Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search
This addresses the problem of domain shift in machine learning for researchers and practitioners, but it is incremental as it builds on existing distance-based methods by adding a new similarity measure and architecture search.
The paper tackled domain adaptation by proposing a new similarity function, Population Correlation (PC), to measure domain discrepancy and introduced DAMPC-NAS, which combines this with neural architecture search to learn domain-invariant features, achieving better results than state-of-the-art methods on benchmark datasets like Office-31, Office-Home, and VisDA-2017.
In Domain Adaptation (DA), where the feature distributions of the source and target domains are different, various distance-based methods have been proposed to minimize the discrepancy between the source and target domains to handle the domain shift. In this paper, we propose a new similarity function, which is called Population Correlation (PC), to measure the domain discrepancy for DA. Base on the PC function, we propose a new method called Domain Adaptation by Maximizing Population Correlation (DAMPC) to learn a domain-invariant feature representation for DA. Moreover, most existing DA methods use hand-crafted bottleneck networks, which may limit the capacity and flexibility of the corresponding model. Therefore, we further propose a method called DAMPC with Neural Architecture Search (DAMPC-NAS) to search the optimal network architecture for DAMPC. Experiments on several benchmark datasets, including Office-31, Office-Home, and VisDA-2017, show that the proposed DAMPC-NAS method achieves better results than state-of-the-art DA methods.