AI Paper Atlas

Research map / Continual learning / Class-incremental

More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning

Yu Liu, Sarah Parisot, Gregory Slabaugh, Xu Jia, Ales Leonardis, Tinne Tuytelaars

ECCV 2020 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 96 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 multiple side classifiers (K=3) to MAS parameter regularizationMAS · CIFAR-100 and Tiny ImageNetaccuracy: about 4%~5% gains on CIFAR-100, 3%~4% on Tiny ImageNetImproved
add multiple side classifiers to LwF activation regularizationLwF · CIFAR-100 and Tiny ImageNetaccuracy: 3%~5% gainsImproved
increase side classifiers from K=2 to K=3 (ablation)MUC-MAS · CIFAR-100 and Tiny ImageNetaccuracy: about 1.5% improvementImproved
increase side classifiers from K=3 to K=4 or 5 (ablation)MUC-MAS · CIFAR-100 and Tiny ImageNetaccuracyNo clear effect
add side classifiers (MUC) to MAS and LwFMAS, LwF · CIFAR-100 and Tiny ImageNetforgetting ratio: -0.55 -> -0.50 (MAS, CIFAR-100, 10 tasks)Improved
add classifier discrepancy loss to side classifier training (ablation)MUC · CIFAR-100Euclidean distance between side classifier parameters: 0.057 -> 5.284Improved
train in two stages instead of one stage (ablation)MUC-MAS · CIFAR-100 (100 classes seen)accuracy: 28.8 -> 31.7Improved
train in two stages instead of one stage (ablation)MUC-LwF · CIFAR-100 (100 classes seen)accuracy: 38.4 -> 41.6Improved
train in two stages instead of one stage (ablation)MUC-MAS · CIFAR-100 (20 classes seen)accuracy: 83.5 -> 82.6Hurt
increase lambda from 0.01 to 0.02 (ablation)MAS · CIFAR-100 (100 classes seen)accuracy: 27.5 -> 30.8Improved
add side classifiers at fixed lambda 0.01MAS · CIFAR-100 (100 classes seen)accuracy: 27.5 -> 31.7Improved
add stability factor to MUC-MAS (ablation)MUC-MAS · CIFAR-100 (100 classes seen)accuracy: 30.8 -> 31.7Improved

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