Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation

TL;DR

This paper revisits subspace alignment for unsupervised domain adaptation, introducing a novel deep learning-based method that improves generalization, reduces data and computational needs, and supports progressive adaptation to new target domains.

Contribution

It proposes a new subspace alignment algorithm that separates feature learning from distribution alignment, enhancing performance and efficiency in unsupervised domain adaptation.

Findings

Competitive performance on standard benchmarks.

Reduced target data and computational requirements.

Effective partial domain adaptation with strong generalization.

Abstract

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their mathematical elegance and tractability, these methods are often found to be ineffective at producing domain-invariant features with complex, real-world datasets. Motivated by the recent advances in representation learning with deep networks, this paper revisits the use of subspace alignment for UDA and proposes a novel adaptation algorithm that consistently leads to improved generalization. In contrast to existing adversarial training-based DA methods, our approach isolates feature learning and distribution alignment steps, and utilizes a primary-auxiliary optimization strategy to effectively balance the objectives of domain invariance and model fidelity. While providing a significant reduction in target data and computational requirements, our subspace-based DA performs competitively and sometimes even outperforms state-of-the-art approaches on several standard UDA benchmarks. Furthermore, subspace alignment leads to intrinsically well-regularized models that demonstrate strong generalization even in the challenging partial DA setting. Finally, the design of our UDA framework inherently supports progressive adaptation to new target domains at test-time, without requiring retraining of the model from scratch. In summary, powered by powerful feature learners and an effective optimization strategy, we establish subspace-based DA as a highly effective approach for visual recognition.