CLIP

The CLIP model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive.

Data and Resources

Cite this as

A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark (2024). Dataset: CLIP. https://doi.org/10.57702/mxw4bsuu

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2306.00301
Citation
  • https://doi.org/10.1109/ICCV51070.2023.01403
  • https://doi.org/10.48550/arXiv.2312.06716
  • https://doi.org/10.48550/arXiv.2305.05095
Author A. Radford
More Authors
J. W. Kim
C. Hallacy
A. Ramesh
G. Goh
S. Agarwal
G. Sastry
A. Askell
P. Mishkin
J. Clark
Homepage https://arxiv.org/abs/2106.07637