Structure Consistency and Class Discriminative Feature Learning for Heterogeneous Domain Adaptation

Heterogeneous domain adaptation (HDA), which learns a target classifier using labeled data from different feature and distribution, has shown promising value in knowledge discovery. Yet it is still a challenging problem. Since most of the existing approaches for HDA are in the special case, we propose a generalized method for this problem. We use Principal Components Analysis (PCA) to align the features from source and target domain. Simultaneously, we match the conditional distribution and preserve the local structure, for the purpose of achieving discriminative feature representations. At last, comprehensive experiments verify that our method can significantly outperform state-of-the-art learning methods on several public image datasets.