计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (1): 72-83.doi: 10.11896/jsjkx.230700101

• 创刊五十周年特别专题 • 上一篇    下一篇

基于伪标签的无监督领域自适应行人重识别研究综述

景叶怡然1, 余增1,2, 时云潇1, 李天瑞1,2   

  1. 1 西南交通大学计算机与人工智能学院 成都611756
    2 综合交通大数据应用技术国家工程实验室 成都611756
  • 收稿日期:2023-07-14 修回日期:2023-09-20 出版日期:2024-01-15 发布日期:2024-01-12
  • 通讯作者: 余增(zyu@swjtu.edu.cn)
  • 作者简介:(jyyr@my.swjtu.edu.cn)
  • 基金资助:
    国家自然科学基金(62176221)

Review of Unsupervised Domain Adaptive Person Re-identification Based on Pseudo-labels

JING Yeyiran1, YU Zeng1,2, SHI Yunxiao1, LI Tianrui1,2   

  1. 1 Institute of Computer and Artficial Intelligence,Southwest Jiaotong University,Chengdu 611756,China
    2 National Engineering Laboratory of Integrated Transportation Big Data Application Technology,Chengdu 611756,China
  • Received:2023-07-14 Revised:2023-09-20 Online:2024-01-15 Published:2024-01-12
  • About author:JING Yeyiran,born in 1999,postgra-duate,is a member of CCF(No.D5389G).Her main research intertests include big data and cloud computing.
    YU Zeng,born in 1983,Ph.D,assistant researcher,is a member of CCF(No.C3378M).His main research interests include data mining,deep lear-ning and computer vision.
  • Supported by:
    National Natural Science Foundation of China(62176221).

PDF (PC)

1549

摘要： 行人重识别是计算机视觉领域的热点研究课题之一。近年来,为了解决行人重识别实际应用中标签数据稀缺的问题,同时也为了有效地利用现有的标签数据,研究者们提出了基于生成对抗网络以及基于伪标签的领域自适应方法,用于进行跨领域的行人重识别研究。基于伪标签的无监督领域自适应行人重识别方法由于效果显著而备受研究者的青睐。文中梳理了近7年来基于伪标签的无监督领域自适应行人重识别的研究成果,将基于伪标签的方法从模型训练角度划分为两个阶段。1)伪标签生成阶段。现有工作的伪标签生成方法大多使用聚类方法,部分工作采用基于图结构学习的图匹配、图卷积网络方法来生成目标域的伪标签。2)伪标签精炼阶段。文中将现有的伪标签精炼方法归纳为基于表征学习的精炼方法以及基于相似度学习的精炼方法,并分别进行模型方法的总结与整理。最后,讨论现阶段基于伪标签的无监督领域自适应行人重识别面临的挑战并对未来可能的发展方向进行展望。

关键词: 行人重识别, 深度学习, 伪标签, 无监督, 领域自适应

Abstract: Person re-identification is one of the hot research topics in the field of computer vision.In recent years,in order to solve the problem of scarcity of label data in the practical application of person re-identification,and to effectively use the existing label data,researchers have proposed domain adaptive methods based on generative adversarial networks and pseudo-labels to carry out cross-domain person re-identification research.The unsupervised domain adaptive person re-identification method based on pseudo-labels is favored by researchers due to its remarkable effect.This paper sorts out the work of pseudo-label-based adaptive person re-identification in the unsupervised field in the past 7 years,and divides the pseudo-label-based method into two stages from the perspective of model training:1)Pseudo-label generation stage.Most of the pseudo-label generation methods in existing works use clustering methods,and some works use graph matching based on graph structure learning and graph neural network methods to generate pseudo-labels in the target domain.2)Pseudo-label refining stage.In this paper,the existing pseudo-label refinement methods are summarized into the refinement method based on representation learning and the refinement method based on similarity learning,and the model methods are summarized and organized respectively.Finally,the current challenges of pseudo-label-based adaptive person re-identification in the unsupervised domain are discussed and the possible future development directions are prospected.

