Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources. (arXiv:2201.01003v1 [cs.LG])

While Unsupervised Domain Adaptation (UDA) algorithms, i.e., there are only
labeled data from source domains, have been actively studied in recent years,
most algorithms and theoretical results focus on Single-source Unsupervised
Domain Adaptation (SUDA). However, in the practical scenario, labeled data can
be typically collected from multiple diverse sources, and they might be
different not only from the target domain but also from each other. Thus,
domain adapters from multiple sources should not be modeled in the same way.
Recent …

arxiv classification distribution