The existing learning methods usually assume that training data and test data follow the same distribution, while this is not always true. Thus, in many cases the performance of these methods on the test data will be severely degraded. In this paper, we study the problem of unsupervised domain adaptation, where no labeled data in the target domain is available. The proposed method first finds a new representation for both the source and the target domain and then learns a prediction function for the classifier by optimizing an objective function which simultaneously tries to minimize the loss function on the source domain while also maximizes the consistency of manifold (which is based on the nature of data) with the prediction function. We run the proposed method on four types of cross-domain image classification problems and show that the proposed method significantly outperforms several state-of-the-art domain adaptation methods.