Tent: Fully Test-Time Adaptation by Entropy Minimization
This is the official project repository for Tent: Fully-Test Time Adaptation by Entropy Minimization by Dequan Wang*, Evan Shelhamer*, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell (ICLR 2021, spotlight).
Please check back soon for our reference code in PyTorch!
Correspondence
Please contact Dequan Wang and Evan Shelhamer at dqwang AT cs.berkeley.edu and shelhamer AT google.com.
Citation
If our fully test-time adaptation setting or tent method are helpful in your research, please cite the paper
Tent: Fully-Test Time Adaptation by Entropy Minimization.
Dequan Wang*, Evan Shelhamer*, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell.
ICLR 2021.
with bibtex
@inproceedings{
wang2021tent,
title={Tent: Fully Test-Time Adaptation by Entropy Minimization},
author={Dequan Wang and Evan Shelhamer and Shaoteng Liu and Bruno Olshausen and Trevor Darrell},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=uXl3bZLkr3c}
}