Bi-Directional Generation for Unsupervised Domain Adaptation


  • Guanglei Yang Harbin Institue of Technology
  • Haifeng Xia Indiana University-Purdue University
  • Mingli Ding Harbin Institute of Technology
  • Zhengming Ding Indiana University-Purdue University



Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. The conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. To balance the mitigation of domain gap and the preservation of the inherent structure, we propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains. Specifically, two cross-domain generators are employed to synthesize one domain conditioned on the other. The performance of our proposed method can be further enhanced by the consistent classifiers and the cross-domain alignment constraints. We also design two classifiers which are jointly optimized to maximize the consistency on target sample prediction. Extensive experiments verify that our proposed model outperforms the state-of-the-art on standard cross domain visual benchmarks.




How to Cite

Yang, G., Xia, H., Ding, M., & Ding, Z. (2020). Bi-Directional Generation for Unsupervised Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 6615-6622.



AAAI Technical Track: Machine Learning