Kernel subspace alignment for unsupervised domain adaptation

Abstract

A general assumption in pattern recognition is that training samples and testing samples come from the same distribution. However, the accuracy rate of classification will dramatically drop when the assumption is invalid. Domain adaptation tries to alleviate the problem via correcting the mismatch of sample distribution in source and target domains. In this paper, we propose a Kernel Subspace Alignment (KSA) approach for unsupervised domain adaptation. The basic idea of KSA is to extract nonlinear feature separately for both the source and target domain, then align the two feature coordinate systems to make the feature invariant to domain shift. Experimental results show that KSA outperforms competitive approaches for unsupervised domain adaptation.