Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms have been proposed to compensate for the degradation in performance due to domain shift.

In this paper, author addresses the case when the target domain is unlabeled, requiring unsupervised adaptation. Here, authors extend CORAL: “Correlation Alignment for Unsupervised Domain Adaptation” to learn a nonlinear transformation that aligns correlations of layer activations in deep neural networks (Deep CORAL). Experiments on standard benchmark datasets show state-of-the-art performance.