Key words: Person re-edentification, Deep learning, Pseudo-label, Unsupervised learning, Domain adaptation

中图分类号: 

  • TP391.41
[1]ZHENG L,YANG Y,HAUPTMANN A G.Person Re-Identification:Past,Present and Future[J].arXiv:1610.02984,2016.
[2]LIN Y,ZHENG L,ZHENG Z,et al.Improving Person Re-Identification by Attribute and Identity Learning[J].Pattern Recognition,2019,95:151-161.
[3]LI W,ZHU X,GONG S.Harmonious Attention Network forPerson Re-Identification[C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2018:2285-2294.
[4]YE M,SHEN J,LIN G,et al.Deep Learning for Person Re-Iden-tification:A Survey and Outlook[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(6):2872-2893.
[5]ZHENG Z,ZHENG L,YANG Y.Unlabeled Samples Generated by Gan Improve the Person Re-Identification Baseline in Vitro[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:3754-3762.
[6]XIAO W.Research on domain adaptive pedestrian re-identification based on deep learning [D].Wuhan:Huazhong University of Science and Technology,2021.
[7]WANG M,DENG W.Deep Visual Domain Adaptation:A Survey[J].Neurocomputing,2018,312:135-153.
[8]LONG M,ZHU H,WANG J,et al.Unsupervised Domain Adaptation with Residual Transfer Networks[J].Advances in Neural Information Processing Systems,2016,31:3073-3086.
[9]GANIN Y,LEMPITSKY V.Unsupervised Domain Adaptationby Backpropagation[C]//International Conference on Machine Learning.2015:1180-1189.
[10]SAITO K,WATANABE K,USHIKU Y,et al.Maximum Clas-sifier Discrepancy for Unsupervised Domain Adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018:3723-3732.
[11]ZHAN F,ZHANG C.Spatial-Aware Gan for Unsupervised Person Re-Identification[C]//2020 25th International Conference on Pattern Recognition(ICPR),2021:6889-6896.
[12]TANG H,ZHAO Y,LU H.Unsupervised Person Re-Identificationwith Iterative Self-Supervised Domain Adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.2019:1536-1543.
[13]ZHOU S,KE M,LUO P.Multi-Camera Transfer Gan for Person Re-Identification[J].Journal of Visual Communication and Image Representation,2019,59:393-400.
[14]DENG W,ZHENG L,YE Q,et al.Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:994-1003.
[15]JIANG Y,CHEN W,SUN X,et al.Exploring the Quality of Gan Generated Images for Person Re-Identification[C]//Proceedings of the 29th ACM International Conference on Multimedia.2021:4146-4155.
[16]VERMA A,SUBRAMANYAM A,WANG Z,et al.Unsuper-vised Domain Adaptation for Person Re-Identification Via Individual-Preserving and Environmental-Switching Cyclic Generation[J].IEEE Transactions on Multimedia,2021:364-377.
[17]HOFFMAN J,TZENG E,PARK T,et al.Cycada:Cycle-Cons-istent Adversarial Domain Adaptation[C]//International Conference on Machine Learning.2018:1989-1998.
[18]BOUSMALIS K,SILBERMAN N,DOHAN D,et al.Unsupervised Pixel-Level Domain Adaptation with Generative Adversa-rial Networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:3722-3731.
[19]WEI L,ZHANG S,GAO W,et al.Person Transfer Gan toBridge Domain Gap for Person Re-Identification[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:79-88.
[20]ZHONG Z,ZHENG L,LI S,et al.Generalizing a Person Retrieval Model Hetero-and Homogeneously[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:172-188.
[21]ZHU M,MING Z Q,YAN J R,et al.A Review of Research on Person Re-Identification Methods Based on Generative Adversarial Networks [J].Journal of Computer-Aided Design & Computer Graphics/Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao,2022,34(2):163-179.
[22]LUO C,SONG C,ZHANG Z.Generalizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain Mixup[C]//Computer Vision-ECCV 2020:16th European Conference,Glasgow,UK,Part XV 16.2020:224-241.
[23]ZHONG Z,ZHENG L,LUO Z,et al.Invariance Matters:Exemplar Memory for Domain Adaptive Person Re-Identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:598-607.
