Deep CORAL: Correlation Alignment for Deep Domain Adaptation
This addresses domain adaptation for machine learning models when labeled target data is unavailable, though it is incremental as it builds on the existing CORAL method.
The paper tackles the problem of domain shift in deep neural networks when the target domain is unlabeled, by extending CORAL to learn a nonlinear transformation that aligns correlations of layer activations, achieving state-of-the-art performance on standard benchmarks.
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, we address the case when the target domain is unlabeled, requiring unsupervised adaptation. CORAL is a "frustratingly easy" unsupervised domain adaptation method that aligns the second-order statistics of the source and target distributions with a linear transformation. Here, we extend CORAL 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.