Instance-aware diversity feature generation for unsupervised person re-identification
Unsupervised person re-identification (Re-ID) methods have made significant progress by exploiting contrastive learning from unlabeled data. However, the previous approaches including cluster-level or instance-level contrast loss, did not fully explore inherent commonality of each identified individ...
Uložené v:
| Vydané v: | Displays Ročník 83; s. 102717 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier B.V
01.07.2024
|
| Predmet: | |
| ISSN: | 0141-9382, 1872-7387 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Unsupervised person re-identification (Re-ID) methods have made significant progress by exploiting contrastive learning from unlabeled data. However, the previous approaches including cluster-level or instance-level contrast loss, did not fully explore inherent commonality of each identified individual from unlabeled samples, where the divergence of individual cluster and convergence of different clusters leads to a set of noisy pseudo labels which may result in label noise accumulation. To address this issue, we propose an instance-aware diversity feature generation (IDFG) framework, which can form a stable clustering feature space by exhuming diverse counterparts of given exemplars to update memory dictionary of each cluster, so as to reduce the effect of noisy labels. Specifically, we combines instance segmentation and masked auto-encoder to generate foreground-invariant diversity counterparts of given exemplars to reduce inter-class convergence caused by background similarity between different identification instances. Further, we introduce an instance-aware diversity feature mining module, which gradually creates more reliable clusters to generate more robust pseudo labels by exploiting the compactness and independence of clustering to update the memory dictionary. Extensive experiments demonstrate that the proposed IDFG framework achieves impressive performances of 85.6%, 73.7%, and 31.0% mAP on Market1501, DukeMTMC-reID and MSMT17, respectively.
•We propose a novel instance-aware diversity feature generation (IDFG) framework, which transcends the limitations of solely relying on hard positive or negative samples for unsupervised person re-identification.•We introduce instance-aware masked auto-encoder that generates foreground-invariant diversity counterparts of given exemplars to alleviate the instance background interference.•We devise an instance-aware diversity feature mining module, which joints diversity-level contrastive loss to exploit the compactness and independence of clustering to update the memory dictionary.•Extensive experiments validate the superiority of our proposed IDFG compared to the star-of-the-art unsupervised ReID methods on Market1501, DukeMTMC-reID and MSMT17 datasets. |
|---|---|
| AbstractList | Unsupervised person re-identification (Re-ID) methods have made significant progress by exploiting contrastive learning from unlabeled data. However, the previous approaches including cluster-level or instance-level contrast loss, did not fully explore inherent commonality of each identified individual from unlabeled samples, where the divergence of individual cluster and convergence of different clusters leads to a set of noisy pseudo labels which may result in label noise accumulation. To address this issue, we propose an instance-aware diversity feature generation (IDFG) framework, which can form a stable clustering feature space by exhuming diverse counterparts of given exemplars to update memory dictionary of each cluster, so as to reduce the effect of noisy labels. Specifically, we combines instance segmentation and masked auto-encoder to generate foreground-invariant diversity counterparts of given exemplars to reduce inter-class convergence caused by background similarity between different identification instances. Further, we introduce an instance-aware diversity feature mining module, which gradually creates more reliable clusters to generate more robust pseudo labels by exploiting the compactness and independence of clustering to update the memory dictionary. Extensive experiments demonstrate that the proposed IDFG framework achieves impressive performances of 85.6%, 73.7%, and 31.0% mAP on Market1501, DukeMTMC-reID and MSMT17, respectively.
