Adaptive Hierarchical Similarity Metric Learning with Noisy Labels
Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since these noisy labels often cause a severe performance degrada...
Saved in:
| Published in: | IEEE transactions on image processing Vol. 32; p. 1 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
IEEE
01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 1057-7149, 1941-0042, 1941-0042 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since these noisy labels often cause a severe performance degradation, it is crucial to enhance the robustness and generalization ability of DML. In this paper, we propose an Adaptive Hierarchical Similarity Metric Learning method. It considers two noise-insensitive information, i.e ., class-wise divergence and sample-wise consistency. Specifically, class-wise divergence can effectively excavate richer similarity information beyond binary in modeling by taking advantage of Hyperbolic metric learning, while sample-wise consistency can further improve the generalization ability of the model using contrastive augmentation. More importantly, we design an adaptive strategy to integrate this information in a unified view. It is noteworthy that the new method can be extended to any pair-based metric loss. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current deep metric learning approaches. |
|---|---|
| AbstractList | Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since these noisy labels often cause a severe performance degradation, it is crucial to enhance the robustness and generalization ability of DML. In this paper, we propose an Adaptive Hierarchical Similarity Metric Learning method. It considers two noise-insensitive information, i.e., class-wise divergence and sample-wise consistency. Specifically, class-wise divergence can effectively excavate richer similarity information beyond binary in modeling by taking advantage of Hyperbolic metric learning, while sample-wise consistency can further improve the generalization ability of the model using contrastive augmentation. More importantly, we design an adaptive strategy to integrate this information in a unified view. It is noteworthy that the new method can be extended to any pair-based metric loss. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current deep metric learning approaches. Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since these noisy labels often cause a severe performance degradation, it is crucial to enhance the robustness and generalization ability of DML. In this paper, we propose an Adaptive Hierarchical Similarity Metric Learning method. It considers two noise-insensitive information, i.e., class-wise divergence and sample-wise consistency. Specifically, class-wise divergence can effectively excavate richer similarity information beyond binary in modeling by taking advantage of Hyperbolic metric learning, while sample-wise consistency can further improve the generalization ability of the model using contrastive augmentation. More importantly, we design an adaptive strategy to integrate this information in a unified view. It is noteworthy that the new method can be extended to any pair-based metric loss. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current deep metric learning approaches.Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since these noisy labels often cause a severe performance degradation, it is crucial to enhance the robustness and generalization ability of DML. In this paper, we propose an Adaptive Hierarchical Similarity Metric Learning method. It considers two noise-insensitive information, i.e., class-wise divergence and sample-wise consistency. Specifically, class-wise divergence can effectively excavate richer similarity information beyond binary in modeling by taking advantage of Hyperbolic metric learning, while sample-wise consistency can further improve the generalization ability of the model using contrastive augmentation. More importantly, we design an adaptive strategy to integrate this information in a unified view. It is noteworthy that the new method can be extended to any pair-based metric loss. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current deep metric learning approaches. |
| Author | Huang, Heng Deng, Cheng Yan, Jiexi Luo, Lei |
| Author_xml | – sequence: 1 givenname: Jiexi surname: Yan fullname: Yan, Jiexi organization: School of Computer Science and Technology, Xidian University, Xi'an, China – sequence: 2 givenname: Lei surname: Luo fullname: Luo, Lei organization: JD Finance American Corporation, Mountain View, CA, USA – sequence: 3 givenname: Cheng orcidid: 0000-0003-2620-3247 surname: Deng fullname: Deng, Cheng organization: School of Electronic Engineering, Xidian University, Xi'an, China – sequence: 4 givenname: Heng orcidid: 0000-0002-3483-8333 surname: Huang fullname: Huang, Heng organization: Department of Electrical and Computer Engineering, University of Pittsburgh, PA, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37022798$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kc1P20AQxVcoFeHrzqGqLPXSi9PZD6_tI0UUkAJFAs6r8XrSbOTY6e4GlP-ejRIkxKGH0czh90bz5h2zUT_0xNg5hwnnUP98un2YCBByIoUSXFUH7IjXiucASozSDEWZl1zVY3YcwgKAq4LrQzaWJQhR1tUR-3XR4iq6F8puHHn0du4sdtmjW7oOvYub7I6idzabEvre9X-zVxfn2f3gwiabYkNdOGVfZtgFOtv3E_b8--rp8iaf_rm-vbyY5laqKuZVpW1rbauLBqwGqVreSCFtSTPbVpLXGkUjC0tcSaiERKHRooACUc8QSJ6wH7u9Kz_8W1OIZumCpa7DnoZ1MMnQ1mstIKHfP6GLYe37dF2iSl3WhRBVor7tqXWzpNasvFui35j37yRA7wDrhxA8zYx1EaMb-ujRdYaD2cZgUgxmG4PZx5CE8En4vvs_kq87iSOiDzioVFq-Ac0xkJY |
| CODEN | IIPRE4 |
| CitedBy_id | crossref_primary_10_1109_TGRS_2024_3407952 crossref_primary_10_1109_TIP_2024_3482182 crossref_primary_10_1080_03081079_2024_2430349 crossref_primary_10_1016_j_asoc_2025_113552 crossref_primary_10_1145_3653456 crossref_primary_10_1007_s11042_024_20114_0 crossref_primary_10_1007_s11263_024_02043_5 crossref_primary_10_1016_j_asoc_2025_113266 crossref_primary_10_1007_s12065_024_00990_z crossref_primary_10_1109_TIP_2025_3555069 crossref_primary_10_1007_s11263_024_02175_8 crossref_primary_10_1016_j_displa_2025_103119 crossref_primary_10_1109_TMM_2024_3443616 crossref_primary_10_1109_LRA_2024_3477292 crossref_primary_10_1109_TNNLS_2025_3546903 crossref_primary_10_1109_TPAMI_2024_3382138 crossref_primary_10_1038_s41598_025_97528_9 crossref_primary_10_1016_j_knosys_2024_111791 |
| Cites_doi | 10.1109/CVPR.2017.240 10.1109/CVPR.2015.7298682 10.1007/978-3-030-01270-0_12 10.1007/978-3-319-24261-3_7 10.1109/CVPR42600.2020.00645 10.1007/s11263-015-0816-y 10.1109/MSP.2017.2693418 10.1109/CVPRW50498.2020.00359 10.1109/CVPR.2019.00535 10.1109/CVPR42600.2020.00642 10.1109/TIP.2017.2717505 10.1109/CVPR.2016.434 10.1109/CVPR.2005.202 10.1145/3446776 10.1109/CVPR.2017.237 10.1145/3292500.3330997 10.1109/CVPR42600.2020.00330 10.1109/CVPR.2006.100 10.1109/ICCV.2017.283 10.1109/CVPRW.2017.79 10.1109/CVPR.2018.00208 10.1007/978-3-030-01231-1_17 10.1109/CVPR.2016.158 10.1109/ICCV.2017.94 10.1007/978-3-030-01246-5_5 10.1109/ICPR.2014.16 10.1109/CVPR.2014.242 10.1109/ICCV.2017.47 10.1109/CVPR.2019.00265 10.1109/TIP.2019.2948472 10.1109/CVPR.2019.00742 10.1109/CVPR42600.2020.00643 10.1109/ICCVW.2013.77 10.1109/CVPR42600.2020.01374 10.1109/TIP.2017.2782366 10.1109/ICCV.2019.00655 10.1109/TIP.2018.2870941 10.1109/CVPR.2019.00020 10.1109/CVPR.2019.00510 10.1007/978-3-030-01246-5_45 10.1109/CVPR.2019.00516 10.1109/TIP.2014.2332398 10.1007/978-3-030-01264-9_9 10.1109/ICCV.2017.265 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TIP.2023.3242148 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic Technology Research Database |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering |
