AI Paper Atlas

Research map / Continual learning / Online and replay-based

On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning

Lorenzo Bonicelli, Matteo Boschini, Angelo Porrello, Concetto Spampinato, Simone Calderara

NeurIPS 2022 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 16 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 LiDER Lipschitz regularization on buffer samplesDER++ · Split CIFAR-100 (buffer 500)Final avg accuracy: 37.13 -> 39.25Improved
add LiDERDER++ · Split CUB-200 (buffer 400)Final avg accuracy: 49.30 -> 57.90Improved
add LiDERiCaRL · Split CIFAR-100 (buffer 500)Final avg accuracy: 44.04 -> 47.02Improved
add LiDERGDumb · Split CIFAR-100 (buffer 500)Final avg accuracy: 09.28 -> 10.22Improved
add LiDERER-ACE · Split miniImageNet (buffer 2000)Final avg accuracy: 22.60 -> 24.13Improved
apply LiDER to current-task examples instead of buffer examples (ablation)DER++ · Split CIFAR-100 (buffer 500)Final avg accuracy: 39.25 -> 34.78Hurt
use fixed Lipschitz targets instead of learned targets (ablation)LiDER on DER++ · Split CIFAR-100 (buffer 500)Final avg accuracy: 39.25 -> 36.42Hurt
add Stable SGD (ablation)ER-ACE · Split CUB-200 (buffer 400)Final avg accuracy: 41.83 -> 22.67Hurt
add online EwC (ablation)ER-ACE · Split CUB-200 (buffer 400)Final avg accuracy: 41.83 -> 48.34Improved
add LiDER under buffer label poisoning (p=0.25%) (ablation)DER++ · Split CIFAR-100 (buffer 500)Final avg accuracy: 28.74 -> 30.78Improved
add LiDER (ablation)ER-ACE · Buffer guessing gameROC-AUC of identifying buffer samplesImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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