Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation

TL;DR

This paper introduces a joint approach combining domain alignment with discriminative feature learning to improve unsupervised deep domain adaptation, addressing the limitations of existing methods that only minimize distribution discrepancy.

Contribution

It proposes novel instance-based and center-based discriminative feature learning methods that enhance domain-invariant features with better intra-class compactness and inter-class separability.

Findings

Significant performance boost in deep domain adaptation tasks.

Discriminative features improve classification accuracy.

Joint learning approach outperforms existing methods.

Abstract

Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution discrepancy across different domains. Due to the fact that all the domain alignment approaches can only reduce, but not remove the domain shift. Target domain samples distributed near the edge of the clusters, or far from their corresponding class centers are easily to be misclassified by the hyperplane learned from the source domain. To alleviate this issue, we propose to joint domain alignment and discriminative feature learning, which could benefit both domain alignment and final classification. Specifically, an instance-based discriminative feature learning method and a center-based discriminative feature learning method are proposed, both of which guarantee the domain invariant features with better intra-class compactness and inter-class separability. Extensive experiments show that learning the discriminative features in the shared feature space can significantly boost the performance of deep domain adaptation methods.