LanguageGroundedSemseg icon indicating copy to clipboard operation
LanguageGroundedSemseg copied to clipboard

Published 20 hours ago • verified publisher icon RozDavid

Text-supervised Contrastive optimization.

Open yhyang-myron opened this issue 2 years ago • 0 comments

Hi, Could I ask why did you choose this loss as your pre-training step? Did you try some other loss for the pre-training step, such as InfoNCEloss? What's the difference between them?

yhyang-myron avatar Oct 28 '22 10:10 yhyang-myron