•We propose a novel instance-aware diversity feature generation (IDFG) framework, which transcends the limitations of solely relying on hard positive or negative samples for unsupervised person re-identification.•We introduce instance-aware masked auto-encoder that generates foreground-invariant diversity counterparts of given exemplars to alleviate the instance background interference.•We devise an instance-aware diversity feature mining module, which joints diversity-level contrastive loss to exploit the compactness and independence of clustering to update the memory dictionary.•Extensive experiments validate the superiority of our proposed IDFG compared to the star-of-the-art unsupervised ReID methods on Market1501, DukeMTMC-reID and MSMT17 datasets. |
| ArticleNumber | 102717 |
| Author | Zhao, Xinpeng Li, Guocong Zhang, Xiaowei Dou, Xiao Wang, Zekang |
| Author_xml | – sequence: 1 givenname: Xiaowei orcidid: 0000-0003-4854-3736 surname: Zhang fullname: Zhang, Xiaowei email: xiaowei19870119@sina.com organization: School of Computer Science and Technology, Qingdao University, Qingdao, 266071, China – sequence: 2 givenname: Xiao surname: Dou fullname: Dou, Xiao organization: School of Computer Science and Technology, Qingdao University, Qingdao, 266071, China – sequence: 3 givenname: Xinpeng surname: Zhao fullname: Zhao, Xinpeng organization: School of Computer Science and Technology, Shandong University, Qingdao, 266237, China – sequence: 4 givenname: Guocong surname: Li fullname: Li, Guocong organization: School of Computer Science and Technology, Qingdao University, Qingdao, 266071, China – sequence: 5 givenname: Zekang surname: Wang fullname: Wang, Zekang organization: School of Computer Science and Technology, Qingdao University, Qingdao, 266071, China |
| BookMark | eNqFkM1OQjEQhRuDiYC-gYv7Ahf7x-3FhYkh_pCQuJF1U9qpGYK9pC0Y3t7CdeVCVzM5M2cy5xuRQegCEHLL6IRR1txtJg7TbmsmnHJZJK6YuiBD1ipeK9GqARlSJlk9Ey2_IqOUNpSWTcWHZLUIKZtgoTZfJkLl8AAxYT5WHkzeF-UDAkSTsQuV72K1D2m_g3jABK4qTSp6hBodhIwe7Xnzmlx6s01w81PHZPX89D5_rZdvL4v547K2gja59oY1jXXMMdFYsZ5R7r0wU-WmUymBw0yuG1NmrWy8sSVOuzbWCa-U4AaoFGNy39-1sUspgtcW8_mDHA1uNaP6BEhvdA9InwDpHlAxy1_mXcRPE4__2R56G5RgB4Sok0UoBB1GsFm7Dv8-8A2KOIZN |
| CitedBy_id | crossref_primary_10_1007_s11227_025_07041_z crossref_primary_10_1016_j_imavis_2024_105244 crossref_primary_10_1109_ACCESS_2025_3538168 crossref_primary_10_1109_ACCESS_2024_3508760 crossref_primary_10_1109_ACCESS_2024_3514129 crossref_primary_10_1016_j_displa_2025_103187 |
| Cites_doi | 10.1109/CVPR.2017.660 10.1109/CVPR42600.2020.01367 10.1109/CVPR.2019.00098 10.1109/CVPR52688.2022.00722 10.1109/IC-NIDC54101.2021.9660560 10.1109/CVPR42600.2020.00345 10.1016/j.displa.2023.102467 10.1109/TMM.2022.3174414 10.1007/978-3-030-58536-5_6 10.1007/978-3-030-58621-8_5 10.1109/CVPR52688.2022.01553 10.1016/j.displa.2023.102437 10.1109/TIP.2022.3173163 10.1109/TIP.2022.3169693 10.1007/978-3-030-58571-6_35 10.1109/CVPR.2018.00110 10.1109/CVPR.2016.90 10.1007/978-3-030-58586-0_29 10.1109/ICCV.2017.405 10.1109/CVPR42600.2020.01099 10.1109/ICCV.2019.00621 10.1109/TCSVT.2023.3261898 10.1007/978-3-030-01225-0_30 10.1109/ICCV48922.2021.01469 10.1109/ICCV.2015.133 10.1109/CVPR.2017.389 10.1109/TIP.2022.3224325 10.1109/CVPR42600.2020.00975 10.1109/CVPR.2009.5206848 10.1109/ICCV.2019.00380 10.1109/CVPR.2018.00541 10.1007/978-3-030-58598-3_38 10.1109/CVPR.2018.00016 10.1109/ICCV.2019.00032 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier B.V. |
| Copyright_xml | – notice: 2024 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.displa.2024.102717 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1872-7387 |
