Title | ||
---|---|---|
Uncertainty-aware Evaluation of Time-series Classification for Online Handwriting Recognition with Domain Shift. |
Abstract | ||
---|---|---|
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). |
Year | Venue | DocType |
---|---|---|
2022 | International Joint Conference on Artificial Intelligence | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andreas Klaß | 1 | 0 | 0.34 |
Sven M. Lorenz | 2 | 0 | 0.34 |
Martin W. Lauer-Schmaltz | 3 | 0 | 0.34 |
David Rügamer | 4 | 0 | 1.01 |
Bernd Bischl | 5 | 0 | 1.01 |
Christopher Mutschler | 6 | 0 | 1.01 |
Felix Ott | 7 | 0 | 1.01 |