Domain Discrepancy Measure for Complex Models in Unsupervised Domain Adaptation

TL;DR

This paper introduces a new discrepancy measure called PHD for unsupervised domain adaptation, addressing limitations of existing measures by being more informative, computationally efficient, and applicable to multi-class problems.

Contribution

The paper proposes the paired hypotheses discrepancy (PHD), a novel measure that improves upon existing discrepancy measures for complex models in unsupervised domain adaptation.

Findings

PHD is computationally efficient for deep neural networks.

PHD effectively handles multi-class classification tasks.

Experimental results validate the practical usefulness of PHD.

Abstract

Appropriately evaluating the discrepancy between domains is essential for the success of unsupervised domain adaptation. In this paper, we first point out that existing discrepancy measures are less informative when complex models such as deep neural networks are used, in addition to the facts that they can be computationally highly demanding and their range of applications is limited only to binary classification. We then propose a novel domain discrepancy measure, called the paired hypotheses discrepancy (PHD), to overcome these shortcomings. PHD is computationally efficient and applicable to multi-class classification. Through generalization error bound analysis, we theoretically show that PHD is effective even for complex models. Finally, we demonstrate the practical usefulness of PHD through experiments.