论文标题
不确定性感知的评估时间序列分类，用于在线手写识别的域转移
Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift
论文作者
论文摘要
对于许多应用，分析机器学习模型的不确定性是必不可少的。尽管不确定性量化（UQ）技术的研究非常先进，但对于计算机视觉应用程序，研究的UQ方法的研究较少。在本文中，我们专注于在线手写识别的模型，这是一种特定类型的时空数据。数据是从传感器增强笔的目标，其目标是对书面字符进行分类的目标。我们基于两种贝叶斯推论，平均高斯（赃物）和深层合奏的两种突出技术，对两种突出的技术进行广泛的评估（数据）和认知（模型）UQ。在对模型的更好理解后，UQ技术可以在组合右手和左撇子作家（一个代表性不足的组）时检测分布数据和域的变化。
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).
