Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation

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 \textit{aligns} the source and the targe-\textit{known} distribution while simultaneously \textit{segregating} the target-\textit{unknown} distribution in the feature alignment procedure. We provide theoretical analyses on the optimized state of the proposed \textit{unknown-aware} feature alignment, so we can guarantee both \textit{alignment} and \textit{segregation} theoretically. Empirically, we evaluate UADAL on the benchmark datasets, which shows that UADAL outperforms other methods with better feature alignments by reporting the state-of-the-art performances.