Deep Nonlinear Feature Coding for Unsupervised Domain Adaptation

Abstract

Deep feature learning has recently emerged with demonstrated effectiveness in domain adaptation. In this paper, we propose a Deep Nonlinear Feature Coding framework (DNFC) for unsupervised domain adaptation. DNFC builds on the marginalized stacked denoising autoencoder (mSDA) to extract rich deep features. We introduce two new elements to mSDA: domain divergence minimization by Maximum Mean Discrepancy (MMD), and nonlinear coding by kernelization. These two elements are essential for domain adaptation as they ensure the extracted deep features to have a small distribution discrepancy and encode data nonlinearity. The effectiveness of DNFC is verified by extensive experiments on benchmark datasets. Specifically, DNFC attains much higher prediction accuracy than state-of-the-art domain adaptation methods. Compared to its basis mSDA, DNFC is able to achieve remarkable prediction improvement and meanwhile converges much faster with a small number of stacked layers.