Any plan for dinov2?

Open twmht opened this issue 2 years ago • 3 comments

DinoV2 has shown remarkable performance on downstream tasks, but its use of Vision Transformer (ViT) is computationally inefficient. Do you have plans to train an efficientVIT version of DinoV2?

Nov 27 '23 04:11 twmht

Hi twmht,

Thank you for your interest. We do have this in our plan. If you want to get informed about our updates, please join our mailing list here or star/watch this repo.

Best, Han

Nov 27 '23 15:11 han-cai

This is awesome! What would be a tentative release date for dinov2?

Dec 11 '23 02:12 JayKarhade