Mixed Set Domain Adaptation
This addresses domain adaptation challenges for scenarios where source data is mixed across domains, which is incremental but relevant for real-world applications.
The paper tackles the problem of domain adaptation when source categories come from different domains, proposing Mixed Set Domain Adaptation (MSDA) and a feature element-wise weighting method to reduce distribution discrepancies, with experimental results showing its effectiveness.
In the settings of conventional domain adaptation, categories of the source dataset are from the same domain (or domains for multi-source domain adaptation), which is not always true in reality. In this paper, we propose \textbf{\textit{Mixed Set Domain Adaptation} (MSDA)}. Under the settings of MSDA, different categories of the source dataset are not all collected from the same domain(s). For instance, category $1\sim k$ are collected from domain $α$ while category $k+1\sim c$ are collected from domain $β$. Under such situation, domain adaptation performance will be further influenced because of the distribution discrepancy inside the source data. A feature element-wise weighting (FEW) method that can reduce distribution discrepancy between different categories is also proposed for MSDA. Experimental results and quality analysis show the significance of solving MSDA problem and the effectiveness of the proposed method.