Unsupervised Person Re-Identification with Pseudo Label Regularization Loss

JIA Jie-ru; ZHANG Shuo-rui; QIAN Yu-hua; RUAN Qiu-qi

doi:10.12263/DZXB.20230828

您当前的位置：

首页 >

文章列表页 >

Unsupervised Person Re-Identification with Pseudo Label Regularization Loss

PAPERS | 更新时间：2025-12-11

- Unsupervised Person Re-Identification with Pseudo Label Regularization Loss
- ACTA ELECTRONICA SINICA Vol. 52, Issue 5, Pages: 1743-1758(2024)
- 作者机构：
  
  1.山西大学大数据科学与产业研究院,山西太原 030006
  2.山西大学计算机与信息技术学院,山西太原 030006
  3.山西省机器视觉与数据挖掘工程研究中心,山西太原030006
  4.北京交通大学信息科学研究所,北京 100044
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62106133)
- DOI：10.12263/DZXB.20230828
  CLC： TP391.41;
- Received：01 September 2023，
  
  Revised：2024-01-19，
  
  Published：25 May 2024
- 稿件说明：
移动端阅览
贾洁茹, 张硕蕊, 钱宇华, 等. 基于伪标签正则化损失的无监督行人重识别[J]. 电子学报, 2024, 52(05): 1743-1758.

JIA Jie-ru, ZHANG Shuo-rui, QIAN Yu-hua, et al. Unsupervised Person Re-Identification with Pseudo Label Regularization Loss[J]. Acta Electronica Sinica, 2024, 52(05): 1743-1758.
贾洁茹, 张硕蕊, 钱宇华, 等. 基于伪标签正则化损失的无监督行人重识别[J]. 电子学报, 2024, 52(05): 1743-1758. DOI：10.12263/DZXB.20230828

JIA Jie-ru, ZHANG Shuo-rui, QIAN Yu-hua, et al. Unsupervised Person Re-Identification with Pseudo Label Regularization Loss[J]. Acta Electronica Sinica, 2024, 52(05): 1743-1758. DOI：10.12263/DZXB.20230828

摘要

无监督行人重识别旨在不需要行人身份标签的情况下，将查询的行人图像与候选集中的行人图像相匹配.目前主流的无监督行人重识别方法通常先利用聚类算法生成伪标签，然后利用伪标签训练深度神经网络.然而由于模型初始表征能力不足和聚类算法的局限性等，伪标签中会引入大量噪声，严重误导模型优化过程，导致模型性能退化.为了减轻伪标签噪声的影响，本文提出了一种新的伪标签正则化损失函数，用伪标签的置信度分数和样本相似度对伪标签噪声进行约束.具体来说，本文首先提出了一种聚类引导的注意力机制，根据伪标签与聚类中心的语义相关程度来估计伪标签的置信度，以此来识别噪声标签并给正确标签分配更多的权重，有效降低伪标签噪声在总体损失函数中的作用.同时，为了充分利用伪标签的判别能力，本文利用伪标签进行在线软样本挖掘，构建mini-batch中的正负样本对并为每个正负样本对计算一个连续的权重分数.通过将以上两种权重引入到对比损失中，本文提出的伪标签正则化损失函数可以有效抑制伪标签噪声的影响，减轻标签噪声对训练过程的影响，提高模型的准确性和鲁棒性.在多个公开行人数据集上的实验结果验证了本文方法的有效性，在Market1501、DukeMTMC-reID和MSMT17数据集上mAP分别达到了85.9%、75.1%和29.3%.

Abstract

Unsupervised person re-identification aims to match query pedestrian images with images in the gallery without the need for identity labels. Currently

mainstream unsupervised person re-identification methods typically utilize clustering algorithms to generate pseudo-labels

which are subsequently exploited to train deep neural networks. However

due to the model’s inferior representation ability at early stages and the limitations of the clustering algorithms

a vast of noise is inevitably introduced into the pseudo-labels

which seriously misleads the training process and impedes the model performance. In this paper

we propose a novel pseudo-label regularization loss (PLRL) to remedy the detrimental effect of pseudo-label noises. Concretely

firstly

this paper proposes a clustering-guided attention mechanism (CGA) to estimate the confidence of pseudo-labels based on the semantic relevance between pseudo-labels and clustering centers. The CGA score is able to identify noisy labels and assign more weight to correct labels

which effectively reduces the influence of pseudo-label noise in the overall loss function. Meanwhile

for the sake of fully utilizing the discriminative power of pseudo-labels

this paper performs soft sample mining using pseudo-labels

which constructs positive and negative sample pairs in mini-batches and calculates a continuous weight score for each pair. By incorporating the confidence of pseudo-labels and the similarity of samples into the contrastive loss

the newly designed pseudo-label regularization loss can effectively alleviate the influence of pseudo-label noise in the training process

thereby improving the accuracy and robustness of the model. Experiments and ablation studies on multiple public datasets demonstrate its effectiveness and superiority

with the mAP on Market1501

DukeMTMC-reID

and MSMT17 datasets reaching 85.9%

75.1%

and 29.3%

respectively.

