Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Unsupervised Domain Adaptation via Regularized Conditional Alignment

About

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.

Safa Cicek, Stefano Soatto• 2019

Related benchmarks

TaskDatasetResultRank
Image ClassificationOffice-31
Average Accuracy87
261
Domain AdaptationImage-CLEF DA (test)
Average Accuracy88.9
76
Showing 2 of 2 rows

Other info

Follow for update