Enhanced Separable Disentanglement for Unsupervised Domain Adaptation

TL;DR

This paper introduces an enhanced separable disentanglement model for unsupervised domain adaptation that improves feature separation and reconstruction, leading to better cross-domain transfer performance.

Contribution

It proposes a novel disentanglement framework with feature separation enhancement and feature reconstruction, addressing limitations of existing methods in domain-invariant feature discrimination.

Findings

Outperforms state-of-the-art methods on three benchmark datasets.

Achieves significant improvements in challenging cross-domain tasks.

Effectively disentangles domain-invariant and domain-specific features.

Abstract

Domain adaptation aims to mitigate the domain gap when transferring knowledge from an existing labeled domain to a new domain. However, existing disentanglement-based methods do not fully consider separation between domain-invariant and domain-specific features, which means the domain-invariant features are not discriminative. The reconstructed features are also not sufficiently used during training. In this paper, we propose a novel enhanced separable disentanglement (ESD) model. We first employ a disentangler to distill domain-invariant and domain-specific features. Then, we apply feature separation enhancement processes to minimize contamination between domain-invariant and domain-specific features. Finally, our model reconstructs complete feature vectors, which are used for further disentanglement during the training phase. Extensive experiments from three benchmark datasets outperform state-of-the-art methods, especially on challenging cross-domain tasks.