AI Paper Atlas

Research map / Continual learning / Class-incremental

Exemplar-Free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation

Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov, Joost van de Weijer

IJCV 2025 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 6 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 gated class-attention (ablation)fine-tuned ViT · CIFAR-100 (10 tasks)Class-IL accuracy: 11.90 -> 31.35Improved
add gated class-attention (ablation)fine-tuned ViT · Tiny-ImageNet (10 tasks)Class-IL accuracy: 7.98 -> 22.79Improved
add cascaded feature drift compensation to gated class-attention + PFR (ablation)GCAB · CIFAR-100 (10 tasks)Class-IL accuracy: 7.96 -> 35.90Improved
add cascaded feature drift compensation to gated class-attention + PFR (ablation)GCAB · Tiny-ImageNet (10 tasks)Class-IL accuracy: 5.52 -> 26.82Improved
add backbone regularization (PFR) without drift compensation (ablation)GCAB · CIFAR-100 (10 tasks)Class-IL accuracy: 31.35 -> 7.96Hurt
add feature drift compensation on top of gated attention and PFR versus gated attention alone (ablation)GCAB · CIFAR-100 (10 tasks)Class-IL accuracy: 31.35 -> 35.90Improved
use feature distillation instead of PFR for backbone regularization (ablation)GCAB · CIFAR-100 (10 tasks)Class-IL accuracy: 35.90 -> 30.50Hurt
distill GCAB into single student block (GCAB-Fast, 80% capacity)GCAB · CIFAR-100 (5 tasks)Class-IL accuracy: 49.86 -> 48.85No clear effect
distill GCAB into single student block (GCAB-Fast)GCAB · ImageNet100 (10 tasks)Class-IL accuracy: 40.10 -> 36.22Hurt
use GCAB without exemplars versus LVT with 200 exemplarsGCAB · Tiny-ImageNet (10 tasks)Class-IL accuracy: 17.34 -> 26.82Improved

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