关键词

Keywords

references

匡澄 , 陈莹 . 基于多粒度特征融合网络的行人重识别 [J ] . 电子学报 , 2021 , 49 ( 8 ): 1541 - 1550 .

KUANG C , CHEN Y . Multi-granularity feature fusion network for person re-identification [J ] . Acta Electronica Sinica , 2021 , 49 ( 8 ): 1541 - 1550 . (in Chinese)

GU X Q , CHANG H , MA B P , et al . Clothes-changing person re-identification with RGB modality only [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 1050 - 1059 .

孙锐 , 张磊 , 余益衡 , 等 . 基于局部异构聚合图卷积网络的跨模态行人重识别 [J ] . 电子学报 , 2023 , 51 ( 4 ): 810 - 825 .

SUN R , ZHANG L , YU Y H , et al . Cross-modality person re-identification based on locally heterogeneous polymerization graph convolutional network [J ] . Acta Electronica Sinica , 2023 , 51 ( 4 ): 810 - 825 . (in Chinese)

FAN H H , ZHENG L , YAN C G , et al . Unsupervised person re-identification: Clustering and fine-tuning [J ] . ACM Transactions on Multimedia Computing, Communications, and Applications , 14 ( 4 ): 83 .

FU Y , WEI Y C , WANG G S , et al . Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification [C ] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2019 : 6111 - 6120 .

ZHANG X Y , CAO J W , SHEN C H , et al . Self-training with progressive augmentation for unsupervised cross-domain person re-identification [C ] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2019 : 8221 - 8230 .

LLOYD S . Least squares quantization in PCM [J ] . IEEE Transactions on Information Theory , 1982 , 28 ( 2 ): 129 - 137 .

ESTER M , KRIEGEL H P , SANDER J , et al . A density-based algorithm for discovering clusters in large spatial databases with noise [C ] // Proceedings of the Second International Conference on Knowledge Discovery and Data Mining . New York : ACM , 1996 : 226 - 231 .

GE Y X , CHEN D P , LI H S . Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification [EB/OL ] . ( 2020-01-30 )[ 2023-08-30 ] . http://arxiv.org/abs/2001.01526 http://arxiv.org/abs/2001.01526 .

GE Y X , ZHU F , CHEN D P , et al . Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . New York : ACM , 2020 : 11309 - 11321 .

LI M K , LI C G , GUO J . Cluster-guided asymmetric contrastive learning for unsupervised person re-identification [J ] . IEEE Transactions on Image Processing , 2022 , 31 : 3606 - 3617 .

HU Z , ZHU C , HE G . Hard-sample guided hybrid contrast learning for unsupervised person re-identification [C ] // 2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC) . Piscataway : IEEE , 2021 : 91 - 95 .

XU M Y , GUO H Y , JIA Y H , et al . Pseudo label rectification with joint camera shift adaptation and outlier progressive recycling for unsupervised person re-identification [J ] . IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 3 ): 3395 - 3406 .

LI P N , WU K Y , HUANG S Z Q , et al . Pseudo labels refinement with intra-camera similarity for unsupervised person re-identification [EB/OL ] . ( 2023-04-25 )[ 2023-08-30 ] . http://arxiv.org/abs/2304.12634 http://arxiv.org/abs/2304.12634 .

YIN J H , ZHANG X Y , MA Z Y , et al . A real-time memory updating strategy for unsupervised person re-identification [J ] . IEEE Transactions on Image Processing , 2023 , 32 : 2309 - 2321 .

YE M , YUEN P C . PurifyNet: A robust person re-identification model with noisy labels [J ] . IEEE Transactions on Information Forensics and Security , 2020 , 15 : 2655 - 2666 .

YE M , LI H , DU B , et al . Collaborative refining for person re-identification with label noise [J ] . IEEE Transactions on Image Processing , 2022 , 31 : 379 - 391 .

SUN H , LI M K , LI C G . Hybrid contrastive learning with cluster ensemble for unsupervised person re-identification [C ] // Asian Conference on Pattern Recognition . Cham : Springer , 2022 : 532 - 546 .

