Deep CORAL: Correlation Alignment for Deep Domain Adaptation

TL;DR

Deep CORAL introduces a simple yet effective method for unsupervised domain adaptation by aligning second-order statistics of deep neural network features, significantly improving cross-domain generalization.

Contribution

We extend CORAL to learn nonlinear transformations for deep features, achieving state-of-the-art results in unsupervised domain adaptation.

Findings

Deep CORAL outperforms existing methods on benchmark datasets.

Nonlinear correlation alignment improves adaptation accuracy.

The approach is computationally efficient and easy to implement.

Abstract

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.