English

Learning Sampling Policies for Domain Adaptation

Computer Vision and Pattern Recognition 2018-05-22 v1 Machine Learning

Abstract

We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning. The core idea is to consider the predictions of a source domain network on target domain data as noisy labels, and learn a policy to sample from this data so as to maximize classification accuracy on a small annotated reward partition of the target domain. Our experiments show that learned sampling policies construct labeled sets that improve accuracies of visual classifiers over baselines.

Keywords

Cite

@article{arxiv.1805.07641,
  title  = {Learning Sampling Policies for Domain Adaptation},
  author = {Yash Patel and Kashyap Chitta and Bhavan Jasani},
  journal= {arXiv preprint arXiv:1805.07641},
  year   = {2018}
}
R2 v1 2026-06-23T02:01:27.340Z