Joint predictive model and representation learning for visual domain adaptation

Traditional learning algorithms cannot perform well in scenarios where training data (source domain data) that are used to learn the model have a different distribution with test data (target domain data). The domain adaptation that intends to compensate this problem is an important capability for an intelligent agent. This paper presents a domain adaptation method which learns to adapt the data distribution of the source domain to that of the target domain where no labeled data of the target domain is available (and just unlabeled data are available for the target domain). Our method jointly learns a low dimensional representation space and an adaptive classifier. In fact, we try to find a representation space and an adaptive classifier on this representation space such that the distribution gap between (the marginal and the conditional distribution of) the two domains is minimized and the risk of the adaptive classifier is also minimized. To evaluate the proposed method, we conduct several experiments on image classification datasets. Experimental results verify the superiority of our method to the existing domain adaptation methods and the proposed method outperforms the other methods with a large margin in some of the domain adaptation problems. These results demonstrate the effectiveness of learning the representation space and the adaptive classifier simultaneously.