Correlated Adversarial Joint Discrepancy Adaptation Network

TL;DR

This paper introduces CAJNet, a novel domain adaptation method that minimizes joint discrepancy using correlated labels, improving classification accuracy across domains without relying solely on marginal features.

Contribution

The paper proposes CAJNet, which aligns joint distributions with correlated labels and introduces a top-$oldsymbol{ extbf{K}}$ correlated label metric for better parameter tuning.

Findings

Significant accuracy improvements on benchmark datasets.

Effective joint distribution alignment with correlated labels.

Robust parameter tuning using the top-$oldsymbol{ extbf{K}}$ label metric.

Abstract

Domain adaptation aims to mitigate the domain shift problem when transferring knowledge from one domain into another similar but different domain. However, most existing works rely on extracting marginal features without considering class labels. Moreover, some methods name their model as so-called unsupervised domain adaptation while tuning the parameters using the target domain label. To address these issues, we propose a novel approach called correlated adversarial joint discrepancy adaptation network (CAJNet), which minimizes the joint discrepancy of two domains and achieves competitive performance with tuning parameters using the correlated label. By training the joint features, we can align the marginal and conditional distributions between the two domains. In addition, we introduce a probability-based top-$\mathcal{K}$ correlated label ($\mathcal{K}$-label), which is a powerful indicator of the target domain and effective metric to tune parameters to aid predictions. Extensive experiments on benchmark datasets demonstrate significant improvements in classification accuracy over the state of the art.