Conditional Support Alignment for Domain Adaptation with Label Shift

no code implementations • 29 May 2023 • Anh T Nguyen, Lam Tran, Anh Tong, Tuan-Duy H. Nguyen, Toan Tran

In this paper, we propose a novel conditional adversarial support alignment (CASA) whose aim is to minimize the conditional symmetric support divergence between the source's and target domain's feature representation distributions, aiming at a more helpful representation for the classification task.

Unsupervised Domain Adaptation