thuml / TCL

Code release for Transferable Curriculum for Weakly-Supervised Domain Adaptation (AAAI2019)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

TCL

Code release for Transferable Curriculum for Weakly-Supervised Domain Adaptation (AAAI2019)

Dataset

Office-31 dataset, with 0.4 label noise

Requirements

  • Python 2.7
  • PyTorch 0.3

Training

bash trainAW.sh for Amazon(0.4 label noise)-> Webcam training
bash trainAD.sh for Amazon(0.4 label noise)-> Dslr training

Citation

If you use this code for your research, please consider citing:

@inproceedings{shu2019transferable,
  title={Transferable Curriculum for Weakly-Supervised Domain Adaptation},
  author={Shu, Yang and Cao, Zhangjie and Long, Mingsheng and Wang, Jianmin},
  year={2019},
  organization={AAAI}
}

Contact

If you have any problems about our code, feel free to contact

or describe your problem in Issues.

About

Code release for Transferable Curriculum for Weakly-Supervised Domain Adaptation (AAAI2019)


Languages

Language:Python 97.1%Language:Shell 2.9%