AI Paper Atlas

Research map / Continual learning / Class-incremental

End-to-End Incremental Learning

Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Cordelia Schmid, Karteek Alahari

ECCV 2018 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 1,206 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 data augmentation to the base model (ablation)Our-CNN-Base · CIFAR-100 ablation, fixed memory (20 classes/step)accuracy: 50.1 -> 57.2Improved
add balanced fine-tuning to the base model (ablation)Our-CNN-Base · CIFAR-100 ablation, fixed memory (20 classes/step)accuracy: 50.1 -> 57.1Improved
add both augmentation and balanced fine-tuning (ablation)Our-CNN-Base · CIFAR-100 ablation, fixed memory (10 classes/step)accuracy: 53.7 -> 64.0Improved
add balanced fine-tuning to augmentation-only model (ablation)Our-CNN-DA · CIFAR-100 ablation, fixed memory (5 classes/step)accuracy: 59.2 -> 63.8Improved
add data augmentation to model with balanced fine-tuning (ablation)Our-CNN-BF · CIFAR-100 ablation, fixed memory (5 classes/step)accuracy: 57.9 -> 63.8Improved
use herding selection instead of random selection for memory (ablation)Representative memory · CIFAR-100 (10 classes/step)accuracy: 63.1 -> 63.6No clear effect
use herding selection instead of histogram selection (ablation)Representative memory · CIFAR-100 (10 classes/step)accuracy: 59.1 -> 63.6Improved
use end-to-end cross-distilled model instead of iCaRLIncremental learner · CIFAR-100 fixed memory (2 classes/step)average incremental accuracy: 54.1 -> 63.8Improved
use end-to-end model instead of iCaRL with many classes per stepIncremental learner · CIFAR-100 fixed memory (50 classes/step)average incremental accuracy: 61.8 -> 60.8Hurt
use end-to-end model instead of iCaRLIncremental learner · ImageNet fixed memory (100 classes/step)accuracy: 62.5 -> 69.4Improved
increase exemplars per old class from 50 to 100Our-CNN · CIFAR-100 fixed samples (5 classes/step)accuracy: 62.4 -> 68.6Improved
use end-to-end model instead of GEM with small memoryIncremental learner · CIFAR-100 task known a priori (memory 200)final accuracy: 48.0 -> 77.9Improved

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