[24]LEE D H.Pseudo-Label:The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks[C]//Workshop on Challenges in Representation Learning,ICML.2013:896.
[25]HE K,ZHANG X,REN S,et al.Deep Residual Learning forImage Recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[26]LIN X,REN P,YEH C H,et al.Unsupervised Person Re-Identification:A Systematic Survey of Challenges and Solutions[J].arxiv:2109.06057,2021.
[27]ZOU G F,FU J X,GAO M L,et al.Research Progress on Me-tric Learning Methods in Person Re-Identification [J].Control and Decision,2021,36(7):1547-1557.
[28]GROSSMANN V,SCHMARJE L,KOCH R.Beyond Hard Labels:Investigating Data Label Distributions[J].arXiv:2207.06224,2022.
[29]XIE Q,LUONG M T,HOVY E,et al.Self-Training with Noisy Student Improves Imagenet Classification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:10687-10698.
[30]ZOU Y,YU Z,LIU X,et al.Confidence Regularized Self-Trai-ning[C]//Proceedings ofthe IEEE/CVF International Conference on Computer Vision.2019:5982-5991.
[31]SOHN K,BERTHELOT D,CARLINI N,et al.Fixmatch:Simplifying Semi-Supervised Learning with Consistency and Confidence[J].Advances in Neural Information Processing Systems,2020,33:596-608.
[32]WENG W,WEI B,KE W,et al.Learning Label-Specific Features with Global and Local Label Correlation for Multi-Label Classification[J].Applied Intelligence,2023,53(3):3017-3033.
[33]ZHAO T,ZHANG Y,PEDRYCZ W.Robust Multi-Label Classification with Enhanced Global and Local Label Correlation[J].Mathematics,2022,10(11):1871.
[34]ZHU Y,KWOK J T,ZHOU Z H.Multi-Label Learning withGlobal and Local Label Correlation[J].IEEE Transactions on Knowledge and Data Engineering,2017,30(6):1081-1094.
[35]SUN W,SONG Y,CHEN C,et al.Face Spoofing DetectionBased on Local Ternary Label Supervision in Fully Convolu-tional Networks[J].IEEE Transactions on Information Forensics and Security,2020,15:3181-3196.
[36]SUN G J,LIU J,LIU L Y.Research on Clustering Algorithms[J].Journal of Software,2008,19(1):48-61.
[37]MADHULATHA T S.An Overview on Clustering Methods[J].arXiv:1205.1117,2012.
[38]OMRAN M G,ENGELBRECHT A P,SALMAN A.An Overview of Clustering Methods[J].Intelligent Data Analysis,2007,11(6):583-605.
[39]ESTER M,KRIEGEL H P,SANDER J,et al.A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise[C]//KDD.1996:226-231.
[40]LIN Y,DONG X,ZHENG L,et al.A Bottom-up Clustering Approach to Unsupervised Person Re-Identification[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.2019:8738-8745.
[41]MOHANTY A,BANERJEE B,VELMURUGAN R.Ssmtreid-Net:Multi-Target Unsupervised Domain Adaptation for Person Re-Identification[J].Pattern Recognition Letters,2022,163:40-46.
[42]REMIGEREAU F,MEKHAZNI D,ABDOLI S,et al.Know-ledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-Identification[C]//2022 IEEE International Conference on Image Processing(ICIP).2022:3853-3557.
[43]SONG L,WANG C,ZHANG L,et al.Unsupervised DomainAdaptive Re-Identification:Theory and Practice[J].Pattern Recognition,2020,102:107173.
[44]TANG C,XUE D,CHEN D.Multi-Level Mutual Supervisionfor Cross-Domain Person Re-Identification[J].Journal of Visual Communication and Image Representation,2022,89:103674.
[45]ZHANG X,CAO J,SHEN C,et al.Self-Training with Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:8222-8231.
[46]MACQUEEN J.Some Methods for Classification and Analysis of Multivariate Observations[C]//Proceedings of the fifth Berkeley Symposium on Mathematical Statistics and Probabi-lity.1967:281-297.
[47]FAN H,ZHENG L,YAN C,et al.Unsupervised Person Re-Identification:Clustering and Fine-Tuning[J].ACM Transactions on Multimedia Computing,Communications,and Applications(TOMM),2018,14(4):1-18.
[48]WU J,LIAO S,WANG X,et al.Clustering and Dynamic Sampling Based Unsupervised Domain Adaptation for Person Re-Identification[C]//2019 IEEE International Conference on Multimedia and Expo(ICME).2019:886-891.
