A probabilistic vision-language adapter that models text tokens as Gaussian distributions and uses Mahalanobis distance for uncertainty-weighted alignment, improving medical image segmentation under data scarcity and domain shift.
A survey on deep learning in medical image analysis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DistMedVL: Distributional Vision-Language Alignment for Uncertainty-Aware Medical Image Segmentation
A probabilistic vision-language adapter that models text tokens as Gaussian distributions and uses Mahalanobis distance for uncertainty-weighted alignment, improving medical image segmentation under data scarcity and domain shift.