| EISSN | 1941-0042 |
| EndPage | 1 |
| ExternalDocumentID | 37022798 10_1109_TIP_2023_3242148 10041006 |
| Genre | orig-research Journal Article |
| GroupedDBID | --- -~X .DC 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 53G 5VS AAYXX ABFSI AETIX AGSQL AI. AIBXA ALLEH CITATION E.L EJD H~9 ICLAB IFJZH VH1 AAYOK NPM PKN RIG Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c348t-886cdccd65b0c6034d1b323c7efcd83196a2b35ce1430823a26aca205aa6fa0e3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 27 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000934998700005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1057-7149 1941-0042 |
| IngestDate | Tue Sep 30 21:55:24 EDT 2025 Mon Jun 30 10:14:41 EDT 2025 Wed Feb 19 02:24:34 EST 2025 Sat Nov 29 03:34:41 EST 2025 Tue Nov 18 21:18:39 EST 2025 Wed Aug 27 02:55:37 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c348t-886cdccd65b0c6034d1b323c7efcd83196a2b35ce1430823a26aca205aa6fa0e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0003-2620-3247 0000-0002-3483-8333 |
| PMID | 37022798 |
| PQID | 2776795228 |
| PQPubID | 85429 |
| PageCount | 1 |
| ParticipantIDs | pubmed_primary_37022798 crossref_citationtrail_10_1109_TIP_2023_3242148 crossref_primary_10_1109_TIP_2023_3242148 ieee_primary_10041006 proquest_journals_2776795228 proquest_miscellaneous_2797149920 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-01-01 |
| PublicationDateYYYYMMDD | 2023-01-01 |
| PublicationDate_xml | – month: 01 year: 2023 text: 2023-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE transactions on image processing |
| PublicationTitleAbbrev | TIP |
| PublicationTitleAlternate | IEEE Trans Image Process |
| PublicationYear | 2023 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref15 ref59 ref14 ref58 Chen (ref36) ref53 Sohn (ref65) ref52 ref11 ref10 ref54 ref17 ref16 Ioffe (ref67) 2015 ref19 ref18 ref51 Chen (ref56) 2020 Han (ref41) 2018 ref44 Chami (ref49) Zhu (ref35) 2020 ref8 Tifrea (ref48) 2018 Berthelot (ref57) 2019 ref7 Mathieu (ref50) ref9 ref4 Yu (ref60) ref3 ref6 ref5 ref40 Khosla (ref37) 2020 ref34 ref31 Sugiyama (ref42) Li (ref25) 2017 ref30 ref33 Paszke (ref66) Van Der Maaten (ref70) 2014; 15 ref2 ref1 ref39 Arpit (ref38) Ma (ref46) Sohn (ref27) 2020 Nickel (ref47) ref24 ref68 ref23 ref26 ref20 ref64 ref63 ref22 ref21 Li (ref45) 2020 ref28 ref29 Wah (ref62) 2011 Kingma (ref69) 2014 Ustinova (ref32) ref61 Van Den Oord (ref55) 2018 Xia (ref43); 32 |
| References_xml | – ident: ref40 doi: 10.1109/CVPR.2017.240 – ident: ref64 doi: 10.1109/CVPR.2015.7298682 – year: 2020 ident: ref37 article-title: Supervised contrastive learning publication-title: arXiv:2004.11362 – ident: ref6 doi: 10.1007/978-3-030-01270-0_12 – year: 2020 ident: ref35 article-title: Fewer is more: A deep graph metric learning perspective using fewer proxies publication-title: arXiv:2010.13636 – ident: ref22 doi: 10.1007/978-3-319-24261-3_7 – ident: ref52 doi: 10.1109/CVPR42600.2020.00645 – ident: ref68 doi: 10.1007/s11263-015-0816-y – ident: ref59 doi: 10.1109/MSP.2017.2693418 – volume: 32 start-page: 6838 volume-title: Proc. NeurIPS ident: ref43 article-title: Are anchor points really indispensable in label-noise learning? – ident: ref28 doi: 10.1109/CVPRW50498.2020.00359 – ident: ref17 doi: 10.1109/CVPR.2019.00535 – ident: ref19 doi: 10.1109/CVPR42600.2020.00642 – ident: