Skip to content

Domain Adaptation with Dynamic Open-Set Targets

Notifications You must be signed in to change notification settings

junwu6/OuterAdapter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

OuterAdapter

An implementation for "Domain Adaptation with Dynamic Open-Set Targets" (KDD'22) [Paper].

Environment Requirements

The code has been tested under Python 3.6.5. The required packages are as follows:

  • numpy==1.18.1
  • sklearn==0.22.1
  • scikit-image==0.16.2
  • torch==1.4.0
  • torchvision==0.5.0

Data Sets

We used the following data sets in our experiments:

Run the Codes

For dynamic open-set domain adaptation on Office-Home/Office-31/Syn2Real-O, please run

python main.py

Acknowledgement

This is the latest source code of OuterAdapter. If you find that it is helpful for your research, please consider to cite our paper:

@inproceedings{wu2022domain,
  title={Domain Adaptation with Dynamic Open-Set Targets},
  author={Wu, Jun and He, Jingrui},
  booktitle={Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  pages={2039--2049},
  year={2022}
}

Releases

No releases published

Packages

No packages published

Languages