CLIP

tags

Transformers, NLP, Computer vision

paper

(Radford et al. 2021)

Architecture

It is an encoder-only model which combines ViT and ResNet to encode images and a transformer for the text encoding.

Bibliography

1. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, et al.. February 26, 2021. February 26, 2021DOI.