Often domain adaptation is performed using a discriminator (domain classifier) to learn domain-invariant feature representations so that a classifier trained on labeled source data will generalize well to unlabeled target data. A line of research stemming from semi-supervised learning uses pseudo labeling to directly generate "pseudo labels" for the unlabeled target data and trains a classifier on the now-labeled target data, where the samples are selected or weighted based on some measure of confidence. In this paper, we propose multi-purposing the discriminator to not only aid in producing domain-invariant representations but also to provide pseudo labeling confidence.
@article{arxiv.1907.07802,
title = {Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence},
author = {Garrett Wilson and Diane J. Cook},
journal= {arXiv preprint arXiv:1907.07802},
year = {2019}
}