AI Paper Atlas

Research map / Continual learning / Class-incremental

Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning

Wuxuan Shi, Mang Ye

ICCV 2023 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 55 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 prototype reminiscence (interpolate/extrapolate stored prototypes with new features) to the prototype-replay baseline (ablation)NECIL baseline with stored prototypes · CIFAR-100 / TinyImageNetaverage incremental accuracyImproved
add self-supervised label augmentation alone (ablation)NECIL baseline · CIFAR-100 / TinyImageNetaverage incremental accuracyMixed
add asymmetric knowledge aggregation on top of SLA (ablation)PRAKA · CIFAR-100 (initial vs new tasks)new-task accuracyImproved
add asymmetric knowledge aggregation (ablation)PRAKA · CIFAR-100 (5 phases)average forgetting: 7.18 -> 12.59Hurt
raise prototype reminiscence threshold eta from low values to about 0.6 (ablation)PRAKA · CIFAR-100average incremental accuracyImproved
raise threshold eta beyond 0.6 (ablation)PRAKA · CIFAR-100average incremental accuracyHurt
use prototype reminiscence instead of Gaussian noise augmentation of prototypes (ablation)old-class feature generation · CIFAR-100 (t-SNE)old class feature separationImproved
use PRAKA instead of SSRENECIL on CIFAR-100 · CIFAR-100 (5 phases)average incremental accuracy: 65.88 -> 70.02Improved
use PRAKA without exemplars vs exemplar-based DERPRAKA · ImageNet-Subset (10 phases)average incremental accuracy: 68.98 vs 75.36 (DER)Hurt

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