Tackling unsupervised multi-source domain adaptation with optimism and consistency

It has been known for a while that the problem of multi-source domain adaptation can be regarded as single source task where corresponds to mixture original domains. Nonetheless, how adjust distribution weights remains an open question. Moreover, most existing work on this topic focuses only minimizing error domains and achieving domain-invariant representations, which is insufficient ensure low target domain. In work, we present novel framework addresses both problems beats current state art by using mildly optimistic objective function consistency regularization samples.