mlsanityData to 7 Oct 2026

Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift

arXiv 2206.08640 ↗First posted 17 Jun 2022cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

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).

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 19 of its 43 references that are in the map. First posted on arXiv 17 Jun 2022.

Builds on

19 of 43 references.

References · 19

  1. 2017On Calibration of Modern Neural Networkscited by 4,860
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  4. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  5. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  6. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  8. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  9. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  10. 2021Towards Causal Representation Learningcited by 207
  11. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  12. 2016Correlation Alignment for Unsupervised Domain Adaptationcited by 146
7 more
  1. 2018Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adamcited by 131
  2. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
  3. 2020Time Series Domain Adaptation via Sparse Associative Structure Alignmentcited by 51
  4. 2021Quantifying Uncertainty in Deep Spatiotemporal Forecastingcited by 48
  5. 2022Domain Adaptation for Time-Series Classification to Mitigate Covariate Shiftcited by 24
  6. 2022Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Penscited by 13
  7. 2021STUaNet: Understanding uncertainty in spatiotemporal collective human mobilitycited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 0; 2026: 3.

7 papers.

  1. 2024Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learningcited by 13
  2. 2024Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Datacited by 12
  3. 2024Evaluating ML Robustness in GNSS Interference Classification, Characterization & Localizationcited by 11
  4. 2026Mixture-of-experts for handwriting trajectory reconstruction from IMU sensorscited by 1
  5. 2026Online Handwriting Trajectory Reconstruction from Kinematic Sensors using Temporal Convolutional Networkcited by 1
  6. 2023Representation Learning for Tablet and Paper Domain Adaptation in Favor of Online Handwriting Recognitioncited by 0
  7. 2026CPDA: Class-Conditional Path Distribution Alignment for Unsupervised Time-Series Domain Adaptationcited by 0