Unsupervised domain adaptation has garnered a great amount of attention and research in past decades. Among all the deep-based methods, the autoencoder-based approach has achieved sound performance for its fast convergence speed and a no-label requirement. The existing methods of autoencoders just serially connect the features generated by different autoencoders, which poses challenges for discriminative representation learning and which fails to find the real cross-domain features.Unsupervised domain adaptation has garnered a great amount of attention and research in past decades. Among all the deep-based methods, the autoencoder-based approach has achieved sound performance for its fast convergence speed and a no-label requirement. The existing methods of autoencoders just serially connect the features generated by different autoencoders, which poses challenges for discriminative representation learning and which fails to find the real cross-domain features.[#item_full_content]