Skip to content

ALIGN

Google ResearchRepresentation learningImage classificationImage representation

The ALIGN model is a representation learning model from Google Research with 820000000.0 parameters.

About ALIGN

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily

Details

Provider
Google Research
Task
Representation learning,Image classification,Image representation
Parameters
820000000.0
Released
2021-06-11
Open weights
No
View model source

Explore

FAQ