一种域增强和域自适应的换衣行人重识别范式

doi:10.19665/j.issn1001-2400.20221106

Abstract

Abstract:

In order to solve the influence of the clothing change on the model’s recognition accuracy of the personal identity,a clothes-changing person re-identification paradigm based on domain augmentation and adaptation is proposed,which enables the model to learn general robust identity representation features in different domains.First,a clothing semantic-aware domain data enhancement method is designed based on the semantic information of the human body,which changes the color of sample clothes without changing the identity of the target person to fill the lack of domain diversity in the data; second,a multi-positive class domain adaptive loss function is designed,which assigns differential weights to the multi-positive class data losses according to the different contributions made by different domain data in the model training,forcing the model to focus on the learning of generic identity features of the samples.Experiments demonstrate that the method achieves 59.5%,60.0%,and 88.0%,84.5% of Rank-1 and mAP on two clothing change datasets,PRCC and CCVID,without affecting the accuracy of non-clothing person re-identification.Compared with other methods,this method has a higher accuracy and stronger robustness and significantly improves the model’s ability to recognize persons.

Key words: artificial intelligence, computer vision, person re-identification, domain adaptation, data augmentation

CLC Number:

TP391.4

ZHANG Peixu,HU Guanyu,YANG Xinyu. Cloth-changing person re-identification paradigm based on domain augmentation and adaptation[J].Journal of Xidian University, 2023, 50(5): 87-94.

Figures/Tables 6

References 20

[1]	YE M, SHEN J, LIN G, et al. Deep Learning for Person Re-Identification:A Survey and Outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(6):2872-2893. doi: 10.1109/TPAMI.2021.3054775
[2]	GU X Q, CHANG H, MA B P, et al. Clothes-Changing Person Re-Identification with RGB Modality Only[C]//Proceedings of the IEEE/CVF 2022 Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2022:1060-1069.
[3]	TERRANCE D, GRAHAM W T. Improved Regularization of Convolutional Neural Networks with Cutout (2017)[J/OL].[2017-08-15]. https://arxiv.org/abs/1708.04552.
[4]	ZHONG Z, ZHENG L, KANG G, et al. Random Erasing Data Augmentation[C]//Proceedings of the AAAI 2020 Conference on Artificial Intelligence. Palo Alto: AAAI, 2020:13001-13008.
[5]	ZHANG H, MOUSTAPHA C, YANN N D, et al. Mixup :Beyond Empirical Risk Minimization[C]//Proceedings of the International Conference on Learning Representations(2018).Piscataway:IEEE, 2018:1-13.
[6]	YUN S, HAN D, CHUN S, et al. CutMix:Regularization Strategy to Train Strong Classifiers with Localizable Features[C]//2019 IEEE/CVF International Conference on Computer Vision.Piscataway:IEEE, 2019:6022-6031.
[7]	WANG J, LAN C, LIU C, et al. Generalizing to Unseen Domains:A Survey on Domain Generalization (2022)[J/OL].[2022-04-24]. https://arxiv.org/abs/2103.03097.
[8]	LI P, XU Y, WEI Y, et al. Self-Correction for Human Parsing[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(7):3260-3271. doi: 10.1109/TPAMI.2020.3048039
[9]	YU S, LI S, CHEN D, et al. COCAS:A Large-Scale Clothes Changing Person Dataset for Re-Identification[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2020:3397-3406.
[10]	ZHENG Z, YANG X, YU Z, et al. Joint Discriminative and Generative Learning for Person Re-Identification[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2019:2133-2142.
[11]	TANG C, GUO J. Clothes-Changing Image Generation Based on Attention for Person Re-Identification[C]//2020 5th International Conference on Mechanical,Control and Computer Engineering.Piscataway:IEEE, 2020:2009-2013.
[12]	GONG K, LIANG X, ZHANG D, et al. Look into Person:Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2017:6757-6765.
[13]	YANG Q, WU A, ZHENG W S. Person Re-Identification by Contour Sketch Under Moderate Clothing Change[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(6):2029-2046. doi: 10.1109/TPAMI.2019.2960509
[14]	HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2016:770-778.
[15]	DIEDERIK P K, JIMMY B. Adam:A Method for Stochastic Optimization (2015)[C/OL],[2015-07-23]. https://arxiv.org/abs/1412.6980.
[16]	SUN Y, ZHENG L, YANG Y, et al. Beyond Part Models:Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)[C]//Proceedings of the European Conference on Computer Vision. Piscataway:IEEE, 2018:480-496.
[17]	HOU R B, MA B P, CHANG H, et al. Interaction-and-Aggregation Network for Person Re-Identifification[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2019:9309-9318.
[18]	HUANG Y, WU Q, XU J S, et al. Clothing Status Awareness for Long-Term Person Re-Identifification[C]//2021 IEEE/CVF International Conference on Computer Vision.Piscataway:IEEE, 2021:11875-11884.
[19]	HONG P, WU T, WU A, et al. Fine-Grained Shape-Appearance Mutual Learning for Cloth-Changing Person Re-Identification[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2021:10508-10517.
[20]	LIU Z, LIN Y, CAO Y, et al. Swin Transformer:Hierarchical Vision Transformer Using Shifted Windows[C]//2021 IEEE/CVF International Conference on Computer Vision. Piscataway:IEEE, 2021:9992-10002.

