Skip to main contentResource added 
CLIP Cluster Plot

All images in the corpus, semantically clustered with CLIP embeddings and projected onto a grid using the “Just the Clusters” tool.
Full description
A square arrangement of thumbnail images of 1200 derivatives and reproductions of four antique statues scraped from multiple art-historical image archives: Laocoon group, Boy with Thorn, Farnese Hercules, and Apollo Belvedere. The images are clustered according to embeddings produced with the CLIP multimodal model. The clustering almost perfectly separates the four different statues with only a few outliers.
- typeImage
- created on
- file formatjpg
- file size1 MB
- creatorFabian Offert and Peter Bell
- rightsThis image is licensed with a CC BY-SA 4.0 deed.
- rights holderFabian Offert and Peter Bell
Manifold uses cookies
We use cookies to analyze our traffic. Please decide if you are willing to accept cookies from our website. You can change this setting anytime in Privacy Settings.