AI Paper Atlas

Research map / Continual learning / Class-incremental

Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning

Jinge Ma, Fengqing Zhu

CVPR 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 0 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 TAL to iCaRLiCaRL · ImageNet-100 (10-task)average accuracy: 43.71 -> 52.19Improved
add TAL to DERDER · CIFAR-100 (10-task)last accuracy: 50.75 -> 53.82Improved
add TAL to TagFexTagFex · Food101 (10-task)last accuracy: 66.67 -> 68.64Improved
add TAL to FOSTERFOSTER · Food101 (10-task)average accuracy: 63.88 -> 64.61Improved
add TAL to MEMOMEMO · CIFAR-100 (10-task)last accuracy: 51.70 -> 52.85Improved
use TAL with r=1.0, lambda=0.995 instead of CE (ablation)ER · CIFAR-100 (10-task)average accuracy: 59.96 -> 63.36Improved
use large steepness r=5.0 in TAL (ablation)ER + TAL · CIFAR-100 (10-task)average accuracy: 59.96 -> 56.70 (lambda=0.99)Hurt
use small r=0.2 in TAL (ablation)ER + TAL · CIFAR-100 (10-task)average accuracy: 59.96 -> 61.30Improved
tune lambda from 0.995 to 0.9995 at r=1.0 (ablation)ER + TAL · CIFAR-100 (10-task)average accuracy: 63.36 -> 61.79Hurt
TAL's reweighting of negative supervision per classiCaRL/DER/MEMO/TagFex · ImageNet-100 final-task class accuracyper-class recall: old classes up, newest classes down slightlyMixed

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