Deep CORAL: Correlation Alignment for Deep Domain Adaptation

6 Jul 2016  ·  Baochen Sun, Kate Saenko ·

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.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Domain Generalization NICO Animal CORAL (Resnet-18) Accuracy 80.27 # 4
Domain Generalization NICO Vehicle CORAL (Resnet-18) Accuracy 71.64 # 5


No methods listed for this paper. Add relevant methods here