| ExternalDocumentID | 10_1016_j_displa_2024_102717 S0141938224000817 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29G 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AABXZ AACTN AAEDT AAEDW AAEPC AAFJI AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABIVO ABJNI ABMAC ABMMH ABXDB ABXRA ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AEZYN AFKWA AFRZQ AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOMHK AOUOD ASPBG AVARZ AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LY7 M41 MAGPM MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PRBVW Q38 R2- RIG ROL RPZ SBC SDF SDG SES SET SEW SPC SPCBC SSB SSM SSO SST SSV SSZ T5K TN5 WUQ XPP ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c306t-fa166cd1d136c3b902ff3a57d5544e2e94b6a136846fac1878bacd3f7732ae043 |
| ISICitedReferencesCount | 7 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001236351000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0141-9382 |
| IngestDate | Sat Nov 29 05:27:52 EST 2025 Tue Nov 18 22:13:59 EST 2025 Tue Jun 18 08:51:18 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Masked autoencoder Diversity features Unsupervised re-ID Pseudo label Contrastive learning |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c306t-fa166cd1d136c3b902ff3a57d5544e2e94b6a136846fac1878bacd3f7732ae043 |
| ORCID | 0000-0003-4854-3736 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_displa_2024_102717 crossref_primary_10_1016_j_displa_2024_102717 elsevier_sciencedirect_doi_10_1016_j_displa_2024_102717 |
| PublicationCentury | 2000 |
| PublicationDate | July 2024 2024-07-00 |
| PublicationDateYYYYMMDD | 2024-07-01 |
| PublicationDate_xml | – month: 07 year: 2024 text: July 2024 |
| PublicationDecade | 2020 |
| PublicationTitle | Displays |
| PublicationYear | 2024 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: CVPR, 2016, pp. 770–778. Y. Lin, L. Xie, Y. Wu, C. Yan, Q. Tian, Unsupervised person re-identification via softened similarity learning, in: CVPR, 2020, pp. 3390–3399. H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in: CVPR, 2017, pp. 2881–2890. Cheng, Zhou, Wang, Gao (b12) 2022; 31 Y. Ge, D. Chen, H. Li, Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification, in: ICLR, 2020. Y. Sun, L. Zheng, Y. Yang, Q. Tian, S. Wang, Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline), in: European Conference on Computer Vision, ECCV, 2018, pp. 480–496. L. Wei, S. Zhang, W. Gao, Q. Tian, Person transfer gan to bridge domain gap for person re-identification, in: CVPR, 2018, pp. 79–88. Han, Yu, Li, Zhao, Pan, Ye, Jiao, Han (b38) 2022; 32 Li, Li, Guo (b14) 2022; 31 Z. Zhong, L. Zheng, D. Cao, S. Li, Re-ranking person re-identification with k-reciprocal encoding, in: CVPR, 2017, pp. 1318–1327. S.-H. Zhang, R. Li, X. Dong, P. Rosin, Z. Cai, X. Han, D. Yang, H. Huang, S.-M. Hu, Pose2Seg: Detection Free Human Instance Segmentation, in: CVPR, 2019, pp. 889–898. X. Zhang, D. Li, Z. Wang, J. Wang, E. Ding, J.Q. Shi, Z. Zhang, J. Wang, Implicit Sample Extension for Unsupervised Person Re-Identification, in: CVPR, 2022, pp. 7359–7368. D. Wang, S. Zhang, Unsupervised person re-identification via multi-label classification, in: CVPR, 2020, pp. 10981–10990. Hermans, Beyer, Leibe (b26) 2017 Qu, Zhang, Zhang (b4) 2023; 78 Z. Hu, C. Zhu, G. He, Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification, in: 2021 7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC, 2021, pp. 91–95. H. Chen, B. Lagadec, F. Bremond, ICE: Inter-instance contrastive encoding for unsupervised person re-identification, in: ICCV, 2021, pp. 14960–14969. J. Li, S. Zhang, Joint visual and temporal consistency for unsupervised