A semi-supervised pipeline applies UniMatch V2 to the WeatherProof dataset by treating degraded images as unlabeled data plus test-time augmentation for semantic segmentation in adverse weather.
arXiv preprint arXiv:2312.09534 , year=
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
-
A Robust Semantic Segmentation Pipeline for the CVPR 2026 8th UG2+ Challenge Track 2
A semi-supervised pipeline applies UniMatch V2 to the WeatherProof dataset by treating degraded images as unlabeled data plus test-time augmentation for semantic segmentation in adverse weather.