[49]WANG R,YAN J,YANG X.Graduated Assignment for JointMulti-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning[J].Advances in Neural Information Processing Systems,2020,33:19908-19919.
[50]GAO S,WANG J,LU H,et al.Pose-Guided Visible Part Ma-tching for Occluded Person Reid[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:11744-11752.
[51]GUO W,ZHANG L,TU S,et al.Self-Supervised Bidirectional Learning for Graph Matching[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2023:7784-7792.
[52]YE M,MA A J,ZHENG L,et al.Dynamic Label Graph Ma-tching for Unsupervised Video Re-Identification[C]//Procee-dings of the IEEE International Conference on Computer Vision.2017:5142-5150.
[53]CAETANO T S,MCAULEY J J,CHENG L,et al.Learning Graph Matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(6):1048-1058.
[54]LIVI L,RIZZI A.The Graph Matching Problem[J].PatternAnalysis and Applications,2013,16:253-283.
[55]XU K,HUW,LESKOVEC J,et al.How Powerful Are Graph Neural Networks?[J].arXiv:1810.00826,2018.
[56]ZHOU J,CUI G,HU S,et al.Graph Neural Networks:A Review of Methods and Applications[J].AI Open,2020,1:57-81.
[57]SCARSELLI F,GORI M,TSOI A C,et al.The Graph Neural Network Model[J].IEEE Transactions on Neural Networks,2008,20(1):61-80.
[58]FENG H,CHEN M,HU J,et al.Complementary Pseudo Labels for Unsupervised Domain Adaptation on Person Re-Identification[J].IEEE Transactions on Image Processing,2021,30:2898-2907.
[59]ZHONG Z,ZHENG L,LUO Z,et al.Learning to Adapt Inva-riance in Memory for Person Re-Identification[J].IEEETran-sactions on Pattern Analysis and Machine Intelligence,2020,43(8):2723-2738.
[60]FU Y,WEI Y,WANG G,et al.Self-Similarity Grouping:A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification[C]//proceedings of the IEEE/CVF International Conference on Computer Vision.2019:6112-6121.
[61]YANG F,LI K,ZHONG Z,et al.Asymmetric Co-Teachingfor Unsupervised Cross-Domain Person Re-Identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:12597-12604.
[62]ZHAI Y,LU S,YE Q,et al.Ad-Cluster:Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:9021-9030.
[63]HUANG Y,PENG P,JIN Y,et al.Domain Adaptive Attention Model for Unsupervised Cross-Domain Person Re-Identification[J].arXiv:1905.10529,2019.
[64]ZHAO F,LIAO S,XIE G S,et al.Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-Identification[C]//Computer Vision－ECCV 2020:16th European Conference.Glasgow,UK,2020:526-544.
[65]GE Y,CHEN D,LI H.Mutual Mean-Teaching:Pseudo LabelRefinery for Unsupervised Domain Adaptation on Person Re-Identification[J].arXiv:2001.01526,2020.
[66]CHEN S,FAN Z,YIN J.Pseudo Label Based on Multiple Clustering for Unsupervised Cross-Domain Person Re-Identification[J].IEEE Signal Processing Letters,2020,27:1460-1464.
[67]LI J,ZHANG S.Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification[C]//Computer Vision-ECCV 2020:16th European Conference.Glasgow,UK,2020:483-499.
[68]ZHENG K,LIU W,HE L,et al.Group-Aware Label Transfer for Domain Adaptive Person Re-Identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:5310-5319.
[69]LIU X,ZHANG S.Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification[J].arXiv:2105.04776,2021.
[70]LI Y,YAO H,XU C.Test:Triplet Ensemble Student-Teacher Model for Unsupervised Person Re-Identification[J].IEEE Transactionson Image Processing,2021,30:7952-7963.
[71]HUANG D,ZHANG L,DIAO Q,et al.Asymmetric MutualLearning for Unsupervised Cross-Domain Person Re-Identification[C]//Trends in Artificial Intelligence:18th Pacific Rim International Conference on Artificial Intelligence(PRICAI 2021).Hanoi,Vietnam,2021:124-137.
[72]ZHENG K,LAN C,ZENG W,et al.Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:3538-3546.
[73]HOU H,ZHOU Y,ZHAO J,et al.Unsupervised Cross-Domain Person Re-Identification with Self-Attention and Joint-Flexible Optimization[J].Image and Vision Computing,2021,111:104191.
