Multi-source Open-Set Deep Adversarial Domain Adaptation

We introduce a novel learning paradigm of multi-source open-set unsupervised domain adaptation (MS-OSDA). Recently, the notion of single-source open-set domain adaptation (SS-OSDA) which considers the presence of previously unseen open-set (unknown) classes in the target-domain in addition to the source-domain closed-set (known) classes has drawn attention. In the SS-OSDA setting, the labeled samples are assumed to be drawn from the same source. Yet, it is more plausible to assume that the labeled samples are distributed over multiple source-domains, but the existing SS-OSDA techniques cannot directly handle this more realistic scenario considering the diversities among multiple source-domains. As a remedy, we propose a novel adversarial learning-driven approach to deal with MS-OSDA. Precisely, we model a shared feature space for all the domains which explicitly mitigates the domain-gap among the source-domains. The adversarial learning strategy is introduced to align the known-class samples from the target-domain with the source data while making the unknown-classes more separable. We validate our method on the Office-31, Office-Home, Office-CalTech, and Digits datasets and find that the proposed model consistently outperforms the baseline and benchmark SS-OSDA approaches.