基于语义融合的域内相似性分组行人重识别

doi:10.11959/j.issn.1000-436x.2022136

Abstract

Abstract:

Unsupervised cross-domain person re-identification aims to adapt a model trained on a labeled source-domain dataset to a target-domain dataset.However, the cluster-based unsupervised cross-domain pedestrian re-identification algorithm often generates noise due to the different input pedestrian pictures during the network feature learning process, which affects the clustering results.To solve this problem, An intra-domain similarity grouping pedestrian re-identification network based on semantic fusion was proposed.Firstly, a semantic fusion layer was added on the basis of the Baseline network, and the semantic fusion of similar features was performed on the intermediate feature maps from the two aspects of space and channel in turn, so as to improve the adaptive perception ability of the network.In addition, by making full use of the fine-grained information of intra-domain similarity, the network’s clustering accuracy of global and local features was improved.Experiments were carried out on three public datasets, DukeMTMC-ReID, Market1501, MSMT17, and the results demonstrate that the mAP and Rank recognition accuracy are significantly improved compared with recent unsupervised cross-domain person re-identification algorithms.

Key words: unsupervised cross domain, person re-identification, semantic fusion, adaptive perception, fine-grained information

CLC Number:

TP391

Qiqi KOU, Ji HUANG, Deqiang CHENG, Yunlong LI, Jianying ZHANG. Person re-identification with intra-domain similarity grouping based on semantic fusion[J]. Journal on Communications, 2022, 43(7): 153-162.

