Unsupervised Domain Adaptation via Regularized Conditional Alignment
This addresses domain shift problems in machine learning, but appears incremental as it builds on existing alignment methods.
The paper tackles unsupervised domain adaptation by training a shared embedding to align joint distributions of inputs and outputs, making classifiers domain-agnostic, and reports improved performance on unannotated domains through adversarial regularization.
We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the marginal distributions of the domain are aligned, but the labels as well. We propose a novel objective function that encourages the class-conditional distributions to have disjoint support in feature space. We further exploit adversarial regularization to improve the performance of the classifier on the domain for which no annotated data is available.