AI Paper Atlas

Research map / Continual learning / Class-incremental

EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning

Huaijie Wang, De Cheng, Lingfeng He, Yan Li, Jie Li, Nannan Wang, Xinbo Gao

IJCV 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 5 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 IPR (importance-aware parameter regularization) (ablation)shared adapter baseline · Split-ImageNetA (10 sessions)A_Last: 57.08 -> 59.14Improved
add IPR (importance-aware parameter regularization) (ablation)shared adapter baseline · Split-ImageNetR (10 sessions)A_Last: 77.71 -> 78.75Improved
add TSDC (trainable semantic drift compensation) (ablation)shared adapter baseline · Split-ImageNetA (10 sessions)A_Last: 57.08 -> 64.10Improved
add TSDC (trainable semantic drift compensation) (ablation)shared adapter baseline · Split-DomainNet (10 sessions)A_Last: 82.75 -> 86.24Improved
add IPR on top of adapter + TSDC (ablation)adapter + TSDC · Split-ImageNetR (10 sessions)A_Last: 80.42 -> 80.60Improved
add global importance (GI) only (ablation)shared adapter baseline · Split-ImageNetA (10 sessions)A_Last: 57.08 -> 58.13Improved
add local importance (LI) only (ablation)shared adapter baseline · Split-ImageNetR (10 sessions)A_Last: 77.71 -> 78.36Improved
add both GI and LI over GI alone (ablation)adapter + GI · Split-ImageNetA (10 sessions)A_Last: 58.13 -> 59.14Improved
add uniform parameter regularization (PR) (ablation)shared adapter baseline · Split-ImageNetR (10 sessions)A_Last: 77.71 -> 74.42Hurt
replace uniform PR with IPR (ablation)adapter + regularization · Split-ImageNetR (10 sessions)A_Last: 74.42 -> 78.75Improved
replace static drift compensation with trainable TSDC (ablation)unified classifier training · Split-ImageNetA (10 sessions)A_Last: 62.43 -> 64.10Improved
add static drift compensation over no drift compensation (ablation)unified classifier training · Split-ImageNetA (10 sessions)A_Last: 59.82 -> 62.43Improved

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