| Benchmark | Score |
|---|---|
| CER (arXiv v2) | |
| bag-of-words similarity (arXiv v2) | |
| BLEU (arXiv v2) | |
| BLEU/METEOR/BoW average (arXiv v2) |
Show 3 more benchmarksHide 3 benchmarks
| Benchmark | Score |
|---|---|
| CER/WER average (arXiv v2) | |
| METEOR (arXiv v2) | |
| WER (arXiv v2) |
unknown · Chat
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
Also known as: fal-ai/florence-2-large/caption-to-phrase-grounding, fal-ai/florence-2-large/dense-region-caption, fal-ai/florence-2-large/more-detailed-caption, fal-ai/florence-2-large/object-detection, fal-ai/florence-2-large/ocr-with-region, fal-ai/florence-2-large/open-vocabulary-detection, fal-ai/florence-2-large/referring-expression-segmentation, fal-ai/florence-2-large/region-proposal, fal-ai/florence-2-large/region-to-description, fal-ai/florence-2-large/region-to-segmentation
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works