AI Paper Atlas

Research map / Continual learning / Class-incremental

Exemplar-Free Class Incremental Learning via Preserving Class-Discriminative Structure

Xin Zhang, Liang Bai, Guanchao Wang, Xian Yang

CVPR 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning

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 SCC (structural consistency constraint) (ablation)baseline without SCC/APR · ImageNet-A (10 tasks)Last-Acc: 60.08 -> 63.60Improved
add APR (adaptive prototype rectification) (ablation)baseline without SCC/APR · ImageNet-A (10 tasks)Last-Acc: 60.08 -> 61.97Improved
add SCC (ablation)baseline without SCC/APR · Cars-196 (10 tasks)Last-Acc: 67.90 -> 74.86Improved
add APR (ablation)baseline without SCC/APR · Cars-196 (10 tasks)Last-Acc: 67.90 -> 77.02Improved
combine SCC and APR (ablation)SCC-only model · Cars-196 (10 tasks)Last-Acc: 74.86 -> 80.23Improved
replace SDC with APR for prototype rectification (ablation)SCC-only model · Cars-196 (10 tasks)Last-Acc: 76.26 -> 80.23Improved
replace SDC with APR (ablation)SCC-only model · ImageNet-A (10 tasks)Last-Acc: 63.88 -> 64.58Improved
add logit distillation to APR-only model (ablation)APR-only model · Cars-196 (10 tasks)Last-Acc: 77.02 -> 67.76Hurt
add feature distillation to APR-only model (ablation)APR-only model · Cars-196 (10 tasks)Last-Acc: 77.02 -> 75.37Hurt
add logit or feature distillation to APR-only model (ablation)APR-only model · ImageNet-A (10 tasks)Last-Acc: 61.97 -> 62.17 (logit), 61.90 (feature)No clear effect
increase covariance correction rho from 0 to 10 (ablation)APR · Cars-196 (10 tasks)Last-Acc: 78.49 -> 80.23Improved
increase covariance correction rho from 0 to 10 (ablation)APR · ImageNet-A (10 tasks)Last-Acc: 63.99 -> 64.58Improved

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