Florence-2 is a new vision foundation model by MSFT capable of a wide variety of tasks 🤯 Let's unpack! 🧶 Demo, models and more on the next one 🐣  

![image_1](image_1.jpg)

This model is can handle tasks that vary from document understanding to semantic segmentation 🤩  
[Demo](https://t.co/7YJZvjhw84) | [Collection](https://t.co/Ub7FGazDz1)

![image_2](image_2.jpg)

The difference from previous models is that the authors have compiled a dataset that consists of 126M images with 5.4B annotations labelled with their own data engine ↓↓  

![image_3](image_3.jpg)

The dataset also offers more variety in annotations compared to other datasets, it has region level and image level annotations with more variety in semantic granularity as well!  

![image_4](image_4.jpg)

The model is a similar architecture to previous models, an image encoder, a multimodality encoder with text decoder. The authors have compiled the multitask dataset with prompts for each task which makes the model trainable on multiple tasks 🤗 

![image_5](image_5.jpg)

You also fine-tune this model on any task of choice, the authors also released different results on downstream tasks and report their results when un/freezing vision encoder 🤓📉  
They have released fine-tuned models too, you can find them in the collection above 🤗 

![image_6](image_6.jpg)

> [!TIP]
Ressources:  
[Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://arxiv.org/abs/2311.06242) 
by Bin Xiao, Haiping Wu, Weijian Xu, Xiyang Dai, Houdong Hu, Yumao Lu, Michael Zeng, Ce Liu, Lu Yuan (2023) 
[Hugging Face blog post](https://huggingface.co/blog/finetune-florence2)   

> [!NOTE]
[Original tweet](https://twitter.com/mervenoyann/status/1803769866878623819) (June 20, 2024)