方法	换衣数据		非换衣数据
方法	Rank-1	mAP	Rank-1	mAP
PCB^[16]	41.8	38.7	99.8	97.0
IANet^[17]	46.3	45.9	99.4	98.3
文中方法	59.5	60.0	99.9	99.8

方法	换衣数据		非换衣数据
方法	Rank-1	mAP	Rank-1	mAP
CAL^[2]	81.7	79.6	82.6	81.3
文中方法	88.0	84.5	89.2	86.2

Cloth-changing person re-identification paradigm based on domain augmentation and adaptation

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 20

Related Articles 10

Metrics

Comments

Recommended 10

[1]	LENG Changfa,YANG Chungang,PENG Yao. Intent-driven autonomous driving networking technology [J]. Journal of Xidian University, 2022, 49(4): 60-70.
[2]	TAO Yang,YANG Na,GUO Tan. Discrimination and structure preserved cross-domain subspace learning for unsupervised domain adaption [J]. Journal of Xidian University, 2022, 49(4): 90-99.
[3]	QIAN Zhihua,GAO Chenqiang,YE Sheng. Method for detection of a student’s pose in a multi-scene classroom based on meta-learning [J]. Journal of Xidian University, 2021, 48(5): 58-67.
[4]	YANG Jingbo,ZHAO Qijun,LYU Zejun. Synthesis of the expression image and its application under the dimentional emotion model [J]. Journal of Xidian University, 2021, 48(5): 30-37.
[5]	SUN Yanjing,WEI Li,ZHANG Nianlong,YUN Xiao,DONG Kaiwen,GE Min,CHENG Xiaozhou,HOU Xiaofeng. Person re-identification method combining the DD-GAN and Global feature in a coal mine [J]. Journal of Xidian University, 2021, 48(5): 201-211.
[6]	CHENG De,HAO Yi,ZHOU Jingyu,WANG Nannan,GAO Xinbo. Cross-modality person re-identification utilizing the hybrid two-stream neural networks [J]. Journal of Xidian University, 2021, 48(5): 190-200.
[7]	XU Qiang;LI Wei;ZHAN Ronghui;ZOU Kun. Improved algorithm for SAR target recognition based on the convolutional neural network [J]. Journal of Xidian University, 2018, 45(5): 177-183.
[8]	SHAN Rui;LI Tao;JIANG Lin;DENG Junyong;YANG Bowen;SHEN Xubang. Design of the transcendental function computing unit of the computer vision array processor [J]. Journal of Xidian University, 2018, 45(4): 166-173.
[9]	LI Jianbing;XIAO Xiao;LI Xiaoping;HOU Xiaoli. Local coordinate gradient descriptor based on cyclic division [J]. Journal of Xidian University, 2016, 43(2): 64-69.
[10]	LI Qing;DONG Qingkuan;ZHAO Lei. Modified forward cloud generator in the cloud model [J]. J4, 2013, 40(5): 169-174+180.