confused about the reg loss considering unknown proposals
TabGuigui opened this issue · 0 comments
TabGuigui commented
The proposals that are auto-labelled as unknowns are used only in the contrastive clustering. It is used to learn the classification/regression head. Does this resolve the confusion?
Please re-open this issue for more discussion.
Originally posted by @JosephKJ in #44 (comment)
hi there,
The proposals that are auto-labelled as unknowns are still used to train the regression head in the code? Is there something improper that the unknown proposals have a corresponding gt boxes to regress?