about knowledge transfer about uvtr HOT 6 OPEN

There are only two files in /UVTR/tree/main/projects/configs/uvtr/camera_based/knowledge_distill. l2c and l2cs3.

from uvtr.

In the ranking of the nuScenes list, the NDS of camera is not as good as that of BEVFormer. Does it mean that it is not feasible to transfer point cloud knowledge to images, or the method is wrong?

from uvtr.

Hi @Lotus-95 , for multi-mod setting, you can directly modify the config according to the multi-mod setting here and turn the config model.type to "UVTRKDM".

from uvtr.

Hi @Alexanderisgod , there are different frameworks with different training settings. You can apply the knowledge transfer to BEVFormer, and should also find the improvement. Moreover, there are several methods better than the BEVFormer in the leaderboard. But it doesn't mean BEVFormer is wrong.

from uvtr.

I'm just not sure whether the structural information uncovered by knowledge transfer in your paper can be learned in the Transformer structure in BEVFormer. Or Transformer can learn structural information that is not weaker than knowledge transfer

from uvtr.

Hi @Lotus-95 , for multi-mod setting, you can directly modify the config according to the multi-mod setting here and turn the config model.type to "UVTRKDM".

If I turn the config model.type to "UVTRKDM", how to change the config about teacher*, it seems default to None?

from uvtr.