Figures/Tables 12

References 32

[33]	KINGMA D P , BA J . Adam:a method for stochastic optimization[J]. arXiv Preprint,arXiv:1412.6980, 2014.
[34]	WANG D K , ZHANG S L . Unsupervised person re-identification via multi-label classification[C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2020: 10978-10987.
[35]	ZHONG Z , ZHENG L , LUO Z M ,et al. Learning to adapt invariance in memory for person re-identification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021,43(8): 2723-2738.
[36]	SELVARAJU R R , COGSWELL M , DAS A ,et al. Grad-CAM:visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020,128(2): 336-359.
[1]	LI J H , CHENG D Q , LIU R H ,et al. Unsupervised person re-identification based on measurement axis[J]. IEEE Signal Processing Letters, 2021,28: 379-383.
[2]	ZHAO K , CHENG D Q , KOU Q Q ,et al. Sequences consistency feature learning for video-based person re-identification[J]. Electronics Letters, 2022,58(4): 142-144.
[3]	任雪娜, 张冬明, 包秀国 ,等. 语义引导的遮挡行人再识别注意力网络[J]. 通信学报, 2021,42(10): 106-116.
	REN X N , ZHANG D M , BAO X G ,et al. Semantic guidance atten-tion network for occluded person re-identification[J]. Journal on Communications, 2021,42(10): 106-116.
[4]	SONG L C , WANG C , ZHANG L F ,et al. Unsupervised domain adaptive re-identification:theory and practice[J]. Pattern Recognition, 2020,102:107173.
[5]	QI L , WANG L , HUO J ,et al. A novel unsupervised camera-aware domain adaptation framework for person re-identification[C]// Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2019: 8079-8088.
[6]	CHEN Y B , ZHU X T , GONG S G . Instance-guided context rendering for cross-domain person re-identification[C]// Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2019: 232-242.
[7]	LI Y J , LIN C S , LIN Y B ,et al. Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation[C]// Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2019: 7918-7928.
[8]	LIN X T , REN P Z , YEH C H ,et al. Unsupervised person re-identification:a systematic survey of challenges and solutions[J]. arXiv Preprint,arXiv:2109.06057, 2021.
[9]	GOODFELLOW I , POUGET-ABADIE J , MIRZA M ,et al. Generative adversarial networks[J]. Communications of the ACM, 2020,63(11): 139-144.
[10]	ZHONG Z , ZHENG L , LUO Z M ,et al. Invariance matters:exemplar memory for domain adaptive person re-identification[C]// Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2019: 598-607.
[11]	MEKHAZNI D , BHUIYAN A , EKLADIOUS G ,et al. Unsupervised domain adaptation in the dissimilarity space for person re-identifica tion[C]// Computer Vision - ECCV 2020. Cham:Springer International Publishing, 2020: 159-174.
[12]	YANG Q Z , YU H X , WU A C ,et al. Patch-based discriminative feature learning for unsupervised person re-identification[C]// Pro ceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2019: 3628-3637.
[13]	YU H X , ZHENG W S , WU A C ,et al. Unsupervised person re-identification by soft multilabel learning[C]// Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2019: 2143-2152.
[14]	JIANG K , ZHANG T , ZHANG Y ,et al. Self-supervised agent learning for unsupervised cross-domain person re-identification[J]. IEEE Transactions on Image Processing:a Publication of the IEEE Signal Processing Society, 2020,29: 8549-8560.
[15]	ZHAO R , OUYANG W L , WANG X G . Unsupervised salience learning for person re-identification[C]// Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2013: 3586-3593.
[16]	RUBLEE E , RABAUD V , KONOLIGE K ,et al. ORB:an efficient alternative to SIFT or SURF[C]// Proceedings of 2011 International Conference on Computer Vision. Piscataway:IEEE Press, 2011: 2564-2571.
[17]	JADERBERG M , SIMONYAN K , ZISSERMAN A ,et al. Spatial transformer networks[C]// Proceedings of the 28th International Conference on Neural Information Processing. Cambridge:MIT Press, 2015: 2017-2025.
[18]	DAI J F , QI H Z , XIONG Y W ,et al. Deformable convolutional networks[C]// Proceedings of 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE Press, 2017: 764-773.
[19]	DENG J , DONG W , SOCHER R ,et al. ImageNet:a large-scale hierarchical image database[C]// Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2009: 248-255.
[20]	HE K M , ZHANG X Y , REN S Q ,et al. Deep residual learning for image recognition[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016: 770-778.
[21]	DU Y , YUAN C F , LI B ,et al. Interaction-aware spatio-temporal pyramid attention networks for action classification[C]// Computer Vision - ECCV 2018. Cham:Springer International Publishing, 2018: 388-404.
[22]	ZHANG S S , YANG J , SCHIELE B . Occluded pedestrian detection through guided attention in CNNs[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2018: 6995-7003.
[23]	WANG G S , YUAN Y F , CHEN X ,et al. Learning discriminative features with multiple granularities for person re-identification[C]// Proceedings of the 26th ACM International Conference On Multimedia. New York:ACM Press, 2018: 274-282.
[24]	ESTER M , KRIEGEL H P , SANDER J ,et al. A density-based algo rithm for discovering clusters in large spatial databases with noise[C]// Proceedings of the Second International Conference on Knowledge Discovery and Data Mining. Palo Alto:AAAI Press, 1996: 226-231.
[25]	ZHENG L , SHEN L Y , TIAN L ,et al. Scalable person re-identification:a benchmark[C]// Proceedings of 2015 IEEE International Conference on Computer Vision. Piscataway:IEEE Press, 2015: 1116-1124.
[26]	ZHENG Z D , ZHENG L , YANG Y . Unlabeled samples generated by GAN improve the person re-identification baseline in vitro[C]// Proceedings of 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE Press, 2017: 3774-3782.
[27]	WEI L H , ZHANG S L , GAO W ,et al. Person transfer GAN to bridge domain GAP for person re-identification[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2018: 79-88.
[28]	LI Y J , YANG F E , LIU Y C ,et al. Adaptation and re-identification network:an unsupervised deep transfer learning approach to person re-identification[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway:IEEE Press, 2018: 285-2856.
[29]	WU J L , LIAO S C , LEI Z ,et al. Clustering and dynamic sampling based unsupervised domain adaptation for person re-identification[C]// Proceedings of 2019 IEEE International Conference on Multimedia and Expo. Piscataway:IEEE Press, 2019: 886-891.
[30]	ZHAO Y R , LU H T . Neighbor similarity and soft-label adaptation for unsupervised cross-dataset person re-identification[J]. Neurocomputing, 2020,388: 246-254.
[31]	GE Y , LIU L , ZHANG H X . A three-stage learning approach to cross-domain person re-identification[J]. Applied Soft Computing, 2021,112:107793.
[32]	ZHONG Z , ZHENG L , ZHENG Z D ,et al. Camera style adaptation for person re-identification[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2018: 5157-5166.

Metrics

Recommended 0

No Suggested Reading articles found!