domain adaptive person re-identification, in: European Conference on Computer Vision, 2020, pp. 483–499. Z. Zheng, L. Zheng, Y. Yang, Unlabeled samples generated by gan improve the person re-identification baseline in vitro, in: ICCV, 2017, pp. 3754–3762. G. Chen, Y. Lu, J. Lu, J. Zhou, Deep credible metric learning for unsupervised domain adaptation person re-identification, in: European Conference on Computer Vision, 2020, pp. 643–659. MacQueen (b20) 1967; vol. 1 K. Zeng, M. Ning, Y. Wang, Y. Guo, Hierarchical clustering with hard-batch triplet loss for person re-identification, in: CVPR, 2020, pp. 13657–13665. Dai, Liu, Chen, Liu, Shi, Liu, Zhou (b24) 2023; 161 Y. Fu, Y. Wei, G. Wang, Y. Zhou, H. Shi, T.S. Huang, Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification, in: ICCV, 2019, pp. 6112–6121. Y. Zhai, Q. Ye, S. Lu, M. Jia, R. Ji, Y. Tian, Multiple expert brainstorming for domain adaptive person re-identification, in: European Conference on Computer Vision, 2020, pp. 594–611. Si, He, Zhang, Duan (b15) 2023; 25 Z. Dai, G. Wang, S. Zhu, W. Yuan, P. Tan, Cluster Contrast for Unsupervised Person Re-Identification, in: ACCV, 2022, pp. 1142–1160. K. He, X. Chen, S. Xie, Y. Li, P. Dollár, R. Girshick, Masked autoencoders are scalable vision learners, in: CVPR, 2022, pp. 16000–16009. K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, in: CVPR, 2020, pp. 9729–9738. K. Zhou, Y. Yang, A. Cavallaro, T. Xiang, Omni-scale feature learning for person re-identification, in: ICCV, 2019, pp. 3702–3712. L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, Q. Tian, Scalable person re-identification: A benchmark, in: ICCV, 2015, pp. 1116–1124. Zou, Yang, Yu, Kumar, Kautz (b23) 2020 Ning, Zhang, Wang, Ning, Chen, Bai (b3) 2023; 79 Z. Zhong, L. Zheng, Z. Zheng, S. Li, Y. Yang, Camera Style Adaptation for Person Re-identification, in: CVPR, 2018, pp. 5157–5166. Y. Chen, X. Zhu, S. Gong, Instance-guided context rendering for cross-domain person re-identification, in: ICCV, 2019, pp. 232–242. W. Deng, L. Zheng, Q. Ye, G. Kang, Y. Yang, J. Jiao, Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification, in: CVPR, 2018, pp. 994–1003. Z. Wang, J. Zhang, L. Zheng, Y. Liu, Y. Sun, Y. Li, S. Wang, Cycas: Self-supervised cycle association for learning re-identifiable descriptions, in: European Conference on Computer Vision, 2020, pp. 72–88. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, Imagenet: A large-scale hierarchical image database, in: CVPR, 2009, pp. 248–255. Zhong, Zheng, Luo, Li, Yang (b32) 2020; 43 Y. Zou, X. Yang, Z. Yu, B. Kumar, J. Kautz, Joint disentangling and adaptation for cross-domain person re-identification, in: European Conference on Computer Vision, 2020, pp. 87–104. Chen, Cui, Zhang, Zhou, Liu (b13) 2023; 33 Ge, Zhu, Chen, Zhao (b7) 2020; 33 MacQueen (10.1016/j.displa.2024.102717_b20) 1967; vol. 1 Zhong (10.1016/j.displa.2024.102717_b32) 2020; 43 Han (10.1016/j.displa.2024.102717_b38) 2022; 32 Ge (10.1016/j.displa.2024.102717_b7) 2020; 33 10.1016/j.displa.2024.102717_b19 Si (10.1016/j.displa.2024.102717_b15) 2023; 25 10.1016/j.displa.2024.102717_b18 10.1016/j.displa.2024.102717_b17 10.1016/j.displa.2024.102717_b39 10.1016/j.displa.2024.102717_b16 10.1016/j.displa.2024.102717_b37 10.1016/j.displa.2024.102717_b36 10.1016/j.displa.2024.102717_b35 10.1016/j.displa.2024.102717_b34 10.1016/j.displa.2024.102717_b11 10.1016/j.displa.2024.102717_b33 10.1016/j.displa.2024.102717_b10 Li (10.1016/j.displa.2024.102717_b14) 2022; 31 10.1016/j.displa.2024.102717_b31 10.1016/j.displa.2024.102717_b30 Qu (10.1016/j.displa.2024.102717_b4) 2023; 78 10.1016/j.displa.2024.102717_b1 