Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation. (arXiv:2206.07551v1 [cs.LG])

Web: http://arxiv.org/abs/2206.07551

Open-Set Domain Adaptation (OSDA) assumes that a target domain contains
unknown classes, which are not discovered in a source domain. Existing domain
adversarial learning methods are not suitable for OSDA because distribution
matching with \textit{unknown} classes leads to the negative transfer. Previous
OSDA methods have focused on matching the source and the target distribution by
only utilizing \textit{known} classes. However, this \textit{known}-only
matching may fail to learn the target-\textit{unknown} feature space.
Therefore, we propose Unknown-Aware Domain Adversarial Learning (UADAL), which …

arxiv domain adaptation learning lg open