AI Paper Atlas

Research map / Continual learning / Class-incremental

Dealing With Cross-Task Class Discrimination in Online Continual Learning

Yiduo Guo, Bing Liu, Dongyan Zhao

CVPR 2023 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 20 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
Use GSA instead of the strongest reported baselineOnline class-incremental learning · MNIST, CIFAR10, CIFAR100, and TinyImageNetaccuracy: 91.4 vs 90.4; 64.6 vs 58.2; 49.7 vs 39.5; 33.2 vs 22.5Improved
remove the within-task classification loss for new classes (ablation)GSA · CIFAR100; TinyImageNetaccuracy: 31.4 -> 30.1; 18.4 -> 17.5Hurt
remove the within-task classification loss for previous classes (ablation)GSA · CIFAR100; TinyImageNetaccuracy: 31.4 -> 12.7; 18.4 -> 4.7Hurt
remove the cross-task classification loss (ablation)GSA · CIFAR100; TinyImageNetaccuracy: 31.4 -> 29.9; 18.4 -> 17.2Hurt
remove the balanced mixed set Xmix (ablation)GSA · CIFAR100; TinyImageNetaccuracy: 31.4 -> 30.1; 18.4 -> 17.5Hurt
replace GSA-CE with ordinary cross-entropy (ablation)GSA · CIFAR100; TinyImageNetaccuracy: 31.4 -> 29.7; 18.4 -> 16.9Hurt

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