Frozen

Reported on 2 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 Processing2 results

Visual Question Answering (VQA)onOK-VQA
Accuracy· 2021-06-25
5.9
best: 66.8 (PaLI-X-VPD)
SOTA
Multimodal Few-Shot Learning with Frozen Language Models arXiv:2106.13884
Visual Question Answering (VQA)onVQA v2 val
Accuracy· 2021-06-25
29.5
best: 82.19 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))
SOTA
Multimodal Few-Shot Learning with Frozen Language Models arXiv:2106.13884