Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories

TL;DR

This paper introduces a novel unsupervised domain adaptation framework for the challenging scenario of one source domain adapting to multiple target domains with potentially different categories, using model parameter adaptation.

Contribution

It proposes a unique model parameter dictionary adaptation method for 1SmT UDA, differing from existing approaches and enabling privacy-preserving knowledge transfer.

Findings

Outperforms existing methods on three benchmark datasets.

Effectively handles multiple target domains with different categories.

Supports privacy protection through parameter-based knowledge transfer.

Abstract

Unsupervised domain adaptation (UDA) aims to learn the unlabeled target domain by transferring the knowledge of the labeled source domain. To date, most of the existing works focus on the scenario of one source domain and one target domain (1S1T), and just a few works concern the scenario of multiple source domains and one target domain (mS1T). While, to the best of our knowledge, almost no work concerns the scenario of one source domain and multiple target domains (1SmT), in which these unlabeled target domains may not necessarily share the same categories, therefore, contrasting to mS1T, 1SmT is more challenging. Accordingly, for such a new UDA scenario, we propose a UDA framework through the model parameter adaptation (PA-1SmT). A key ingredient of PA-1SmT is to transfer knowledge through adaptive learning of a common model parameter dictionary, which is completely different from existing popular methods for UDA, such as subspace alignment, distribution matching etc., and can also be directly used for DA of privacy protection due to the fact that the knowledge is transferred just via the model parameters rather than data itself. Finally, our experimental results on three domain adaptation benchmark datasets demonstrate the superiority of our framework.