ref10 doi: 10.1109/TIP.2017.2717505 – ident: ref23 doi: 10.1109/CVPR.2016.434 – ident: ref1 doi: 10.1109/CVPR.2005.202 – year: 2018 ident: ref55 article-title: Representation learning with contrastive predictive coding publication-title: arXiv:1807.03748 – ident: ref39 doi: 10.1145/3446776 – start-page: 233 volume-title: Proc. ICML ident: ref38 article-title: A closer look at memorization in deep networks – start-page: 6338 volume-title: Proc. NIPS ident: ref47 article-title: Poincaré embeddings for learning hierarchical representations – ident: ref14 doi: 10.1109/CVPR.2017.237 – ident: ref51 doi: 10.1145/3292500.3330997 – ident: ref20 doi: 10.1109/CVPR42600.2020.00330 – ident: ref31 doi: 10.1109/CVPR.2006.100 – ident: ref13 doi: 10.1109/ICCV.2017.283 – year: 2015 ident: ref67 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: arXiv:1502.03167 – volume: 15 start-page: 3221 issue: 1 year: 2014 ident: ref70 article-title: Accelerating t-SNE using tree-based algorithms publication-title: J. Mach. Learn. Res. – ident: ref11 doi: 10.1109/CVPRW.2017.79 – start-page: 4170 volume-title: Proc. NIPS ident: ref32 article-title: Learning deep embeddings with histogram loss – ident: ref2 doi: 10.1109/CVPR.2018.00208 – ident: ref24 doi: 10.1007/978-3-030-01231-1_17 – start-page: 7164 volume-title: Proc. ICML ident: ref60 article-title: How does disagreement help generalization against label corruption? – ident: ref4 doi: 10.1109/CVPR.2016.158 – ident: ref63 doi: 10.1109/ICCV.2017.94 – ident: ref26 doi: 10.1007/978-3-030-01246-5_5 – year: 2011 ident: ref62 article-title: The Caltech-UCSD birds-200-2011 dataset – start-page: 4868 volume-title: Proc. NIPS ident: ref49 article-title: Hyperbolic graph convolutional neural networks – ident: ref5 doi: 10.1109/ICPR.2014.16 – year: 2019 ident: ref57 article-title: ReMixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring publication-title: arXiv:1911.09785 – year: 2020 ident: ref27 article-title: FixMatch: Simplifying semi-supervised learning with consistency and confidence publication-title: arXiv:2001.07685 – start-page: 1 volume-title: Proc. NeurIPS ident: ref42 article-title: Co-teaching: Robust training of deep neural networks with extremely noisy labels – ident: ref8 doi: 10.1109/CVPR.2014.242 – ident: ref33 doi: 10.1109/ICCV.2017.47 – ident: ref54 doi: 10.1109/CVPR.2019.00265 – start-page: 8026 volume-title: Proc. NIPS ident: ref66 article-title: PyTorch: An imperative style, high-performance deep learning library – ident: ref15 doi: 10.1109/TIP.2019.2948472 – ident: ref18 doi: 10.1109/CVPR.2019.00742 – ident: ref21 doi: 10.1109/CVPR42600.2020.00643 – ident: ref61 doi: 10.1109/ICCVW.2013.77 – ident: ref44 doi: 10.1109/CVPR42600.2020.01374 – ident: ref12 doi: 10.1109/TIP.2017.2782366 – ident: ref34 doi: 10.1109/ICCV.2019.00655 – ident: ref7 doi: 10.1109/TIP.2018.2870941 – year: 2018 ident: ref48 article-title: Poincaré GloVe: Hyperbolic word embeddings publication-title: arXiv:1810.06546 – ident: ref58 doi: 10.1109/CVPR.2019.00020 – start-page: 3355 volume-title: Proc. ICML ident: ref46 article-title: Dimensionality-driven learning with noisy labels – start-page: 12565 volume-title: Proc. NIPS ident: ref50 article-title: Continuous hierarchical representations with Poincaré variational auto-encoders – year: 2020 ident: ref45 article-title: DivideMix: Learning with noisy labels as semi-supervised learning publication-title: arXiv:2002.07394 – year: 2014 ident: ref69 article-title: Adam: A method for stochastic optimization publication-title: arXiv:1412.6980 – start-page: 1857 volume-title: Proc. NIPS ident: ref65 article-title: Improved deep metric learning with multi-class n-pair