Awesome
[IJCAI-2023] RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
Prerequisites:
- python == 3.6.8
- pytorch ==1.1.0
- torchvision == 0.3.0
- numpy, scipy, sklearn, PIL, argparse, tqdm
Training:
Execute train_rain.py.
Method:
<img src="figs/frame1.png" width="1000"/> <img src="figs/frame2.png" width="400"/>Results:
<img src="figs/result1.png" width="1000"/> <img src="figs/result2.png" width="1000"/>Citation
If you find this code useful for your research, please cite our paper
@inproceedings{ijcai2023p458,
title = {RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation},
author = {Peng, Qucheng and Ding, Zhengming and Lyu, Lingjuan and Sun, Lichao and Chen, Chen},
booktitle = {Proceedings of the Thirty-Second International Joint Conference on
Artificial Intelligence, {IJCAI-23}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Edith Elkind},
pages = {4118--4126},
year = {2023},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2023/458},
url = {https://doi.org/10.24963/ijcai.2023/458},
}