Extending Interpolation Consistency Training for Unsupervised Domain Adaptation

Interpolation consistency training (ICT) is a semi-supervised learning method that encourages predictions of interpolated samples to be consistent with the interpolation of predictions of the corresponding original samples. It has achieved highly impressive results on semi-supervised learning benchmarks, but has not been evaluated in domain adaptation settings where the distributions of labeled and unlabeled data are different. We extend the ICT principle for domain adaptation tasks, by combining ICT with a gradient reversal mechanism that accounts for the domain shift in an adversarial manner. We show that ICT alone is not sufficient for handling the distribution shift and even deteriorates the performance, but the proposed method achieves good performance on visual domain adaptation benchmarks.