Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

Zhedong Zheng; Yi Yang

doi:10.1007/s11263-020-01395-y

ScienceGate Book Chapters

JOURNAL ARTICLE

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

Zhedong Zheng Yi Yang

Year: 2021 Journal: International Journal of Computer Vision Vol: 129 (4)Pages: 1106-1120 Publisher: Springer Science+Business Media

DOI: 10.1007/s11263-020-01395-y

Get Full-Text PDF Get Analytical Report

Keywords:

Segmentation Computer science Benchmark (surveying) Artificial intelligence Context (archaeology) Domain (mathematical analysis) Machine learning Ground truth Pattern recognition (psychology) Exploit Variance (accounting) Mathematics

Metrics

515

Cited By

62.23

FWCI (Field Weighted Citation Impact)

Refs

1.00

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

Advanced Neural Network Applications

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

Metrics

Citation History

Topics

Related Documents

Uncertainty-aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation

Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation with Implicit Neural Representations

Uncertainty-weighted prototype active learning in domain adaptive semantic segmentation

Confidence-guided Source Label Refinement and Class-aware Pseudo-Label Thresholding for Domain-Adaptive Semantic Segmentation