WeatherSeg combines dual teacher-student weight sharing and classifier-updating attention to deliver more accurate and robust semantic segmentation across clear, rainy, cloudy, and foggy conditions.
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning re- sults
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
WeatherSeg: Weather-Robust Image Segmentation using Teacher-Student Dual Learning and Classifier-Updating Attention
WeatherSeg combines dual teacher-student weight sharing and classifier-updating attention to deliver more accurate and robust semantic segmentation across clear, rainy, cloudy, and foggy conditions.