.png){kind=icon}
.png){kind=icon}
Return
Structure-conditioned adversarial learning for unsupervised domain adaptation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.04.094.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.(c) 2022 Published by Elsevier B.V.
Keywords:
Unsupervised domain adaptation
Image classification
Adversarial learning
Clustering