FewVLM

Reported on 3 benchmarks across 2 tasks · 1 paper

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
Accuracy· 2021-10-16
16.5
best: 66.8 (PaLI-X-VPD)
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models arXiv:2110.08484
Image CaptioningonFlickr30k Captions test
CIDEr· 2021-10-16
31
best: 67.4 (Unified VLP)
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models arXiv:2110.08484
Image CaptioningonFlickr30k Captions test
SPICE· 2021-10-16
10
best: 17 (Unified VLP)
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models arXiv:2110.08484