Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-ok-vqa
RA-VQA-v2 (BLIP 2)
#7
Accuracy: 62.08
Exact Match (EM): 62.01
Recall@5: 89.32
visual-question-answering-on-ok-vqa
RA-VQA-v2 (T5-large)
#13
Accuracy: 54.85
Rank counts only results with a code link.