Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies

doi:doi:10.57702/t6hrskc9

Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies

This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets.

Data and Resources

Original MetadataJSON
The json representation of the dataset with its distributions based on DCAT.
Explore
- Preview
- Download

Cite this as

Zichao Li, Cihang Xie, Ekin Dogus Cubuk (2024). Dataset: Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies. https://doi.org/10.57702/t6hrskc9

DOI retrieved: December 16, 2024

Additional Info

Field	Value
Created	December 16, 2024
Last update	December 16, 2024
Author	Zichao Li
More Authors	Cihang Xie Ekin Dogus Cubuk