AI Paper Atlas

Research map / Time series / Foundation models for time series

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

Zhen Liu, Peitian Ma, Dongliang Chen, Wenbin Pei, Qianli Ma

NeurIPS 2023 · Time series › Foundation models for time series · approach: Time series classification · 4 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
remove cross-scale fusion (ablation)Scale-teaching · UniMiB-SHAR Sym 50%accuracy (%): 73.32 -> 81.31Improved
remove cross-scale fusion (ablation)Scale-teaching · HAR Sym 50%accuracy (%): 88.47 -> 90.17Improved
use only a single scale instead of multi-scale (ablation)Scale-teaching · UniMiB-SHAR Asym 40%accuracy (%): 60.32 -> 70.68Improved
add graph-learning label correction (ablation)Scale-teaching · HAR Sym 50%accuracy (%): 88.06 -> 90.17Improved
add momentum embedding stabilization (ablation)Scale-teaching · UniMiB-SHAR Sym 50%accuracy (%): 80.57 -> 81.31Improved
add dynamic threshold for pseudo-label selection (ablation)Scale-teaching · UniMiB-SHAR Sym 50%accuracy (%): 77.42 -> 81.31Improved
add cross-scale fusion to coarse scale classifier (ablation)Scale-teaching · UCR 128 Sym 20%avg accuracy (%): 28.17 -> 68.70Improved
add cross-scale fusion to fine scale classifier (ablation)Scale-teaching · UCR 128 Sym 20%avg accuracy (%): 65.13 -> 59.67Hurt
Scale-teaching vs CULCU under Asym 40% noiseScale-teaching · HARaccuracy (%): 87.22 -> 89.62Improved
Scale-teaching vs CULCU under Sym 50% noiseScale-teaching · HARaccuracy (%): 89.91 -> 90.17No clear effect
Scale-teaching vs Standard training under Sym 20% noiseScale-teaching · UniMiB-SHARaccuracy (%): 87.07 -> 90.69Improved
Scale-teaching vs SREA/Mixup without noiseScale-teaching · HAR (clean labels)accuracy (%): 95.42 -> 94.72No clear effect

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