Visual Question Answering Vqa On Pmc Vqa

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
MedVInT	42.3	PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
Open-Flamingo	26.4	Flamingo: a Visual Language Model for Few-Shot Learning
PMC-CLIP	24.7	PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents
BLIP-2	24.3	BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

0 of 4 row(s) selected.