Code release for Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation (ICML 2019)
toy.py: code for reproducing the experiments in the toy datasetdev.py: code for calculating the DEV risk
The dev.py:get_weight can be used to get importance weight, and dev.py:get_dev_risk can be used to get validation risk.
please cite:
@InProceedings{DEV_2019_ICML,
author = {You, Kaichao and Wang, Ximei and Long, Mingsheng and Jordan, Michael I.},
title = {Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation},
booktitle = {International Conference on Machine Learning (ICML)},
month = {June},
year = {2019}
}
