Long-tailed representation learning algorithm based on adaptive prototypes and semantic awareness.
Saved in:
| Title: | Long-tailed representation learning algorithm based on adaptive prototypes and semantic awareness. |
|---|---|
| Authors: | LI, Tiantian1, XUE, Zhen1 xuezhen@nuc.edu.cn, ZHANG, Liangliang1, LIAN, Xu1 |
| Source: | Journal of Measurement Science & Instrumentation. Jun2026, Vol. 17 Issue 2, p331-343. 13p. |
| Subjects: | Contrastive learning, Fault diagnosis, Feature extraction, Mathematics |
| Abstract: | Label scarcity and long-tailed distribution imbalance are significant challenges in industrial equipment monitoring. Currently, self-supervised learning methods are affected by sample quantity bias and semantic confusion under complex operating conditions, which limits their ability to represent sparse critical states. To address these issues, we propose a co-evolutionary prototypical contrastive learning (EPCL) framework. Through progressive learning from coarse-grained semantic discovery to fine-grained discriminative enhancement, this framework enables an in-depth analysis of the intrinsic structure of long-tailed data. Specifically, an adaptive prototype-based clustering algorithm based on optimal transport theory is introduced, thereby achieving unbiased representation learning through data-driven dynamic priors. Furthermore, a semantic-aware and hierarchical negative sample weighting scheme is designed to optimize discriminative boundaries while mitigating class imbalance by enforcing prototype consistency constraints and employing an adaptive weighting strategy. Extensive experiments were conducted on several public long-tailed visual benchmarks, including CIFAR10-LT, CIFAR100-LT, and ImageNet-100-LT, as well as the industrial fault diagnosis dataset. The results demonstrated that the EPCL achieved better performance than fifteen mainstream self-supervised methods (e.g., SimCLR and SwAV) in both linear evaluation and few-shot classification tasks. On the CIFAR100-LT dataset, the EPCL improved the tail-class accuracy by 4.56% compared to SimCLR. Ablation studies and visualization results verified the effectiveness and generalization ability of the framework. This work offers a promising insight and practical solution for representation learning from unlabeled long-tailed measurement data. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Measurement Science & Instrumentation is the property of Journal of Measurement Science & Instrumentation and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 195003987 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Long-tailed representation learning algorithm based on adaptive prototypes and semantic awareness. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22LI%2C+Tiantian%22">LI, Tiantian</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22XUE%2C+Zhen%22">XUE, Zhen</searchLink><relatesTo>1</relatesTo><i> xuezhen@nuc.edu.cn</i><br /><searchLink fieldCode="AR" term="%22ZHANG%2C+Liangliang%22">ZHANG, Liangliang</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22LIAN%2C+Xu%22">LIAN, Xu</searchLink><relatesTo>1</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Measurement+Science+%26+Instrumentation%22">Journal of Measurement Science & Instrumentation</searchLink>. Jun2026, Vol. 17 Issue 2, p331-343. 13p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Contrastive+learning%22">Contrastive learning</searchLink><br /><searchLink fieldCode="DE" term="%22Fault+diagnosis%22">Fault diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematics%22">Mathematics</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Label scarcity and long-tailed distribution imbalance are significant challenges in industrial equipment monitoring. Currently, self-supervised learning methods are affected by sample quantity bias and semantic confusion under complex operating conditions, which limits their ability to represent sparse critical states. To address these issues, we propose a co-evolutionary prototypical contrastive learning (EPCL) framework. Through progressive learning from coarse-grained semantic discovery to fine-grained discriminative enhancement, this framework enables an in-depth analysis of the intrinsic structure of long-tailed data. Specifically, an adaptive prototype-based clustering algorithm based on optimal transport theory is introduced, thereby achieving unbiased representation learning through data-driven dynamic priors. Furthermore, a semantic-aware and hierarchical negative sample weighting scheme is designed to optimize discriminative boundaries while mitigating class imbalance by enforcing prototype consistency constraints and employing an adaptive weighting strategy. Extensive experiments were conducted on several public long-tailed visual benchmarks, including CIFAR10-LT, CIFAR100-LT, and ImageNet-100-LT, as well as the industrial fault diagnosis dataset. The results demonstrated that the EPCL achieved better performance than fifteen mainstream self-supervised methods (e.g., SimCLR and SwAV) in both linear evaluation and few-shot classification tasks. On the CIFAR100-LT dataset, the EPCL improved the tail-class accuracy by 4.56% compared to SimCLR. Ablation studies and visualization results verified the effectiveness and generalization ability of the framework. This work offers a promising insight and practical solution for representation learning from unlabeled long-tailed measurement data. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Journal of Measurement Science & Instrumentation is the property of Journal of Measurement Science & Instrumentation and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=195003987 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.62756/jmsi.1674-8042.2026028 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 13 StartPage: 331 Subjects: – SubjectFull: Contrastive learning Type: general – SubjectFull: Fault diagnosis Type: general – SubjectFull: Feature extraction Type: general – SubjectFull: Mathematics Type: general Titles: – TitleFull: Long-tailed representation learning algorithm based on adaptive prototypes and semantic awareness. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: LI, Tiantian – PersonEntity: Name: NameFull: XUE, Zhen – PersonEntity: Name: NameFull: ZHANG, Liangliang – PersonEntity: Name: NameFull: LIAN, Xu IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 16748042 Numbering: – Type: volume Value: 17 – Type: issue Value: 2 Titles: – TitleFull: Journal of Measurement Science & Instrumentation Type: main |
| ResultId | 1 |
