AI Paper Atlas

Research map / Continual learning / Class-incremental

Learnability and Algorithm for Continual Learning

Gyuhak Kim, Changnan Xiao, Tatsuya Konishi, Bing Liu

ICML 2023 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 2 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 a separate WP head on top of the OOD-head model (ROW vs ROW (-WP)) (ablation)ROW · C10-5T, C100-10T, C100-20Taverage classification accuracy: +2.47, +2.43, +2.63Improved
add distance-based (Mahalanobis) coefficient to TP probability (ROW (-WP) vs ROW (-WP-MD)) (ablation)ROW (-WP) · C10-5T, C100-10T, C100-20Taverage classification accuracy: +4.44, +4.76, +6.12Improved
halve replay memory buffer size (ablation)ROW · Average over 5 benchmarksaverage classification accuracy: -1.02 avg (73.72 to 72.70)No clear effect
halve replay memory buffer size (ablation)DER++ · Average over 5 benchmarksaverage classification accuracy: -4.73 avg (66.89 to 62.16)Hurt
ROW (full method with OOD replay and WP head) vs replay baseline MOREROW · Average over 5 benchmarksaverage classification accuracy: +2.13 (73.72 vs 71.59)Improved
replace pre-trained feature extractor with adapter-tuned DeiT (vs frozen SLDA classifier-only)SLDA · C100-10T, T-5Taverage classification accuracy: SLDA 67.82 / 57.93 vs ROW 74.72 / 65.11Hurt
remove classes overlapping with CL datasets from pre-training (L2P)L2P · Average over 5 benchmarksaverage classification accuracy: drops to 60.47 averageHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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