ShijieVVu

> I understand that is the reason we generally use the negative branch in the focal loss. What I don't understand is how you do that in your implementation, since...

The good thing of focal cost is that it is very sensitive when p is close to 0 or 1, meaning class will be matched better in later stages.

in maptr, inter_references and outputs_pts_coords and exactly the same. in maptrv2, inter_references and outputs_pts_coords_one2one are exactly the same.