Unsupervised Domain Adaptation with Progressive Domain Augmentation

Abstract

Domain adaptation aims to exploit a label-rich source domain for learning classifiers in a different label-scarce target domain. It is particularly challenging when there are significant divergences between the two domains. In the paper, we propose a novel unsupervised domain adaptation method based on progressive domain augmentation. The proposed method generates virtual intermediate domains via domain interpolation, progressively augments the source domain and bridges the source-target domain divergence by conducting multiple subspace alignment on the Grassmann manifold. We conduct experiments on multiple domain adaptation tasks and the results shows the proposed method achieves the state-of-the-art performance.

Certainty Volume Prediction for Unsupervised Domain Adaptation

“…Please note that due to Office-Caltech's average target domain size of only 633 images, a 0.6% difference arises from less than 2 misclassifications per transfer task on average. Therefore, our CVP method can be considered on par with the top performing methods UFAL [37], PrDA [20] and RWA [44].…”