papers AI Learner
The Github is limit! Click to go to the new site.

Unsupervised Domain Adaptation via Regularized Conditional Alignment

2019-05-26
Safa Cicek, Stefano Soatto

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.10885

PDF

http://arxiv.org/pdf/1905.10885


Similar Posts

Comments