RA-VQA-v2 (BLIP 2)

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Visual Question Answering (VQA)onOK-VQA
Exact Match (EM)· 2023-09-29
62.01
SOTA
Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering arXiv:2309.17133
Visual Question Answering (VQA)onOK-VQA
Recall@5· 2023-09-29
89.32
SOTA
Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering arXiv:2309.17133
Visual Question Answering (VQA)onOK-VQA
Accuracy· 2023-09-29
62.08
best: 66.8 (PaLI-X-VPD)
Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering arXiv:2309.17133