Deep Feature Registration for Unsupervised Domain Adaptation
This addresses domain adaptation for machine learning applications where labeled data is scarce, but it appears incremental as it builds on existing alignment methods.
The paper tackles the problem of aligning source and target features in unsupervised domain adaptation by proposing a deep feature registration model that uses histogram matching and pseudo label refinement, achieving new state-of-the-art performance on multiple benchmarks.
While unsupervised domain adaptation has been explored to leverage the knowledge from a labeled source domain to an unlabeled target domain, existing methods focus on the distribution alignment between two domains. However, how to better align source and target features is not well addressed. In this paper, we propose a deep feature registration (DFR) model to generate registered features that maintain domain invariant features and simultaneously minimize the domain-dissimilarity of registered features and target features via histogram matching. We further employ a pseudo label refinement process, which considers both probabilistic soft selection and center-based hard selection to improve the quality of pseudo labels in the target domain. Extensive experiments on multiple UDA benchmarks demonstrate the effectiveness of our DFR model, resulting in new state-of-the-art performance.