search

tiancity-NJU / da-faster-rcnn-PyTorch

An unofficial implementation of 'Domain Adaptive Faster R-CNN for Object Detection in the Wild ’
Other
136 stars 37 forks source link

why target-domain pictures for training also need annotations? #27

Open wzh241215 opened 3 years ago

wzh241215 commented 3 years ago

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?

tiancity-NJU commented 3 years ago

You can regard the anntotations of target-domain as the placeholders which are not uesful. You can set them as constant number. It is just for convenience of coding.