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?
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?
Please re-open this issue for more discussion.
Originally posted by @JosephKJ in https://github.com/JosephKJ/OWOD/issues/44#issuecomment-851234016
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?