Is a caption worth a thousand images? a controlled study for representation learning

S Santurkar, Y Dubois, R Taori, P Liang… - arXiv preprint arXiv …, 2022 - arxiv.org
The development of CLIP [Radford et al., 2021] has sparked a debate on whether language
supervision can result in vision models with more transferable representations than …
Save Cite Cited by 36 Related articles View as HTML

Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning

S Santurkar, Y Dubois, R Taori, P Liang… - arXiv e …, 2022 - ui.adsabs.harvard.edu
The development of CLIP [Radford et al., 2021] has sparked a debate on whether language
supervision can result in vision models with more transferable representations than …
Cite