Gu Hongyang, Li Jianmin, Fu Guangyuan, et al. Autoloss-GMS: Searching generalized margin-based softmax loss function for person re-identification[C]//Proc of the 35th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 4744−4753
[51]	Yuan Ye, Chen Wuyang, Yang Yang, et al. In defense of the triplet loss again: Learning robust person re-identification with fast approximated triplet loss and label distillation[C]//Proc of the 33rd IEEE Conf on Computer Vision and Pattern Recognition Workshops. Piscataway, NJ: IEEE, 2020: 354−355
[52]	Van der Maaten L, Hinton G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(11): 2579−2605

[1]	Zhang Hao, Wu Jianxin. A Survey on Unsupervised Image Retrieval Using Deep Features[J]. Journal of Computer Research and Development, 2018, 55(9): 1829-1842. DOI: 10.7544/issn1000-1239.2018.20180058
[2]	Shan Yanhu, Zhang Zhang, Huang Kaiqi. Visual Human Action Recognition: History, Status and Prospects[J]. Journal of Computer Research and Development, 2016, 53(1): 93-112. DOI: 10.7544/issn1000-1239.2016.20150403
[3]	Li Kenli, Guo Li, Tang Zhuo, Jiang Yong, and Li Renfa. A Molecular Solution for the Ramsey Number on DNA-Based Supercomputing[J]. Journal of Computer Research and Development, 2011, 48(3): 447-454.
[4]	Zhai Weiming, Sheng Lin, Song Yixu, Zhao Yangnan, Wang Hong, Jia Peifa. Image Guided Computer Assisted Microwave Ablation for Liver Cancer[J]. Journal of Computer Research and Development, 2011, 48(2): 281-288.
[5]	Guo Kangde, Zhang Mingmin, Sun Chao, Li Yang, Tang Xing. 3D Fingertip Tracking Algorithm Based on Computer Vision[J]. Journal of Computer Research and Development, 2010, 47(6): 1013-1019.
[6]	Shu Bo, Qiu Xianjie, Wang Zhaoqi. Survey of Shape from Image[J]. Journal of Computer Research and Development, 2010, 47(3): 549-560.
[7]	Zhao Hongwei, Wang Hui, Liu Pingping, and Dai Jinbo. A Computer Model of Directional Visual Attention[J]. Journal of Computer Research and Development, 2009, 46(7): 1192-1197.
[8]	Li Kenli, Liu Jie, Yang Lei, Liu Wenbin. An O(1.414\+n) Volume Molecular Solutions for the Exact Cover Problem on DNA-Based Supercomputing[J]. Journal of Computer Research and Development, 2008, 45(10): 1782-1788.
[9]	Xiong Tinggang, Ma Zhong, Yuan Youguang. Research on Synchronization Technology of Fault-Tolerant Computer System Based on Operating System Calls[J]. Journal of Computer Research and Development, 2006, 43(11): 1985-1992.
[10]	Zhang Liangguo, Gao Wen, Chen Xilin, Chen Yiqiang, Wang Chunli. A Medium Vocabulary Visual Recognition System for Chinese Sign Language[J]. Journal of Computer Research and Development, 2006, 43(3): 476-482.

Cited By

Cited by

Periodical cited type(2)

1.	马乾骏，郭虎升，王文剑. 在线深度神经网络的弱监督概念漂移检测方法. 小型微型计算机系统. 2024(09): 2094-2101 .
2.	韩光洁，赵腾飞，刘立，张帆，徐政伟. 基于多元区域集划分的工业数据流概念漂移检测. 电子学报. 2023(07): 1906-1916 .