Skip to content

Unsupervised Domain Adaptation without Source Data by Casting a BAIT

Notifications You must be signed in to change notification settings

Albert0147/BAIT_SFUDA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

BAIT_SFUDA

Code (pytorch) for 'Unsupervised Domain Adaptation without Source Data by Casting a BAIT' on VisDA. If for Office-Home and Office-31, please use learning rate 10 times larger.

TL;DR: We extend MCD to source-free domain adaptation.

Preliminary

You need to download the VisDA dataset.

Our codes are using PyTorch 1.3.1, torchvision 0.4.2 (python 3.7.6). The experiments are conducted on one GPU (RTX6000).

Training and evaluation

  1. First training model on the source data.

python train_source.py

  1. Then adapting source model to target domain, with only the unlabeled target data.

python train_target.py

Results in paper

VisDA

The result of SHOT is from the ICML camera-ready version.

Acknowledgement

The codes are based on SHOT (ICML 2020, also source-free).

About

Unsupervised Domain Adaptation without Source Data by Casting a BAIT

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages