Hi @marckatzenmaier,
Thanks very much for pointing this out.
This is indeed a bug. Instead of iterating over all the individual binary instance masks of void segments, this loop only runs once on the total binary mask of all void objects. So instead of matching predicted segments with void segments, this part of the code tries to match predicted segments with the union of all void segments, which probably never happens.

So at the end of the day, segments predicted for void objects are not ignored (though they should be), resulting in "false FP" (false positives that shouldn't be false positives).
This artificially reduces the RQ value and thus the PQ score.

I think this line should be
*torch.unique(instance_true[batch_idx]*void_mask, return_counts=True).

This is fixed now.
I re-evaluated the models on PASTIS with the new code and the bug fix results in a ~2-3pt PQ increase thanks to the reduced number of False Positives.

Facing issue with :
from utils.dataset import ijgiDataset as Dataset
no module error in Main_SITSMamba.py
Possible fix please @VSainteuf @marckatzenmaier

Hi @clotilda-0 I don't think your issue refers to the utae-paps repository as it does not contain an ijgiDataset nor a Main_SITSMamba.py script.