slei109/PATNet

Question about PATM

canglangzhige opened this issue · 1 comments

Thanks for your work!
In Section 5.1, you said Since the domain-agnostic metric space is constant, it will be much easier for the downstream segmentation modules to make predictions in such a stable space.
I wonder why it is useful to select such a stable space?
I noticed that TAFT module uses the same idea. However, TAFT also does not explain why it works.

We observe that the dataset (both training and test sets) for CD-FSS task is a bit confusing, can you provide a well-organized training and test set directly used for the CDFSS task? Thank you.