You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, I'm not consider doing this now. This is an interesting question. I believe this may need more delicate design of augmentations on sample to generate negative pairs for image only contrastive learning.
DINOv2 seems powerful in some applications like CLIP, maybe a similar Alpha-DINOv2 is very useful too
The text was updated successfully, but these errors were encountered: