Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift
This work addresses uncertainty-aware evaluation for spatio-temporal data in handwriting recognition, which is incremental as it applies existing UQ methods to a less-studied domain.
The paper tackled the problem of evaluating uncertainty quantification (UQ) methods for online handwriting recognition under domain shift, specifically combining data from right-handed and left-handed writers, and found that UQ techniques like SWAG and Deep Ensembles can detect out-of-distribution data and domain shifts.
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).