Correlation-aware Adversarial Domain Adaptation and Generalization

TL;DR

This paper introduces a correlation-aware adversarial framework for domain adaptation and generalization, combining correlation alignment with adversarial learning to better reduce domain discrepancy and improve performance on benchmark datasets.

Contribution

It proposes a novel correlation-aware adversarial approach that integrates correlation alignment with adversarial training for both DA and DG, addressing limitations of existing methods.

Findings

Achieves improved state-of-the-art performance on benchmark datasets.

Effectively reduces domain discrepancy with unlabeled target data.

Enhances domain-agnostic feature learning.

Abstract

Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the domain shift problem where the distribution of the source and target data is different. The task of DG is more challenging than DA as the target data is totally unseen during the training phase in DG scenarios. The current state-of-the-art employs adversarial techniques, however, these are rarely considered for the DG problem. Furthermore, these approaches do not consider correlation alignment which has been proven highly beneficial for minimizing domain discrepancy. In this paper, we propose a correlation-aware adversarial DA and DG framework where the features of the source and target data are minimized using correlation alignment along with adversarial learning. Incorporating the correlation alignment module along with adversarial learning helps to achieve a more domain agnostic model due to the improved ability to reduce domain discrepancy with unlabeled target data more effectively. Experiments on benchmark datasets serve as evidence that our proposed method yields improved state-of-the-art performance.