[74]YU S,WANG S.Consistency Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification[C]//2022 the 5th International Conference on Image and Graphics Processing(ICIGP).2022:159-166.
[75]WANG W,ZHAO F,LIAO S,et al.Attentive Waveblock:Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and Beyond[J].IEEE Transactions on Image Processing,2022,31:1532-1544.
[76]TAO Y,ZHANG J,HONG J,et al.Dreamt:Diversity Enlarged Mutual Teaching for Unsupervised Domain Adaptive Person Re-Identifcation[J].IEEE Transactions on Multimedia,2022,25:4586-4597.
[77]HE T,SHEN L,GUO Y,et al.Secret:Self-Consistent Pseudo Label Refinement for Unsupervised Domain Adaptive Person Re-Identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022:879-887.
[78]CHEN Z,CUI Z,ZHANG C,et al.Dual Clustering Co-Teaching with Consistent Sample Mining for Unsupervised Person Re-Identification[J].IEEE Transactions on Circuits and Systems for Video Technology,2023,33:5908-5920.
[79]WANG H,YANG M,LIU J,et al.Pseudo-Label Noise Prevention,Suppression and Softening for Unsupervised Person Re-Identification[J].IEEE Transactions on Information Forensics and Security,2023,18:3222-3237.
[80]WANG X L.A Review of Label Noise Learning Algorithms[J].Computer System Applications,2021,30(1):10-18.
[81]HINTON G,VINYALS O,DEAN J.Distilling the Knowledgein a Neural Network[J].arXiv:1503.02531,2015.
[82]CHEN P,LIU S,ZHAO H,et al.Distilling Knowledge ViaKnowledge Review[C]//Proceedings of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.2021:5008-5017.
[83]KUMAR M,PACKER B,KOLLER D.Self-Paced Learning for Latent Variable Models[J].Advances in Neural Information Processing Systems,2010,23:1-9.
[84]WANG G,YUAN Y,CHEN X,et al.Learning Discriminative Features with Multiple Granularities for Person Re-Identification[C]//Proceedings of the 26th ACM InternationalConfe-rence on Multimedia.2018:274-282.
[85]YANG W,ZHANG D.Unsupervised Person Re-Identification by Part-Compensated Soft Multi-Label Learning[J].IET Image Processing,2022,16(7):2012-2024.
[86]TAY C P,YAP K H.Collaborative Learning Mutual Network for Domain Adaptation in Person Re-Identification[J].Neural Computing and Applications,2022,34(14):12211-12222.
[87]TU Y.Domain Camera Adaptation and Collaborative MultipleFeature Clustering for Unsupervised Person Re-Id[C]//Proceedings of the 3rd International Workshop on Human-Centric Multimedia Analysis.2022:51-59.
[88]ZHENG L,SHEN L,TIAN L,et al.Scalable Person Re-Identification:A Benchmark[C]//Proceedings of the IEEE International Conference on Computer Vision,2015:1116-1124.
[89]SANTINI S,JAIN R.Similarity Measures[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(9):871-883.
[90]CHENG D,LI J,KOU Q,et al.H-Net:Unsupervised Domain Adaptation Person Re-Identification Network Based on Hierarchy[J].Image and Vision Computing,2022,124:104493.
[91]CHEN G,LU Y,LU J,et al.Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-Identification[C]//Computer Vision－ECCV 2020:16th European Confe-rence.Glasgow,UK,2020:643-659.
[92]WANG D,ZHANG S.Unsupervised Person Re-IdentificationVia Multi-Label Classification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:10981-10990.
[93]FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object Detection with Discriminatively Trained Part-Based Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,32(9):1627-1645.
[94]ZHONG Z,ZHENG L,CAO D,et al.Re-Ranking Person Re-Identification with K-Reciprocal Encoding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1318-1327.
[95]REN S,HE K,GIRSHICK R,et al.Faster R-Cnn:TowardsReal-Time Object Detection with Region Proposal Networks[J].Advances in Neural Information Processing Systems,2015,28(39):1137-1149.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发