why target-domain pictures for training also need annotations?
wzh241215 opened this issue · comments
why target-domain pictures for training also need annotations?Target-domain pictures' annotations in real world need much manual work and time,if training needs those annotations,how to adptive real world?
hey, did u get any insight on this ? the paper also mentions target domain with unlabeled images.
I am also looking for an explanation and hope to get an answer to my issue: yuhuayc/sa-da-faster#5 (improved scale-aware version of this model).