Certainty Volume Prediction for Unsupervised Domain Adaptation

TL;DR

This paper introduces a novel uncertainty-aware approach for unsupervised domain adaptation that models uncertainty as a multivariate Gaussian in feature space, leading to improved generalization and state-of-the-art results.

Contribution

It proposes a new uncertainty modeling method in feature space for UDA, enhancing classifier robustness and generalization.

Findings

Achieves state-of-the-art results on UDA datasets.

Uncertainty measure correlates with existing quantifications.

Improves decision boundary smoothing and generalization.

Abstract

Unsupervised domain adaptation (UDA) deals with the problem of classifying unlabeled target domain data while labeled data is only available for a different source domain. Unfortunately, commonly used classification methods cannot fulfill this task adequately due to the domain gap between the source and target data. In this paper, we propose a novel uncertainty-aware domain adaptation setup that models uncertainty as a multivariate Gaussian distribution in feature space. We show that our proposed uncertainty measure correlates with other common uncertainty quantifications and relates to smoothing the classifier's decision boundary, therefore improving the generalization capabilities. We evaluate our proposed pipeline on challenging UDA datasets and achieve state-of-the-art results. Code for our method is available at https://gitlab.com/tringwald/cvp.