AI Paper Atlas

Research map / Continual learning / Class-incremental

FOSTER: Feature Boosting and Compression for Class-Incremental Learning

Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan

ECCV 2022 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 403 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
replace weight alignment with logits alignment (ablation)FOSTER · CIFAR-100 B50 5 stepsfinal accuracy: about 4%Improved
add feature enhancement (ablation)FOSTER · CIFAR-100 B50 5 stepslast-stage accuracy: more than 3% decline without itImproved
add feature enhancement (ablation)FOSTER · CIFAR-100 B50 5 steps (old classes, last step)accuracy: more than 4 %Improved
add feature enhancement (ablation)FOSTER · CIFAR-100 B50 5 steps (new classes, last step)accuracyNo clear effect
use balanced distillation instead of normal KD (ablation)FOSTER compression · CIFAR-100 B50 5 stepsincremental accuracyImproved
vary beta from 0.93 to 0.999 (ablation)FOSTER · CIFAR-100 B50 5 stepsaccuracy: 0.93, 0.95, 0.97, 0.99, 0.995, 0.999No clear effect
increase exemplars per class from 5 to 200 (ablation)FOSTER · CIFAR-100 B50 5 stepslast-step accuracy: 53.53% -> 71.4%Improved
use only 10 exemplars per class (ablation)FOSTER · CIFAR-100 B50 5 stepslast-round accuracy: more than 60%Improved
initialize O by fine-tuning instead of all zero (ablation)FOSTER boosting · CIFAR-100 B50 5 stepsaccuracyNo clear effect
add bias learning to all-zero O (AZB) (ablation)FOSTER boosting · CIFAR-100 B50 5 stepsaccuracyNo clear effect
compress dual-branch model to single backboneFOSTER B4 · CIFAR-100 and ImageNet-100incremental accuracyNo clear effect
FOSTER vs DERFOSTER · ImageNet-1000 (10 steps)average accuracy: 66.73% to 68.34% (+1.61%)Improved

Later papers that compared with this method

15 later accepted papers report FOSTER as a baseline in their results tables; 14 of them report a better number on most of the results they share with it.

7 more not listed.

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