Learning Transferable Visual Models
Connecting images and language through contrastive learning, with a path to zero-shot visual recognition.
Radford et al.
The open catalogue
A starting point for understanding AI. Explore the ideas, examine the evidence, and make up your own mind.
2 papers in the starter collection
Connecting images and language through contrastive learning, with a path to zero-shot visual recognition.
Treat an image as a sequence of patches, and revisit the role of convolution in visual recognition.
This is the beginning of the library.
Help us decide what belongs here next.