AI Paper Atlas

Research map / Continual learning / Online and replay-based

A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal

Yaqian Zhang, Bernhard Pfahringer, Eibe Frank, Albert Bifet, Nick Jin Sean Lim, Alvin Jia

NeurIPS 2022 · Continual learning › Online and replay-based · approach: Plug-and-play online training enhancements · 12 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 repeated augmented rehearsal to ERER · Seq-CIFAR100, Seq-MiniImageNet, CORE50-NC, and CLRS25-NC (2K and 5K memory)accuracy: +8.8, +10.0, +10.0, +13.5, +15.3, +17.2, +9.9, +9.7Improved
Add repeated augmented rehearsal to SCRSCR · Seq-CIFAR100, Seq-MiniImageNet, CORE50-NC, and CLRS25-NC (2K and 5K memory)accuracy: +5.1, +8.4, +5.7, +10.6, +8.3, +10.8, +14.9, +17.9Improved
Add repeated augmented rehearsal to MIRMIR · Four OCL benchmarks, 2K and 5K memoryaccuracy: +9.1, +10.4, +10.1, +12.6, +13.9, +17.7, +13.5, +14.0Improved
Add repeated augmented rehearsal to ASERASER · Four OCL benchmarks, 2K and 5K memoryaccuracy: +7.2, +11.5, +11.3, +14.7, +7.8, +13.3, +9.3, +9.8Improved
Add repeated augmented rehearsal to DERDER · Four OCL benchmarks, 2K and 5K memoryaccuracy: +21.6, +32.8, +14.4, +23.2, +11.9, +18.6, +16.6, +14.8Improved
Tune RAR hyperparameters with RL rather than HTOCLRAR · Seq-CIFAR100, Seq-Mini-ImageNet, CORE50-NC, and CLRS25-NCaccuracy: 23.4 -> 29.6; 26.0 -> 32.1; 40.8 -> 44.4; 26.9 -> 35.0Improved
Use augmentation alone without repeated rehearsal (ablation)Online rehearsal · Three of four OCL datasets; CORE50-NC is the exceptionaccuracyMixed
Use repeated rehearsal alone without augmentation (ablation)Online rehearsal · Three of four OCL datasets; CLRS is the exceptionaccuracyMixed
Increase repeated rehearsal to more than two iterations without augmentation (ablation)Repeated rehearsal on CIFAR100 and MiniImageNet · Seq-CIFAR100 and Seq-MiniImageNetaccuracyHurt
Use RAR with up to 20 repeats (ablation)RAR · OCL benchmarksaccuracyNo clear effect
Augment both memory and incoming batches rather than only one (ablation)RAR · Four OCL benchmarksaccuracyImproved
Augment incoming data only (ablation)Repeated experience replay · CORE50-NCaccuracy: 7.7%Improved

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