Enhanced Separable Disentanglement for Unsupervised Domain Adaptation
This work addresses domain adaptation for machine learning applications where labeled data is scarce, representing an incremental improvement over existing disentanglement-based methods.
The paper tackles the problem of domain-invariant features not being discriminative in unsupervised domain adaptation by proposing an enhanced separable disentanglement model, which outperforms state-of-the-art methods on three benchmark datasets, especially in challenging cross-domain tasks.
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.