10.1016/j.displa.2024.102717_b2 Dai (10.1016/j.displa.2024.102717_b24) 2023; 161 Cheng (10.1016/j.displa.2024.102717_b12) 2022; 31 Chen (10.1016/j.displa.2024.102717_b13) 2023; 33 Zou (10.1016/j.displa.2024.102717_b23) 2020 10.1016/j.displa.2024.102717_b29 Ning (10.1016/j.displa.2024.102717_b3) 2023; 79 10.1016/j.displa.2024.102717_b28 10.1016/j.displa.2024.102717_b27 Hermans (10.1016/j.displa.2024.102717_b26) 2017 10.1016/j.displa.2024.102717_b25 10.1016/j.displa.2024.102717_b5 10.1016/j.displa.2024.102717_b6 10.1016/j.displa.2024.102717_b22 10.1016/j.displa.2024.102717_b8 10.1016/j.displa.2024.102717_b21 10.1016/j.displa.2024.102717_b9 10.1016/j.displa.2024.102717_b42 10.1016/j.displa.2024.102717_b41 10.1016/j.displa.2024.102717_b40 |
| References_xml | – reference: K. He, X. Chen, S. Xie, Y. Li, P. Dollár, R. Girshick, Masked autoencoders are scalable vision learners, in: CVPR, 2022, pp. 16000–16009. – volume: 79 year: 2023 ident: b3 article-title: Pedestrian re-ID based on feature consistency and contrast enhancement publication-title: Displays – volume: 78 year: 2023 ident: b4 article-title: PMA-Net: A parallelly mixed attention network for person re-identification publication-title: Displays – start-page: 87 year: 2020 end-page: 104 ident: b23 article-title: Joint disentangling and adaptation for cross-domain person re-identification publication-title: ECCV – reference: K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: CVPR, 2016, pp. 770–778. – reference: Z. Hu, C. Zhu, G. He, Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification, in: 2021 7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC, 2021, pp. 91–95. – reference: L. Wei, S. Zhang, W. Gao, Q. Tian, Person transfer gan to bridge domain gap for person re-identification, in: CVPR, 2018, pp. 79–88. – reference: J. Li, S. Zhang, Joint visual and temporal consistency for unsupervised domain adaptive person re-identification, in: European Conference on Computer Vision, 2020, pp. 483–499. – reference: S.-H. Zhang, R. Li, X. Dong, P. Rosin, Z. Cai, X. Han, D. Yang, H. Huang, S.-M. Hu, Pose2Seg: Detection Free Human Instance Segmentation, in: CVPR, 2019, pp. 889–898. – reference: Z. Wang, J. Zhang, L. Zheng, Y. Liu, Y. Sun, Y. Li, S. Wang, Cycas: Self-supervised cycle association for learning re-identifiable descriptions, in: European Conference on Computer Vision, 2020, pp. 72–88. – reference: J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, Imagenet: A large-scale hierarchical image database, in: CVPR, 2009, pp. 248–255. – reference: H. Chen, B. Lagadec, F. Bremond, ICE: Inter-instance contrastive encoding for unsupervised person re-identification, in: ICCV, 2021, pp. 14960–14969. – reference: Z. Zhong, L. Zheng, Z. Zheng, S. Li, Y. Yang, Camera Style Adaptation for Person Re-identification, in: CVPR, 2018, pp. 5157–5166. – volume: vol. 1 start-page: 281 year: 1967 end-page: 297 ident: b20 article-title: Some methods for classification and analysis of multivariate observations publication-title: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability – reference: K. Zeng, M. Ning, Y. Wang, Y. Guo, Hierarchical clustering with hard-batch triplet loss for person re-identification, in: CVPR, 2020, pp. 13657–13665. – reference: Z. Dai, G. Wang, S. Zhu, W. Yuan, P. Tan, Cluster Contrast for Unsupervised Person Re-Identification, in: ACCV, 2022, pp. 1142–1160. – volume: 32 start-page: 29 year: 2022 end-page: 42 ident: b38 article-title: Rethinking sampling strategies for unsupervised person re-identification publication-title: IEEE Trans. Image Process. – reference: