GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation

Xinhong Ma, Tianzhu Zhang, Changsheng Xu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To bridge source and target domains for domain adaptation, there are three important types of information including data structure, domain label, and class label. Most existing domain adaptation approaches exploit only one or two types of the above information and cannot make them complement and enhance each other. Different from existing methods, we propose an end-to-end Graph Convolutional Adversarial Network (GCAN) for unsupervised domain adaptation by jointly modeling data structure, domain
more » ... a structure, domain label, and class label in a unified deep model. The proposed GCAN model enjoys several merits. First, to the best of our knowledge, this is the first work to model the three kinds of information jointly in a deep model for unsupervised domain adaptation. Second, the proposed model has designed three effective alignment mechanisms including structureaware alignment, domain alignment, and class centroid alignment, which can learn domain-invariant and semantic representations effectively to reduce the domain discrepancy for domain adaptation. Extensive experimental results on five standard benchmarks demonstrate that the proposed GCAN algorithm performs favorably against state-of-theart unsupervised domain adaptation methods.
doi:10.1109/cvpr.2019.00846 dblp:conf/cvpr/MaZX19 fatcat:jqlykvdghbelvllzbcaqdbzvoa