A Self-Paced Category-Aware Approach For Unsupervised Adaptation Networks

The success of deep neural networks usually relies on a large number of labeled training samples, which unfortunately are not easy to obtain in practice. Unsupervised domain adaptation focuses on the problem where there is no labeled data in the target domain. In this paper, we propose a novel deep unsupervised domain adaptation method that learns transferable features. Different from most existing methods, it attempts to learn a better domain-invariant feature representation by performing a category-wise adaptation to match the conditional distributions of samples with respect to each category. A self-paced learning strategy is used to bring the awareness of label information gradually, which makes the category-wise adaptation feasible even if the labels are unavailable in target domain. Then, we give detailed theoretical analysis to explain how the better performance is obtained. The experimental results show that our method outperforms the current state of the arts on standard domain adaptation datasets.