Supervised contrastive learning with corrected labels for noisy label learning

Jihong Ouyang; Chenyang Lu; Bing Wang; Changchun Li

doi:10.1007/s10489-023-05018-0

ScienceGate Book Chapters

JOURNAL ARTICLE

Supervised contrastive learning with corrected labels for noisy label learning

Jihong Ouyang Chenyang Lu Bing Wang Changchun Li

Year: 2023 Journal: Applied Intelligence Vol: 53 (23)Pages: 29378-29392 Publisher: Springer Science+Business Media

DOI: 10.1007/s10489-023-05018-0

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Artificial intelligence Supervised learning Machine learning Semi-supervised learning Feature vector Artificial neural network Feature learning Feature (linguistics) ENCODE Sample (material) Cross entropy Pattern recognition (psychology)

Metrics

Cited By

1.28

FWCI (Field Weighted Citation Impact)

Refs

0.80

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Machine Learning and Data Classification

Physical Sciences → Computer Science → Artificial Intelligence

Water Systems and Optimization

Physical Sciences → Engineering → Civil and Structural Engineering

Domain Adaptation and Few-Shot Learning

Physical Sciences → Computer Science → Artificial Intelligence

Supervised contrastive learning with corrected labels for noisy label learning

Metrics

Citation History

Topics

Related Documents

Selective-Supervised Contrastive Learning with Noisy Labels

NCMatch: Semi-supervised Learning with Noisy Labels via Noisy Sample Filter and Contrastive Learning

Federated semi-supervised learning with contrastive representations against noisy labels

Combining layered label correction and mixup supervised contrastive learning to learn noisy labels

Twin Contrastive Learning with Noisy Labels