PNP-VQA

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing4 results

Visual Question Answering (VQA)onVQA v2 val
Accuracy· 2022-10-17
63.3
best: 82.19 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))
SOTA
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training arXiv:2210.08773
Visual Question Answering (VQA)onOK-VQA
Accuracy· 2022-10-17
35.9
best: 66.8 (PaLI-X-VPD)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training arXiv:2210.08773
Visual Question Answering (VQA)onGQA test-dev
Accuracy· 2022-10-17
41.9
best: 72.1 (CFR)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training arXiv:2210.08773
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2022-10-17
64.8
best: 84.3 (PaLI)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training arXiv:2210.08773