Decomposing clinical terms into visual attributes lets 0.23B-2B vision-language models match or beat much larger medical VLMs for abnormality grounding with only 16k training pairs.
Padchest: A large chest x-ray image dataset with multi-label annotated reports
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding
Decomposing clinical terms into visual attributes lets 0.23B-2B vision-language models match or beat much larger medical VLMs for abnormality grounding with only 16k training pairs.