Transfer Learning with Joint Distribution Adaptation and Maximum Margin Criterion

Transfer learning aims to transfer knowledge from the labelled source domain data to build a good classifier for the target domain data which has few labels or none. Existing feature-based transfer learning methods seek to transform the data to a new feature space under which the distribution discrepancy is reduced. However, data in different classes may not be easy to be separated in the new feature representation. Therefore, a modified transfer learning algorithm with Joint Distribution Adaptation (JDA) and Maximum Margin Criterion (MMC) is put forward in this paper, which we call MMC-JDA for short. MMC-JDA is aimed at minimizing the distribution discrepancy between two domains and maximizing the separability of each class at the same time. Comparative experiments on 16 cross-domain public image datasets show that MMC-JDA is effective and performs better than several common transfer learning methods.