AI Paper Atlas

Research map / Continual learning / Class-incremental

Time Series Class-Incremental Learning via Confidence-guided Mask Distillation and Prototype-guided Contrastive Learning

Yu Liu, Haoqin Yang, Jinping Sui, Hui Wang, Haipeng Li, Weimin Wang, Qi Jia

AAAI 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 0 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
add confidence-guided mask distillation (CMD) to DT2W baseline (ablation)DT2W baseline · UCI-HARaverage accuracy / forgetting: A_T 51.50 -> 55.42; F_T 62.00 -> 47.86Improved
add prototype-guided contrastive learning (PCL) alone to DT2W baseline (ablation)DT2W baseline · UCI-HARaverage accuracy / forgetting: A_T 51.50 -> 52.04; F_T 62.00 -> 63.79Mixed
combine CMD and PCL (ablation)DT2W baseline · UCI-HARaverage accuracy / forgetting: A_T 51.50 -> 59.91; F_T 62.00 -> 44.55Improved
reduce lambda1 (weight of masked feature distillation) to 0.001 (ablation)CMD+PCL · UCI-HARaverage accuracy / forgetting: A_T 59.8 -> 33.6; F_T 47.8 -> 93.1Hurt
increase lambda1 to 1.0 (ablation)CMD+PCL · UCI-HARaverage accuracy: 59.8 -> 44.9Hurt
increase lambda2 (weight of PCL loss) to 1.0 (ablation)CMD+PCL · UCI-HARaverage accuracy / forgetting: A_T 59.8 -> 48.5; F_T 47.8 -> 69.9Hurt
decrease lambda2 to 0.01 (ablation)CMD+PCL · UCI-HARaverage accuracy / forgetting: A_T 59.8 -> 58.3; F_T 47.8 -> 56.2Hurt
apply CMD+PCL versus best replay-free baseline DT2W1D-CNN replay-free TSCIL · DSAaverage accuracy / forgetting: A_T 24.5 -> 29.6; F_T 87.2 -> 60.6Improved
apply CMD+PCL versus DT2W on WISDM1D-CNN replay-free TSCIL · WISDMaverage accuracy / forgetting: A_T 16.4 -> 19.0; F_T 62.1 -> 57.3Improved
add PCL loss, visualised with t-SNE (ablation)CMD · UCI-HARfeature separability (qualitative)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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