loss objective – ident: ref30 doi: 10.1109/CVPR.2019.00510 – year: 2018 ident: ref41 article-title: Co-teaching: Robust training of deep neural networks with extremely noisy labels publication-title: arXiv:1804.06872 – ident: ref16 doi: 10.1007/978-3-030-01246-5_45 – ident: ref29 doi: 10.1109/CVPR.2019.00516 – ident: ref9 doi: 10.1109/TIP.2014.2332398 – ident: ref53 doi: 10.1007/978-3-030-01264-9_9 – year: 2020 ident: ref56 article-title: Improved baselines with momentum contrastive learning publication-title: arXiv:2003.04297 – start-page: 1597 volume-title: Proc. ICML ident: ref36 article-title: A simple framework for contrastive learning of visual representations – ident: ref3 doi: 10.1109/ICCV.2017.265 – year: 2017 ident: ref25 article-title: WebVision database: Visual learning and understanding from web data publication-title: arXiv:1708.02862 |
| SSID | ssj0014516 |
| Score | 2.568089 |
| Snippet | Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1 |
| SubjectTerms | Adaptation models Cognitive tasks Consistency Contrastive Augmentation Deep Metric Learning Geometry Hierarchical Similarity Hyperbolic Geometry Labels Machine learning Measurement Noise measurement Noisy Labels Performance degradation Robustness Similarity Task analysis Training |
| Title | Adaptive Hierarchical Similarity Metric Learning with Noisy Labels |
| URI | https://ieeexplore.ieee.org/document/10041006 https://www.ncbi.nlm.nih.gov/pubmed/37022798 https://www.proquest.com/docview/2776795228 https://www.proquest.com/docview/2797149920 |
| Volume | 32 |
| WOSCitedRecordID | wos000934998700005&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: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 1941-0042 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014516 issn: 1057-7149 databaseCode: RIE dateStart: 19920101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB60eNCD1fqqLyJ48bDtvrM5VrEoaBGs0tuSnaSyUFuxreC_N5NNSy8KXpaFze6GzGTnS2bn-wAu0UCQROrECxVHLzZBwBOp0l4h48J03MQwqxn5-sB7vWwwEE-uWN3Wwmit7c9nukWnNpevJjinrbI2sZsFlmB7nfO0KtZapgxIcdamNhPucYP7FzlJX7T7908tkglvEXoISOpnJQZZUZXf8aWNM936P3u4A9sOULJO5QG7sKbHDag7cMnc1J02YGuFeXAPrjtKftCXjt2VVIJsFVFG7Ll8L81S1yBz9khSW8gc_-obow1b1puU02_2IAsTUffhpXvbv7nznJyCh1GczbwsS1EhqjQpfEz9KFZBEYURcj1EldFUlGERJagNhKL8mwxTiZJMKdOh9HV0ALXxZKyPgKHPhR_HMkWD-MxBhqjVsCgCHaNUKJrQXgxwjo5rnCQvRrldc_giNybJySS5M0kTrpZ3fFQ8G3-03aeRX2lXDXoTThdGzN1MnOYh0RUJgzLNbRfLy2YOUWJEjvVkTm0EeYwI_SYcVsZfPjzilmQxO_7lpSewSX2rdmVOoTb7nOsz2MCvWTn9PDeOOsjOraP-AJfV4v0 |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD6ICuqD98u8RvDFh25Zm17yqKJMnENwim8lPcmkoJu4TfDfm5NmYy8KvpRC0zbk5PR8yen5PoAztBAkViYOQp1iIGwQCGSiTVAoUdiO2xjmNCOf22mnk728yAdfrO5qYYwx7uczU6dTl8vXAxzTVlmD2M2ajmB7IRYi5FW51jRpQJqzLrkZp0Fqkf8kK8llo3v7UCeh8DrhhyaJ_cxEISer8jvCdJHmZu2ffVyHVQ8p2UU1BzZgzvQ3Yc3DS-add7gJKzPcg1tweaHVB33rWKukImSnifLGHsv30i52LTZn9yS2hcwzsL4y2rJlnUE5_GZtVdiYug1PN9fdq1bgBRUCjEQ2CrIsQY2ok7jgmPBI6GYRhRGmpoc6I2dUYRHFaCyIogycChOFioypkp7iJtqB-f6gb_aAIU8lF0IlaDGfPagQje4VRdMIVBplDRqTAc7Rs42T6MVb7lYdXObWJDmZJPcmqcH59I6Pimnjj7bbNPIz7apBr8HhxIi598VhHhJhkbQ40952Or1svYhSI6pvBmNqI2nGyJDXYLcy_vThUepoFrP9X156Akut7n07b9927g5gmfpZ7dEcwvzoc2yOYBG_RuXw89hN1x8zKOVc |
| 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=Adaptive+Hierarchical+Similarity+Metric+Learning+With+Noisy+Labels&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Yan%2C+Jiexi&rft.au=Luo%2C+Lei&rft.au=Deng%2C+Cheng&rft.au=Huang%2C+Heng&rft.date=2023-01-01&rft.issn=1057-7149&rft.eissn=1941-0042&rft.volume=32&rft.spage=1245&rft.epage=1256&rft_id=info:doi/10.1109%2FTIP.2023.3242148&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIP_2023_3242148 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon |