.png){kind=icon}
Return
Semi-supervised semantic segmentation with confidence-driven consistency learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.128965.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• The CDCL is proposed to fully exploit the information in unlabeled data. • The RPR strategy reduces inter-class competition and enhances prediction certainty. • The NLA module is designed to extract robust information from low-confidence pixels. • Experimental results on two benchmark datasets demonstrate the superiority of CDCL.
Journal
IF:
7.5
Papers:
3.0W
Citations:
10.2W
Organization
No organization information available
Cited Papers
Learning pseudo labels for semi-and-weakly supervised semantic segmentation.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSave
Representation-Enhanced Status Replay Network for Multisource Remote-Sensing Image Classification
PREAI
ShareSaveNoise-robust consistency regularization for semi-supervised semantic segmentationNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
ShareSaveShareSaveShareSave
View more