- python == 3.7.13
- cudatoolkit == 10.1.243
- pytorch ==1.7.1
- torchvision == 0.8.2
- numpy, scikit-learn, PIL, argparse
- Configure the PyTorch environment.
- Download the Office-Home dataset. Configure the data lists in data and the checkpoints in logs.
- Run the code in pseudocal.sh.
@inproceedings{hu2024pseudocalibration,
title={Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation},
author={Dapeng Hu and Jian Liang and Xinchao Wang and Chuan-Sheng Foo},
booktitle={Forty-first International Conference on Machine Learning},
year={2024}
}
- The code is heavily borrowed from TransCal.