融合多聚类信息的无监督行人重识别算法

doi:10.3778/j.issn.1002-8331.2102-0013

摘要/Abstract

摘要： 在无监督的行人重识别领域中，始终很难对数据集中的难样本对进行很好的挖掘。针对这个问题，提出了融合多种聚类信息生成软多重标签并进行难样本对挖掘的方法。该方法基于不同聚类方法使用的聚类机制不同这一原理，发掘类内样本的共通性与类间样本的差异性，进而使模型能够学习到更有区分性的特征。在Market-1501数据集与DukeMTMC-reID数据集上进行的对比实验结果表明，提出的方法在原来初步学习的网络的基础上，mAP分别提高了14.4%与8.9%，精度均提高显著。

关键词: 行人重识别, 神经网络, 聚类, 难样本挖掘

Abstract: It is never easy to conduct satisfactory data mining in the feild of unsupervised person re-identification. Aiming at this problem, a method that integrates multiple types of clustering information is proposed to generate soft multi-labels and mine hard sample pairs. Based on the principle that different clustering methods use different clustering mechanisms, this method explores the commonality of samples within a class and the differences of samples between classes, thus the model can learn more distinguishing features. The results of comparative experiments carried out on the Market-1501 and the DukeMTMC-reID show that, compared with the original network, the mAP of the proposed method is increased by 14.4% and 8.9% respectively, indicating significant accuracy enhancement.

Key words: person re-identification, neural network, cluster, hard samples mining

苏荻翔, 王帮海, 叶子成. 融合多聚类信息的无监督行人重识别算法[J]. 计算机工程与应用, 2022, 58(18): 195-204.

SU Dixiang, WANG Banghai, YE Zicheng. Unsupervised Person Re-Identification Algorithm by Fusing Multi-Cluster Information[J]. Computer Engineering and Applications, 2022, 58(18): 195-204.

参考文献

[1] HUANG H，LI D，ZHANG Z，et al.Adversarially occluded samples for person Re-identification[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：5098-5107.
[2] LUO H，GU Y，LIAO X，et al.Bag of tricks and a strong baseline for deep person re-identification[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops（CVPRW），2019：1487-1495.
[3] ZHANG Z，LAN C，ZENG W，et al.Densely semantically aligned person re-identification[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Long Beach，CA，USA，2019：667-676.
[4] WANG Y，CHEN Z，WU F，et al.Person re-identification with cascaded pairwise convolutions[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Salt Lake City，UT，2018：1470-1478.
[5] SUN Y G，ZHENG L，YANG Y，et al.Beyond part models：person retrieval with refined part pooling（and a strong convolutional baseline）[C]//Proceedings of the 2018 European Conference on Computer Vision.Munich，Germany：Springer，2018：480-496.
[6] HERMANS A，BEYER L，LEIBE B.In defense of the triplet lossfor person re-identification[C]//IEEE International Conference on Computer Vision，2017：5426-5434.
[7] WANG D，ZHANG S.Unsupervised person re-identification via multi-label classification[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Seattle，WA，USA，2020：10978-10987.
[8] JIN X，LAN C L，ZENG W J，et al.Global distance-distributions separation for unsupervised person re-identification[J].arXiv：2006.00752，2020.
[9] GE Y，CHEN D，LI H.Mutual mean-teaching：pseudo label refinery for unsupervised domain adaptation on person re-identification[C]//International Conference on Learning Representations，2020：1-15.
[10] ZHANG X，CAO J，SHEN C，et al.Self-training with progressive augmentation for unsupervised cross-domain person re-identification[C]//International Conference on Computer Vision，2019.
[11] ZHAI Y，LU S，YE Q，et al.Ad-cluster：augmented discriminative clustering for domain adaptive person re-identification[C]//Computer Vision and Pattern Recognition（CVPR），2020.
[12] YU H，ZHENG W，WU A，et al.Unsupervised person re-identification by soft multilabel learning[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Long Beach，CA，USA，2019：2143-2152.
[13] ZHONG Z，ZHENG L，ZHENG Z，et al.Camera style adaptation for person re-identification[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Salt Lake City，UT，2018：5157-5166.
[14] 张师林，曹旭.基于Camstyle改进的行人重识别算法[J]计算机工程与应用，2020，56（15）：124-131.
ZHANG S L，CAO X.Improved person re-identification algorithm on camstyle[J].Computer Engineering and Applications，2020，56（15）：124-131.
[15] DENG W，ZHENG L，YE Q，et al.Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Salt Lake City，UT，2018：994-1003.
[16] CAMPELLO R J G B，MOULAVI D，SANDER J.Density-based clustering based on hierarchical density estimates[C]//Proceedings of Pacific-Asia Conference on Knowledge Discovery & Data Mining，2013：160-172.
[17] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas：IEEE Computer Society，2016：770-778.
[18] HUANG H J，YANG W J，CHEN X T，et al.EANet：enhancing alignment for cross-domain person re-identification[EB/OL].[2020-10-21].http：//arxiv.org/abs/1812.11369.
[19] ZHONG Z，ZHENG L，ZHENG Z，et al.Camera style adaptation for person re-identification[C]//International Conference on Computer Vision and Pattern Recognition，2018：5157-5166.
[20] DENG W，ZHENG L，YE Q，et al.Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：994-1003.
[21] ZHAO F，LIAO S，XIE G S，et al.Unsupervised domain adaptation with noise resistible mutual-training for person re-identification[C]//European Conference on Computer Vision，2020.
[22] GE Y，ZHU F，CHEN D，et al.Self-paced contrastive learning with hybrid memory for domain adaptive object re-id[J].arXiv：2006.02713，2020.
[23] DENG J，DONG W，SOCHER R，et al.ImageNet：a large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition，2009：248-255.
[24] WOO S，PARK J，LEE J，et al.CBAM：convolutional block attention module[C]//European Conference on Computer Vision，2018：3-19.
[25] 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 ACM SIGKDD International Conference on Knowledge Discovery & Data Mining，1996：226-231.
[26] ZHENG L，SHEN L，TIAN L，et al.Scalable person re-identification：a benchmark[C]//IEEE International Conference on Computer Vision.Santiago，Chile，2015：1116-1124.
[27] ZHENG Z，ZHENG L，YANG Y.Unlabeled samples generated by gan improve the person re-identification baseline in vitro[C]//IEEE International Conference on Computer Vision，2017：3754-3762.
[28] ZHONG Z，ZHENG L，CAO D，et al.Re-ranking person reidentification with k-reciprocal encoding[J].arXiv：1701.08398，2017.
[29] WANG J Y，ZHU X T，GONG S G，et al.Transferable joint attribute-identity deep learning for unsupervised person reidentification[J].arXiv：1803.09786，2018.
[30] DENG W，ZHENG L，YE Q，et al.Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]//Computer Vision and Pattern Recognition，2018.
[31] ZHONG Z，ZHENG L，LI S，et al.Generalizing a person retrieval model hetero-and homogeneously[C]//European Conference on Computer Vision，2018：172-188.
[32] ZHONG Z，ZHENG L，LUO Z，et al.Invariance matters：exemplar memory for domain adaptive person reidentification[J].arXiv：1904.01990，2019.
[33] LI Y J，LIN C S，LIN Y B，et al.Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation[J].arXiv：1909.09675，2019.