Learning Sampling Policies for Domain Adaptation

TL;DR

This paper proposes a deep Q-learning approach to learn sampling policies for semi-supervised domain adaptation, improving classifier accuracy by intelligently selecting target domain data.

Contribution

It introduces a novel method that learns sampling policies using deep Q-learning to enhance semi-supervised domain adaptation performance.

Findings

Learned sampling policies outperform baselines in accuracy

Constructed labeled sets improve classifier performance

Method effective across different visual classification tasks

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.