Closed xuanlinli17 closed 1 year ago
Hi Xuanlin!
Thanks for your interest in our work!
Admittedly, the label_offset
strategy is quite complicated and for sure, can be improved. You are right. You need to take special provisions in order to make it work for ScanNet200. Here, we take care of the floor class problem.
Best, Jonas
During the data collation process here, the code subtracts
label_offset
from the remapped semantic id (i.e. the semantic id obtained after_remap_from_zero
in here) and clamps the resulting semantic id to be at least zero. During the evaluation process here, the code addslabel_offset
back to the semantic id.However, this poses an issue for Scannet200 since its ignored remapped semantic ids are
[0,2]
withlabel_offset=2
(see here). In Scannet200,0
in the remapped semantic id corresponds to the wall,1
the chair, and2
the floor. When performing evaluation, the1
of the chair will become0
after subtractinglabel_offset
and then clamping to be at least zero. It will then become2
during evaluation after addinglabel_offset
back to0
, which causes the floor class to correspond to the chair class.