Stochastic Classifiers for Unsupervised Domain Adaptation (CVPR2020)

[Paper Link]

Short introduction

This is the implementation for STAR (STochastic clAssifieRs). The main idea for that is to build a distribution over the weights of the classifiers. With that, infinite number of classifiers can be sampled without extra parameters.

Architecture

Citation

If you find this helpful, please cite it.

@InProceedings{Lu_2020_CVPR,
author = {Lu, Zhihe and Yang, Yongxin and Zhu, Xiatian and Liu, Cong and Song, Yi-Zhe and Xiang, Tao},
title = {Stochastic Classifiers for Unsupervised Domain Adaptation},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

Further discussion

If you have any problems, please contact zhihe.lu@surrey.ac.uk or simply write it in the issue session.