Multimodal model

Falcon Perception

Falcon Perception is TII UAE’s 0.6B early-fusion vision-language model for open-vocabulary grounding and instance segmentation. Given an image and a natural language query, it can return zero, one, or many matching objects with pixel-accurate masks, making it suited for promptable object selection and dense visual localization tasks.

Type
Multimodal
Weights
Open
Downloads
13k
Likes
145
Pipeline
mask generation
License
apache-2.0

Model hub

tiiuae/Falcon-Perception

Repo
tiiuae/Falcon-Perception
Library
transformers
Access
Public
Technical tags and languages
transformers safetensors falcon_perception text-generation falcon segmentation vision-language open-vocabulary mask-generation custom_code eval-results
Open on Hugging Face

Papers

2

More from Technology Innovation Institute

5

About Technology Innovation Institute

1

TII is a leading global research center dedicated to pushing the frontiers of knowledge.