Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search

TL;DR

This paper introduces a novel domain adaptation method that maximizes population correlation using neural architecture search to learn flexible, domain-invariant features, outperforming existing methods on benchmark datasets.

Contribution

It proposes a new similarity measure called Population Correlation and integrates neural architecture search to optimize the model architecture for domain adaptation.

Findings

DAMPC-NAS outperforms state-of-the-art DA methods on benchmark datasets.

The proposed PC measure effectively captures domain discrepancy.

Neural architecture search improves model flexibility and performance.

Abstract

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.