Shuhao Cui, Xuan Jin, Shuhui Wang, Yuan He, Qingming Huang
TL;DR本文提出了一种基于启发式搜索的领域不变和领域特定信息建模方法 —— 启发式领域自适应 (HDA)，并通过导出启发式表示约束，提出了一种启发式领域自适应网络 (HDAN)。实验证明，该方法在无监督 DA、多源 DA 和半监督 DA 等任务上均超过了现有最先进方法。
Abstract
In visual domain adaptation (DA), separating the domain-specific
characteristics from the domain-invariant representations is an ill-posed
problem. Existing methods apply different kinds of priors or directly minimize
the domain discrepancy to address this problem, which lack flexibili