W. Deng, L. Zheng, Q. Ye, G. Kang, Y. Yang, J. Jiao, Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification, in: CVPR, 2018, pp. 994–1003. – volume: 161 year: 2023 ident: b24 article-title: Swin MAE: Masked autoencoders for small datasets publication-title: Comput. Biol. Med. – reference: Z. Zheng, L. Zheng, Y. Yang, Unlabeled samples generated by gan improve the person re-identification baseline in vitro, in: ICCV, 2017, pp. 3754–3762. – volume: 25 start-page: 4323 year: 2023 end-page: 4334 ident: b15 article-title: Hybrid contrastive learning for unsupervised person re-identification publication-title: IEEE Trans. Multimed. – reference: Y. Ge, D. Chen, H. Li, Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification, in: ICLR, 2020. – volume: 31 start-page: 3606 year: 2022 end-page: 3617 ident: b14 article-title: Cluster-guided asymmetric contrastive learning for unsupervised person re-identification publication-title: IEEE Trans. Image Process. – reference: X. Zhang, D. Li, Z. Wang, J. Wang, E. Ding, J.Q. Shi, Z. Zhang, J. Wang, Implicit Sample Extension for Unsupervised Person Re-Identification, in: CVPR, 2022, pp. 7359–7368. – reference: D. Wang, S. Zhang, Unsupervised person re-identification via multi-label classification, in: CVPR, 2020, pp. 10981–10990. – reference: Y. Chen, X. Zhu, S. Gong, Instance-guided context rendering for cross-domain person re-identification, in: ICCV, 2019, pp. 232–242. – reference: K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, in: CVPR, 2020, pp. 9729–9738. – reference: Y. Zou, X. Yang, Z. Yu, B. Kumar, J. Kautz, Joint disentangling and adaptation for cross-domain person re-identification, in: European Conference on Computer Vision, 2020, pp. 87–104. – reference: Y. Zhai, Q. Ye, S. Lu, M. Jia, R. Ji, Y. Tian, Multiple expert brainstorming for domain adaptive person re-identification, in: European Conference on Computer Vision, 2020, pp. 594–611. – volume: 31 start-page: 3334 year: 2022 end-page: 3346 ident: b12 article-title: Hybrid dynamic contrast and probability distillation for unsupervised person re-id publication-title: IEEE Trans. Image Process. – volume: 33 start-page: 5908 year: 2023 end-page: 5920 ident: b13 article-title: Dual clustering co-teaching with consistent sample mining for unsupervised person re-identification publication-title: IEEE Trans. Circuits Syst. Video Technol. – reference: G. Chen, Y. Lu, J. Lu, J. Zhou, Deep credible metric learning for unsupervised domain adaptation person re-identification, in: European Conference on Computer Vision, 2020, pp. 643–659. – reference: Z. Zhong, L. Zheng, D. Cao, S. Li, Re-ranking person re-identification with k-reciprocal encoding, in: CVPR, 2017, pp. 1318–1327. – reference: K. Zhou, Y. Yang, A. Cavallaro, T. Xiang, Omni-scale feature learning for person re-identification, in: ICCV, 2019, pp. 3702–3712. – volume: 43 start-page: 2723 year: 2020 end-page: 2738 ident: b32 article-title: Learning to adapt invariance in memory for person re-identification publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: Y. Sun, L. Zheng, Y. Yang, Q. Tian, S. Wang, Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline), in: European Conference on Computer Vision, ECCV, 2018, pp. 480–496. – reference: Y. Fu, Y. Wei, G. Wang, Y. Zhou, H. Shi, T.S. Huang, Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification, in: ICCV, 2019, pp. 6112–6121. – reference: L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, Q. Tian, Scalable person re-identification: A benchmark, in: ICCV, 2015, pp. 1116–1124. – volume: 33 start-page: 11309 year: 2020 end-page: 11321 ident: b7 article-title: Self-paced contrastive learning with hybrid memory for