算法	DukeMTMC-ReID→Market1501				Market1501→DukeMTMC-ReID
算法	mAP	R-1	R-5	R-10	mAP	R-1	R-5	R-10
ARN	39.4%	70.3%	80.4%	86.3%	33.4%	60.2%	73.9%	79.5%
PAUL	53.2%	72.0%	82.7%	86.0%	40.1%	68.5%	82.4%	87.4%
CDS	39.9%	71.6%	81.2%	84.7%	42.7%	67.2%	75.9%	79.4%
CR-GAN	54.0%	77.7%	89.7%	92.7%	48.6%	68.9%	80.2%	84.7%
PDA-Net	47.6%	75.2%	86.3%	90.2%	45.1%	63.2%	77.0%	82.5%
UCDA	34.5%	64.3%	-	-	36.7%	55.4%	-	-
MAR	48.0%	67.1%	79.8%	84.2%	40.0%	67.7%	81.9%	87.3%
ECN	43.0%	75.1%	87.6%	91.6%	40.4%	63.3%	75.8%	80.4%
UDAP	53.7%	74.7%	86.9%	90.3%	49.0%	68.4%	80.1%	83.5%
D-MMD	48.8%	70.6%	87.0%	91.5%	46.0%	63.5%	78.8%	83.9%
NSSA	47.9%	76.2%	88.7%	92.4%	45.5%	65.5%	77.9%	81.3%
SAL	38.7%	65.3%	79.7%	84.6%	48.5%	67.6%	80.9%	84.7%
DCJ	51.4%	74.5%	83.8%	87.0%	50.9%	68.3%	79.4%	83.6%
本文算法	56.3%	78.6%	88.7%	92.0%	52.4%	71.7%	79.9%	83.0%

算法	DukeMTMC-ReID→MSMT17				Market1501→MSMT17
算法	mAP	R-1	R-5	R-10	mAP	R-1	R-5	R-10
ECN^[10]	10.2	30.2	41.5	46.8	8.5	25.3	36.3	42.1
NSSA^[30]	12.1	32.8	43.1	48.3	10.6	28.9	38.2	43.3
D-MMD^[11]	15.3	34.4	51.1	58.5	13.5	29.1	46.3	54.1
ECN+GPP^[34]	16.0	42.5	55.9	61.5	15.2	40.4	53.1	58.7
MMCL^[35]	16.2	43.6	54.3	58.9	15.1	40.8	51.8	56.7
本文算法	17.4	45.3	56.2	62.8	15.9	42.2	53.0	57.8

E	DukeMTMC-ReID→Market1501
E	mAP	R-1	R-5	R-10
E=1	53.7	75.9	86.2	90.3
E=2	55.8	78.1	87.9	91.9
E=3	56.3	78.6	88.7	92.0
E=5	55.7	76.2	84.4	89.6

G	DukeMTMC-ReID→Market1501
G	mAP	R-1	R-5	R-10
最大值	53.9	77.0	87.5	89.8
累加	54.4	76.9	88.0	90.4
相乘	56.3	78.6	88.7	92.0

语义模块	DukeMTMC-ReID→Market1501
语义模块	mAP	R-1	R-5	R-10
Baseline（不添加语义模块）	52.3	75.5	85.7	88.9
Baseline+空间语义融合	54.1	77.5	87.3	90.3
Baseline+通道语义融合	53.8	77.1	87.4	90.3
本文算法	56.3	78.6	88.7	92.0

Person re-identification with intra-domain similarity grouping based on semantic fusion

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 32

Related Articles 2

Metrics

Recommended 0

分块情况	DukeMTMC-ReID→Market1501
分块情况	mAP	R-1	R-5	R-10
不分块	51.3	74.2	83.6	87.7
分2块	56.3	78.6	88.7	92.0
分3块	49.2	70.0	81.8	84.5
分4块	40.5	67.2	79.2	83.7

[1]	Xuena REN, Dongming ZHANG, Xiuguo BAO, Bing LI. Semantic guidance attention network for occluded person re-identification [J]. Journal on Communications, 2021, 42(10): 106-116.
[2]	Yanfeng LI,Bin ZHANG,Jia SUN,Houjin CHEN,Jinlei ZHU. Cross-dataset person re-identification method based on multi-pool fusion and background elimination network [J]. Journal on Communications, 2020, 41(10): 70-79.