search

GiovanniPasq / DA-Faster-RCNN

Detectron2 implementation of DA-Faster R-CNN, Domain Adaptive Faster R-CNN for Object Detection in the Wild
MIT License
53 stars 10 forks source link

How to implement the source-only comparative experiment part of the original paper in this code？ #16

Closed yzy3314992 closed 6 months ago

yzy3314992 commented 6 months ago

Hello author! Thanks for the code! If I want to implement the "source-only" item in the experimental table of the original paper, how should I modify the uda_train.py file of this code?

GiovanniPasq commented 6 months ago

Hello, from what I've read, I think you should study the problem and the definition of unsupervised domain adaptation more thoroughly. This is the implementation of Da-Faster R-CNN. The source-only experiments correspond to the Faster R-CNN trained with the source domain and tested with the target without using any domain adaptation technique. Regards.