A new AFR module improves HRDA-based UDA semantic segmentation by roughly 1 mIoU using logit-guided attention and uncertainty-driven refinement.
The cityscapes dataset for semantic urban scene understanding,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AFRDA: Attentive Feature Refinement for Domain Adaptive Semantic Segmentation
A new AFR module improves HRDA-based UDA semantic segmentation by roughly 1 mIoU using logit-guided attention and uncertainty-driven refinement.