AI Paper Atlas

Research map / Continual learning / Class-incremental

Class-Incremental Learning via Dual Augmentation

Fei Zhu, Zhen Cheng, Xu-yao Zhang, Cheng-lin Liu

NeurIPS 2021 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 68 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 semanAug (implicit semantic augmentation of old classes) to class-mean replay baseline (ablation)IL2A baseline · CIFAR-100 10 phasesfinal accuracy: 34.71 -> 42.09Improved
add classAug (class augmentation by mixing) to baseline (ablation)IL2A baseline · CIFAR-100 10 phasesfinal accuracy: 34.71 -> 41.56Improved
add classAug on top of semanAug (ablation)IL2A · CIFAR-100 10 phasesfinal accuracy: 42.09 -> 45.07Improved
add semanAug on top of classAug (ablation)IL2A · CIFAR-100 10 phasesfinal accuracy: 41.56 -> 45.07Improved
replace Knowledge Distillation with class-mean replay baseline (ablation)IL2A · CIFAR-100 10 phasesfinal accuracy: 6.04 -> 34.71Improved
add classAug (ablation)IL2A baseline · CIFAR-100 10 phasesnew task accuracy and forgettingImproved
use Mixup instead of classAug as regularizer (ablation)IL2A · CIFAR-100 final accuracyfinal accuracyHurt
use label smoothing instead of classAug (ablation)IL2A · CIFAR-100 final accuracyfinal accuracyHurt
use diagonal covariance instead of full covariance in semanAug (ablation)IL2A · CIFAR-100final accuracyHurt
add classAug to baseline OOD detectorCIFAR-10 ResNet-18 · OOD meanAUROC: 88.57 -> 94.30Improved
use Mixup instead of classAugCIFAR-10 ResNet-18 · OOD meanAUPR-In: 83.35 -> 79.21 (AUPR-In); 88.57 -> 89.90 (AUROC)Mixed

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