WXinlong / DenseCL

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Have you tried on keypoint matching task?

triangleCZH opened this issue · comments

Since the model is trained on the dense matching loss, it would be natural to evaluate its performance on keypoint matching task and compare with sotas. May I know if you have conducted experiments or have related plan? Thank you!

Hi, we didn't try the keypoint matching task.:)