Few VLM (zero-shot)

Reported on 1 benchmark 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 Processing1 result

Visual Question Answering (VQA)onVQA v2 val
Accuracy· 2021-10-16
47.7
best: 82.19 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))
SOTA
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models arXiv:2110.08484