Self-Supervised Domain Adaptation with Consistency Training

Repository for the paper "Self-Supervised Domain Adaptation with Consistency Training".

@inproceedings{ss-da-consistency:2019,
  title={Self-Supervised Domain Adaptation with Consistency Training},
  author={L. Xiao, J. Xu, D. Zhao etal},
  booktitle={ICPR},
  year={2020}
}

Requirements

• python3.5+

• pytorch 1.0+

Pretrained models

• caffenet

Prepare dataset

• Digits

• PACS

• Image-clef

• Office-31

• Office-Home

• VLCS

Running experiments

The configuration files for each experiment can be found at config/ folder.

For example:

python3 main.py --config configs/<experiment>.yaml --seed <random_seed>

References

[1] J. Xu, L. Xiao, A. M. Lopez. Self-supervised domain adaptation for computer vision tasks. IEEE Access, 2019.

[2] F. M. Carlucci, A. D’Innocente, S. Bucci, B. Caputo, and T. Tommasi. Domain generalization by solving jigsaw puzzles. In CVPR, 2019.