domain adaptive object re-id publication-title: Adv. Neural Inf. Process. Syst. – reference: H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in: CVPR, 2017, pp. 2881–2890. – reference: Y. Lin, L. Xie, Y. Wu, C. Yan, Q. Tian, Unsupervised person re-identification via softened similarity learning, in: CVPR, 2020, pp. 3390–3399. – year: 2017 ident: b26 article-title: In defense of the triplet loss for person re-identification – ident: 10.1016/j.displa.2024.102717_b27 doi: 10.1109/CVPR.2017.660 – ident: 10.1016/j.displa.2024.102717_b36 doi: 10.1109/CVPR42600.2020.01367 – ident: 10.1016/j.displa.2024.102717_b10 – ident: 10.1016/j.displa.2024.102717_b16 doi: 10.1109/CVPR.2019.00098 – ident: 10.1016/j.displa.2024.102717_b19 doi: 10.1109/CVPR52688.2022.00722 – ident: 10.1016/j.displa.2024.102717_b11 doi: 10.1109/IC-NIDC54101.2021.9660560 – ident: 10.1016/j.displa.2024.102717_b35 doi: 10.1109/CVPR42600.2020.00345 – volume: 79 year: 2023 ident: 10.1016/j.displa.2024.102717_b3 article-title: Pedestrian re-ID based on feature consistency and contrast enhancement publication-title: Displays doi: 10.1016/j.displa.2023.102467 – volume: 25 start-page: 4323 year: 2023 ident: 10.1016/j.displa.2024.102717_b15 article-title: Hybrid contrastive learning for unsupervised person re-identification publication-title: IEEE Trans. Multimed. doi: 10.1109/TMM.2022.3174414 – ident: 10.1016/j.displa.2024.102717_b31 doi: 10.1007/978-3-030-58536-5_6 – ident: 10.1016/j.displa.2024.102717_b37 doi: 10.1007/978-3-030-58621-8_5 – ident: 10.1016/j.displa.2024.102717_b17 doi: 10.1109/CVPR52688.2022.01553 – year: 2017 ident: 10.1016/j.displa.2024.102717_b26 – volume: 78 year: 2023 ident: 10.1016/j.displa.2024.102717_b4 article-title: PMA-Net: A parallelly mixed attention network for person re-identification publication-title: Displays doi: 10.1016/j.displa.2023.102437 – volume: 31 start-page: 3606 year: 2022 ident: 10.1016/j.displa.2024.102717_b14 article-title: Cluster-guided asymmetric contrastive learning for unsupervised person re-identification publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2022.3173163 – volume: 31 start-page: 3334 year: 2022 ident: 10.1016/j.displa.2024.102717_b12 article-title: Hybrid dynamic contrast and probability distillation for unsupervised person re-id publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2022.3169693 – ident: 10.1016/j.displa.2024.102717_b34 doi: 10.1007/978-3-030-58571-6_35 – ident: 10.1016/j.displa.2024.102717_b22 doi: 10.1109/CVPR.2018.00110 – ident: 10.1016/j.displa.2024.102717_b29 doi: 10.1109/CVPR.2016.90 – ident: 10.1016/j.displa.2024.102717_b30 doi: 10.1007/978-3-030-58586-0_29 – ident: 10.1016/j.displa.2024.102717_b9 doi: 10.1109/ICCV.2017.405 – volume: vol. 1 start-page: 281 year: 1967 ident: 10.1016/j.displa.2024.102717_b20 article-title: Some methods for classification and analysis of multivariate observations – ident: 10.1016/j.displa.2024.102717_b25 doi: 10.1109/CVPR42600.2020.01099 – ident: 10.1016/j.displa.2024.102717_b6 – ident: 10.1016/j.displa.2024.102717_b18 doi: 10.1109/ICCV.2019.00621 – volume: 33 start-page: 5908 issue: 10 year: 2023 ident: 10.1016/j.displa.2024.102717_b13 article-title: Dual clustering co-teaching with consistent sample mining for unsupervised person re-identification publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2023.3261898 – ident: 10.1016/j.displa.2024.102717_b1 doi: 10.1007/978-3-030-01225-0_30 – ident: 10.1016/j.displa.2024.102717_b39 doi: 10.1109/ICCV48922.2021.01469 – ident: 10.1016/j.displa.2024.102717_b8 doi: 10.1109/ICCV.2015.133 – volume: 33 start-page: 11309 year: 2020 ident: 10.1016/j.displa.2024.102717_b7 