mlsanityData to 7 Oct 2026

Robust Augmentation for Multivariate Time Series Classification

arXiv 2201.11739 ↗First posted 27 Jan 2022cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Neural networks are capable of learning powerful representations of data, but they are susceptible to overfitting due to the number of parameters. This is particularly challenging in the domain of time series classification, where datasets may contain fewer than 100 training examples. In this paper, we show that the simple methods of cutout, cutmix, mixup, and window warp improve the robustness and overall performance in a statistically significant way for convolutional, recurrent, and self-attention based architectures for time series classification. We evaluate these methods on 26 datasets from the University of East Anglia Multivariate Time Series Classification (UEA MTSC) archive and analyze how these methods perform on different types of time series data.. We show that the InceptionTime network with augmentation improves accuracy by 1% to 45% in 18 different datasets compared to without augmentation. We also show that augmentation improves accuracy for recurrent and self attention based architectures.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 27 Jan 2022.

Builds on

20 of 25 references.

References · 20

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  3. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  4. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  5. 2018Deep learning for time series classification: a reviewcited by 575
  6. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
  7. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
  8. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  9. 2018The UEA multivariate time series classification archive, 2018cited by 330
  10. 2020Time Series Data Augmentation for Deep Learning: A Surveycited by 225
  11. 2020Benchmarking Multivariate Time Series Classification Algorithmscited by 145
  12. 2017LSTM Fully Convolutional Networks for Time Series Classificationcited by 135
8 more
  1. 2020An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networkscited by 128
  2. 2017Dataset Augmentation in Feature Spacecited by 124
  3. 2017Attend and Diagnose: Clinical Time Series Analysis using Attention Modelscited by 105
  4. 2019Self-attention for raw optical Satellite Time Series Classificationcited by 75
  5. 2020The Canonical Interval Forest (CIF) Classifier for Time Series Classificationcited by 48
  6. 2020Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentationcited by 31
  7. 2016Quantifying the vanishing gradient and long distance dependency problem in recursive neural networks and recursive LSTMscited by 21
  8. 2021Predictive Maintenance for General Aviation Using Convolutional Transformerscited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2023Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Datacited by 3
  2. 2024Time Series Viewmakers for Robust Disruption Predictioncited by 1
  3. 2022An Empirical Evaluation of Multivariate Time Series Classification with Input Transformation across Different Dimensionscited by 0
  4. 2025Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentationcited by 0