A CARLA-based dataset with four weather appearances per scene and a multi-layer feature alignment loss improves semantic segmentation under domain shift.
SanMiguel, Marcos Escudero-Vi˜nolo, and Pablo Caballeira
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances
A CARLA-based dataset with four weather appearances per scene and a multi-layer feature alignment loss improves semantic segmentation under domain shift.