AI Paper Atlas

Research map / Continual learning / Online and replay-based

Rehearsal Revealed: The Limits and Merits of Revisiting Samples in Continual Learning

Eli Verwimp, Matthias De Lange, Tinne Tuytelaars

ICCV 2021 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 86 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 n memory-only update steps after each task minimum (ER-step) (ablation)ER · MNIST (|M|=100)average accuracy after 5 tasks: 72.9 -> 82.3Improved
add n memory-only update steps after each task minimum (ER-step) (ablation)ER · MNIST (|M|=500)average accuracy after 5 tasks: 87.1 -> 90.0Improved
add n memory-only update steps after each task minimum (ER-step) (ablation)ER · MNIST (|M|=1000)average accuracy after 5 tasks: 90.2 -> 91.8Improved
add n memory-only update steps after each task minimum (ER-step) (ablation)ER · MNIST (|M|=200)average accuracy after 5 tasks: 81.8 -> 87.6Improved
add n memory-only update steps after each task minimum (ER-step) (ablation)ER · MNIST (|M|=2000)average accuracy after 5 tasks: 91.8 -> 92.6Improved
add n memory-only update steps after each task minimum (ER-step) (ablation)ER (stable) · CIFAR10 (|M|=100)average accuracy after 5 tasks: 46.7 -> 47.4No clear effect
add n memory-only update steps after each task minimum (ER-step) (ablation)ER (stable) · CIFAR10 (|M|=500)average accuracy after 5 tasks: 65.1 -> 66.2No clear effect
add n memory-only update steps after each task minimum (ER-step) (ablation)ER (stable) · CIFAR10 (|M|=1000)average accuracy after 5 tasks: 70.7 -> 70.8No clear effect
add n memory-only update steps after each task minimum (ER-step) (ablation)ER (stable) · Mini-Imagenet (|M|=100)average accuracy after 5 tasks: 25.7 -> 29.8Improved
add n memory-only update steps after each task minimum (ER-step) (ablation)ER (stable) · Mini-Imagenet (|M|=500)average accuracy after 5 tasks: 39.7 -> 42.3Improved
add n memory-only update steps after each task minimum (ER-step) (ablation)ER (stable) · Mini-Imagenet (|M|=1000)average accuracy after 5 tasks: 46.6 -> 47.4Improved
add rehearsal of stored samples versus plain finetuningfinetuning · MNIST, CIFAR10, Mini-Imagenet (5 tasks, shared head)average accuracy over all tasks: 60%, 9% and 7% gainImproved

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