AI Paper Atlas

Research map / Time series / Foundation models for time series

Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning

Berken Utku Demirel, Christian Holz

NeurIPS 2023 · Time series › Foundation models for time series · approach: Time series representation learning · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use proposed phase/magnitude mixup instead of linear mixup (ablation)Ours (tailored mixup + SimCLR) · UCIHARaccuracy: 83.09 -> 91.60Improved
use proposed phase/magnitude mixup instead of linear mixup (ablation)Ours (tailored mixup + SimCLR) · USCaccuracy: 45.10 -> 60.13Improved
use proposed phase/magnitude mixup instead of linear mixup (ablation)Ours (tailored mixup + SimCLR) · DaLiaMAE: 24.11 -> 10.57Improved
use proposed phase/magnitude mixup instead of linear mixup (ablation)Ours (tailored mixup + SimCLR) · IEEE SPC12MAE: 20.45 -> 16.26Improved
use proposed phase/magnitude mixup instead of linear mixup (ablation)Ours (tailored mixup + SimCLR) · ChapmanAUC: 86.30 -> 95.90Improved
sample mixing coefficients by latent-space distance (ablation)Ours (tailored mixup + SimCLR) · UCIHARaccuracy: 80.86 -> 91.60Improved
sample mixing coefficients by latent-space distance (ablation)Ours (tailored mixup + SimCLR) · HHARaccuracy: 87.53 -> 88.05Improved
sample mixing coefficients by latent-space distance (ablation)Ours (tailored mixup + SimCLR) · IEEE SPC22MAE: 16.01 -> 12.25Improved
sample mixing coefficients by latent-space distance (ablation)Ours (tailored mixup + SimCLR) · DaLiaMAE: 11.10 -> 10.57 (MAE); RMSE 20.13 -> 20.37Mixed
sample mixing coefficients by latent-space distance (ablation)Ours (tailored mixup + SimCLR) · ChapmanAUC: 95.98 -> 95.90No clear effect
sample mixing coefficients by latent-space distance (ablation)Ours (tailored mixup + SimCLR) · CPSC2018AUC: 80.67 -> 85.30Improved
use tailored mixup in contrastive learning instead of DACL hidden-representation mixupSimCLR · UCIHARaccuracy: 73.12 -> 91.60Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy