Menu

Blog

Apr 25, 2024

MoDE: CLIP Data Experts via Clustering

Posted by in category: futurism

Meta presents MoDE

CLIP Data Experts via Clustering.

The success of contrastive language-image pretraining (CLIP) relies on the supervision from the pairing between images and captions, which tends to be noisy in web-crawled data.


Join the discussion on this paper page.

Comments are closed.