Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning. In principle, existing UDA approaches mainly focus on the global distribution alignment between domains while ignoring the intrinsic local distribution properties. Motivated by this observation, we propose an end-to-end structure-conditioned adversarial learning scheme (SCAL) that is able to preserve the intra-class compactness during domain distribution alignment. By using local structures as structure-aware conditions, the proposed scheme is implemented in a structure-conditioned adversarial learning pipeline. The above learning procedure is iteratively performed by alternating between local structures establishment and structure-conditioned adversarial learning. Experimental results demonstrate the effectiveness of the proposed scheme in UDA scenarios.

提出了一种基于结构条件对抗学习方案（SCAL），该方案能够在域分布对齐期间保留内部类紧密性。结合本地结构作为结构感知条件，通过结构条件对抗学习管道实现。实验结果证明了该方案在无监督领域适应方案中的有效性。

通过结构条件对抗学习进行无监督域自适应图像分类