Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation

JoonHo Lee; Gyemin Lee

doi:10.1016/j.neunet.2023.02.009

ScienceGate Book Chapters

JOURNAL ARTICLE

Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation

JoonHo Lee Gyemin Lee

Year: 2023 Journal: Neural Networks Vol: 161 Pages: 682-692 Publisher: Elsevier BV

DOI: 10.1016/j.neunet.2023.02.009

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Artificial intelligence Pattern recognition (psychology) Feature (linguistics) Feature vector Generator (circuit theory) Domain adaptation Benchmark (surveying) Classifier (UML) Consistency (knowledge bases) Machine learning

Metrics

Cited By

10.47

FWCI (Field Weighted Citation Impact)

Refs

0.98

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Domain Adaptation and Few-Shot Learning

Physical Sciences → Computer Science → Artificial Intelligence

Multimodal Machine Learning Applications

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Cancer-related molecular mechanisms research

Life Sciences → Biochemistry, Genetics and Molecular Biology → Cancer Research

Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation

Metrics

Citation History

Topics

Related Documents

SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation

Domain‐specific feature recalibration and alignment for multi‐source unsupervised domain adaptation

FGPLFA: Fine-Grained Pseudo-Labeling and Feature Alignment for Source-Free Unsupervised Domain Adaptation

Source-Free Unsupervised Domain Adaptation

Feature mixing and self-training for source-free active domain adaptation