Skip to content

BEIT-3

MicrosoftObject detectionSemantic segmentationImage classificationVisual question answeringImage captioningLanguage generationOpen weights

BEIT-3 is object detection model published by Microsoft in 2022 featuring 1900000000.0 parameters.

About BEIT-3

A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language ta

Details

Provider
Microsoft
Task
Object detection,Semantic segmentation,Image classification,Visual question answering,Image captioning,Language generation
Parameters
1900000000.0
Released
2022-08-22
Open weights
Yes
View model source

Explore

FAQ