article-title: Self-paced contrastive learning with hybrid memory for domain adaptive object re-id publication-title: Adv. Neural Inf. Process. Syst. – volume: 43 start-page: 2723 issue: 8 year: 2020 ident: 10.1016/j.displa.2024.102717_b32 article-title: Learning to adapt invariance in memory for person re-identification publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – ident: 10.1016/j.displa.2024.102717_b42 doi: 10.1109/CVPR.2017.389 – volume: 32 start-page: 29 year: 2022 ident: 10.1016/j.displa.2024.102717_b38 article-title: Rethinking sampling strategies for unsupervised person re-identification publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2022.3224325 – ident: 10.1016/j.displa.2024.102717_b28 doi: 10.1109/CVPR42600.2020.00975 – start-page: 87 year: 2020 ident: 10.1016/j.displa.2024.102717_b23 article-title: Joint disentangling and adaptation for cross-domain person re-identification – volume: 161 year: 2023 ident: 10.1016/j.displa.2024.102717_b24 article-title: Swin MAE: Masked autoencoders for small datasets publication-title: Comput. Biol. Med. – ident: 10.1016/j.displa.2024.102717_b41 doi: 10.1109/CVPR.2009.5206848 – ident: 10.1016/j.displa.2024.102717_b2 doi: 10.1109/ICCV.2019.00380 – ident: 10.1016/j.displa.2024.102717_b21 doi: 10.1109/CVPR.2018.00541 – ident: 10.1016/j.displa.2024.102717_b33 doi: 10.1007/978-3-030-58598-3_38 – ident: 10.1016/j.displa.2024.102717_b40 doi: 10.1109/CVPR.2018.00016 – ident: 10.1016/j.displa.2024.102717_b5 doi: 10.1109/ICCV.2019.00032 |
| SSID | ssj0002472 |
| Score | 2.401078 |
| Snippet | Unsupervised person re-identification (Re-ID) methods have made significant progress by exploiting contrastive learning from unlabeled data. However, the... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 102717 |
| SubjectTerms | Contrastive learning Diversity features Masked autoencoder Pseudo label Unsupervised re-ID |
| Title | Instance-aware diversity feature generation for unsupervised person re-identification |
| URI | https://dx.doi.org/10.1016/j.displa.2024.102717 |
| Volume | 83 |
| WOSCitedRecordID | wos001236351000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-7387 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002472 issn: 0141-9382 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELag5QAHxFNtKSgHbsirJs7G8bFqCxShikMr7S3yE6Wqkmizoe2_7_gRb2ARL4lLFHnjODvzafzZ-jyD0FuYAVIzZwxLXuY4LySDOJiXWGfgEmPzfwhXteQzPTsrFwv2JZw96V05Ado05c0N6_6rq6ENnG2Pzv6Fu-NLoQHuwelwBbfD9Y8cf-oIn9SYX1tVl4rCC6NdEk9bNFkv1xrDoemHzkaMHrhn5wj4u6XGtQo6orXrAoc9rvvuit9GMh73nBc1b691HblxO4ytk0db39Z0OsyZVg3kJAUfhhYW51-n-xBZHjWrYXNs44BM2K9MMSO-vtBM-xhbUiD1JMyzIQj7ajYb8dxvLVzOlPtnMzuuTTZB_XnPHzJlW6FaagezuligOvQ-2s7onEG83j48PVl8ilN0lruqXvHrxjOVTvi3OdbPOcuEh5w_QY_DAiI59I5_iu7p5hl6NEkr-RxdfA-BJEIgCRBI1hBIAALJFAKJh0CyAYEX6OL9yfnRRxzKZ2AJ68AVNjwtCqlSlZJCEsEOMmMIn1MFDDLXmWa5KDj8BgzUcAleKQWXihhKScb1QU5eoq2mbfQOSowwwERFqcBwsERWJUmFMPNCcCoIS8UuIqOBKhlyy9sSJ1fVKCK8rLxZK2vWypt1F-HYq_O5VX7zPB1tXwV-6HlfBXD5Zc-9f-75Cj1cg30fba2Wg36NHshvq7pfvgm4ugNaS43R |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Instance-aware+diversity+feature+generation+for+unsupervised+person+re-identification&rft.jtitle=Displays&rft.au=Zhang%2C+Xiaowei&rft.au=Dou%2C+Xiao&rft.au=Zhao%2C+Xinpeng&rft.au=Li%2C+Guocong&rft.date=2024-07-01&rft.pub=Elsevier+B.V&rft.issn=0141-9382&rft.eissn=1872-7387&rft.volume=83&rft_id=info:doi/10.1016%2Fj.displa.2024.102717&rft.externalDocID=S0141938224000817 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0141-9382&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0141-9382&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0141-9382&client=summon |