For many applications, analyzing the uncertainty of a machine learning model is indispensable. While research of uncertainty quantification (UQ) techniques is very advanced for computer vision applications, UQ methods for spatio-temporal data are less studied. In this paper, we focus on models for online handwriting recognition, one particular type of spatio-temporal data. The data is observed from a sensor-enhanced pen with the goal to classify written characters. We conduct a broad evaluation of aleatoric (data) and epistemic (model) UQ based on two prominent techniques for Bayesian inference, Stochastic Weight Averaging-Gaussian (SWAG) and Deep Ensembles. Next to a better understanding of the model, UQ techniques can detect out-of-distribution data and domain shifts when combining right-handed and left-handed writers (an underrepresented group).
@article{arxiv.2206.08640,
title = {Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift},
author = {Andreas Klaß and Sven M. Lorenz and Martin W. Lauer-Schmaltz and David Rügamer and Bernd Bischl and Christopher Mutschler and Felix Ott},
journal= {arXiv preprint arXiv:2206.08640},
year = {2024}
}