AI Paper Atlas

Research map / Continual learning / Class-incremental

DiAPR: Dimensionally-Allocated Prototype Refinement for Non-Exemplar Class Incremental Learning

Ruixuan Gao, Qijun Zhao, Keren Fu

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 DAP and GSA dimension-wise refinement instead of Gaussian noise augmentation (ablation)ViT baseline · CIFAR-100 (5 tasks)LAST accuracy: 60.78 -> 63.47Improved
add DAP and GSA instead of new feature injection (ablation)ViT baseline · CIFAR-100 (10 tasks)LAST accuracy: 60.78 -> 61.67Improved
add CDT on top of DAP&GSA (ablation)ViT baseline · CIFAR-100 (5 tasks)LAST accuracy: 63.47 -> 64.58Improved
add CDT on top of Gaussian augmentation (ablation)ViT baseline · CIFAR-100 (5 tasks)LAST accuracy: 60.78 -> 62.82Improved
add CDT on top of DAP&GSA (ablation)ViT baseline · CIFAR-100 (10 tasks)LAST accuracy: 61.67 -> 62.17Improved
use closed-form ridge regression instead of learnable layers for task transition (ablation)CDT · CIFAR-100accuracy: +2.17%Improved
use closed-form ridge regression instead of learnable layers for task transition (ablation)CDT · TinyImageNetaccuracy: +0.38%Improved
DiAPR vs best NECIL baselineDiAPR (ViT) · CIFAR-100 (5 tasks)AVG accuracy: 70.44 -> 72.79Improved
DiAPR vs best NECIL baselineDiAPR (ViT) · TinyImageNet (20 tasks)AVG accuracy: 52.50 -> 52.90Improved
lower average forgetting than baselinesDiAPR (ViT) · CIFAR-100 (5 tasks)AF: 12.20 -> 10.53Improved

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