Fine-tuning Florence-2 on a 1% subset of Kvasir-VQA with medical image augmentations yields moderate VQA performance on gastrointestinal endoscopy questions.
Vqa: Visual question an- swering
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Multimodal AI for Gastrointestinal Diagnostics: Tackling VQA in MEDVQA-GI 2025
Fine-tuning Florence-2 on a 1% subset of Kvasir-VQA with medical image augmentations yields moderate VQA performance on gastrointestinal endoscopy questions.