RA-VQA (T5-large)

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)· 2022-10-07
59.41
best: 62.01 (RA-VQA-v2 (BLIP 2))
SOTA
Retrieval Augmented Visual Question Answering with Outside Knowledge arXiv:2210.03809
Visual Question Answering (VQA)onOK-VQA
Recall@5· 2022-10-07
82.84
best: 89.32 (RA-VQA-v2 (BLIP 2))
SOTA
Retrieval Augmented Visual Question Answering with Outside Knowledge arXiv:2210.03809
Visual Question Answering (VQA)onOK-VQA
Accuracy· 2022-10-07
54.48
best: 66.8 (PaLI-X-VPD)
Retrieval Augmented Visual Question Answering with Outside Knowledge arXiv:2210.03809