A disease-aware prompting method that reweights chest X-ray features using the model's own explainability map improves weakly-supervised visual grounding on three benchmarks.
Coco- stuff: Thing and stuff classes in context
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
-
Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
A disease-aware prompting method that reweights chest X-ray features using the model's own explainability map improves weakly-supervised visual grounding on three benchmarks.