AI Paper Atlas

Research map / Continual learning / Class-incremental

Dual-Estimator: Decoupling Global and Local Semantic Shift for Drift Compensation in Class-Incremental Learning

Fankang Xu, Lu Jin, Yanpeng Sun, Shiyu Xuan, Zechao Li

CVPR 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention

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 MoE-E on top of the base distillation model (ablation)Base (Lcls + Lkd) · TinyImageNet (20 tasks)A_inc (%): 36.40 -> 43.55Improved
add LoR-E on top of the base distillation model (ablation)Base (Lcls + Lkd) · TinyImageNet (20 tasks)A_inc (%): 36.40 -> 39.49Improved
add LoR-E alone on top of the base model (ablation)Base (Lcls + Lkd) · ImageNet-Subset (20 tasks)A_inc (%): 55.17 -> 54.17Hurt
add LoR-E to MoE-E (combine global and local estimators) (ablation)Dual-E · TinyImageNet (20 tasks)A_inc (%): 43.55 -> 44.36Improved
add historical preservation term in LoR-E (ablation)Dual-E · TinyImageNet (20 tasks)A_inc (%): 44.23 -> 44.36Improved
add rotation-based pixel fusion augmentation for MoE-E experts (ablation)Dual-E · TinyImageNet (20 tasks)A_last (%): 3.88 -> 30.35Improved
add HP weight alpha greater than 0 (alpha=5) (ablation)LoR-E · CIFAR-100 / ImageNet-Subset (10 tasks)accuracyImproved
vary number of experts K and rank r (ablation)Dual-E · CIFAR-100 (10 tasks)accuracyNo clear effect
plug Dual-E into PASS instead of no compensation or LDC/DPPASS · TinyImageNet (20 tasks)A_inc (%): 32.01 -> 39.75Improved
plug Dual-E into NAPA-VQNAPA-VQ · ImageNet-Subset (20 tasks)A_inc (%): 24.38 -> 49.61Improved
use Dual-E instead of DP on long 50-task sequencesdrift compensation · ImageNet-1K (50 tasks)A_inc (%): 38.88 -> 40.13Improved

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