You're currently viewing an old version of this dataset. To see the current version, click here.

FLIP: A Method for Reducing Computation in Contrastive Language-Image Pre-training

This paper proposes a method called FLIP, which masks half or more patches of the training images to reduce computation by 2x and allow for the use of larger batch sizes.

Data and Resources

Cite this as

Xi Chen, Xiao Wang, Soravit Changpinyo (2024). Dataset: FLIP: A Method for Reducing Computation in Contrastive Language-Image Pre-training. https://doi.org/10.57702/n67htx19

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Xi Chen
More Authors
Xiao Wang
Soravit Changpinyo