In this paper, we formulate a novel unified person re-identification architecture called Unsupervised Joint Attention-Attribute Network (UJ-AAN). The proposed model adopts multi-branch structure to carry out multi-task heterogeneous learning for pedestrians at different levels. Our model is used for joint learning of attention selection and high-level semantic attributes to minimize the distance between different viewpoints of the same person by designing a bilinear feature aggregation module. Furthermore, we introduce attribute-related learning scheme to ensure the domain adaptability of UJ-AAN model in unlabeled domain.