ZHENG K C , LAN C L , ZENG W J , et al . Exploiting sample uncertainty for domain adaptive person re-identification [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 4 ): 3538 - 3546 .

彭锦佳 , 王辉兵 . 基于异构卷积神经网络集成的无监督行人重识别方法 [J ] . 电子学报 , 2023 , 51 ( 10 ): 2902 - 2914 .

PENG J J , WANG H B . An unsupervised person re-identification method based on heterogeneous convolutional neural networks ensemble [J ] . Acta Electronica Sinica , 2023 , 51 ( 10 ): 2902 - 2914 . (in Chinese)

DAI Z Z , WANG G Y , YUAN W H , et al . Cluster contrast for unsupervised person re-identification [C ] // Asian Conference on Computer Vision . Cham : Springer , 2023 : 319 - 337 .

ZHAO Y Y , ZHONG Z , YANG F X , et al . Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 6273 - 6282 .

YANG F X , ZHONG Z , LUO Z M , et al . Joint noise-tolerant learning and meta camera shift adaptation for unsupervised person re-identification [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 4853 - 4862 .

WANG X S , HUA Y , KODIROV E , et al . Deep metric learning by online soft mining and class-aware attention [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2019 , 33 ( 1 ): 5361 - 5368 .

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 (CVPR) . Piscataway : IEEE , 2016 : 770 - 778 .

ZHENG L , SHEN L Y , TIAN L , et al . Scalable person re-identification: A benchmark [C ] // 2015 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2015 : 1116 - 1124 .

RISTANI E , SOLERA F , ZOU R , et al . Performance measures and a data set for multi-target, multi-camera tracking [C ] // European Conference on Computer Vision . Amsterdam : Springer , 2016 : 17 - 35 .

WEI L H , ZHANG S L , GAO W , et al . Person transfer GAN to bridge domain gap for person re-identification [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 79 - 88 .

ZHANG Z Z , LAN C L , ZENG W J , et al . Relation-aware global attention for person re-identification [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 3183 - 3192 .

LIN Y T , DONG X Y , ZHENG L , et al . A bottom-up clustering approach to unsupervised person re-identification [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2019 , 33 ( 1 ): 8738 - 8745 .

LIN Y T , XIE L X , WU Y , et al . Unsupervised person re-identification via softened similarity learning [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 3387 - 3396 .

WANG D K , ZHANG S L . Unsupervised person re-identification via multi-label classification [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 10978 - 10987 .

ZENG K W , NING M N , WANG Y H , et al . Hierarchical clustering with hard-batch triplet loss for person re-identification [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 13654 - 13662 .

WANG Z D , ZHANG J W , ZHENG L , et al . CycAs: Self-supervised cycle association for learning re-identifiable descriptions [C ] // European Conference on Computer Vision . Cham : Springer , 2020 : 72 - 88 .

WU J L , LIU H , YANG Y , et al . Unsupervised graph association for person re-identification [C ] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2019 : 8320 - 8329 .

ZHONG Z , ZHENG L , LUO Z M , et al . Invariance matters: Exemplar memory for domain adaptive person re-identification [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2019 : 598 - 607 .

LI M X , ZHU X T , GONG S G . Unsupervised person re-identification by deep learning tracklet association [C ] // European Conference on Computer Vision . Cham : Springer , 2018 : 772 - 788 .

LI M X , ZHU X T , GONG S G . Unsupervised noisy tracklet person re-identification [EB/OL ] . ( 2021-01-16 )[ 2023-08-30 ] . http://arxiv.org/abs/2101.06391 http://arxiv.org/abs/2101.06391 .

SELVARAJU R R , COGSWELL M , DAS A , et al . Grad-CAM: Visual explanations from deep networks via gradient-based localization [C ] // 2017 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 618 - 626 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Progressive Image Synthesis Method Based on Diffusion-Mamba and Scale-Invariant Loss

Neighborhood and Hypergraph Collaboration for Session-Based Recommendation

Construction and Analysis of Cross-Modal General Feature Space Driven by Prior Information

Unsupervised Domain Adaptive Person Re-Identification Based on Progressive Hybrid Contrastive Learning

Related Author

JIA Jie-ru

ZHANG Shuo-rui

QIAN Yu-hua

RUAN Qiu-qi

LI Hao

HAO Wen-ning

ZOU Shi-chen

XIE Xiao-yu

Related Institution

Engineering Research Center for Machine Vision and Data Mining of Shanxi；Province

School of Information and Technology， Shanxi University

Institute of Big Data Science and Industry， Shanxi University

Institute of Information Science， Beijing Jiaotong University

College of Command and Control Engineering, Army Engineering University of PLA

⁰