Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence

TL;DR

This paper introduces a novel approach that repurposes domain discriminators to simultaneously learn domain-invariant features and estimate confidence levels for pseudo labels in domain adaptation tasks.

Contribution

It proposes a multi-purposing discriminator that enhances domain adaptation by providing both feature alignment and pseudo label confidence estimation.

Findings

Improved domain adaptation performance with pseudo labeling.

Effective confidence estimation for pseudo labels.

Enhanced feature invariance across domains.

Abstract

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.