AI Paper Atlas

Research map / Continual learning / Class-incremental

Few-Shot Class-Incremental Learning from an Open-Set Perspective

Can Peng, Kun Zhao, Tianren Wang, Meng Li, Brian C. Lovell

ECCV 2022 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 120 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 cross-entropy with angular penalty (cosFace) loss (ablation)ALICE (balanced prototypes) · CIFAR100 5-shot, last sessionaverage accuracy: 46.2 -> 49.5Improved
replace cross-entropy with angular penalty (cosFace) loss (ablation)ALICE (balanced prototypes) · CIFAR100 5-shot, last sessionharmonic accuracy: 31.4 -> 25.2Hurt
add projection layers before the final fully connected layer (ablation)ALICE · CIFAR100 5-shot, last sessionharmonic accuracy: 25.2 -> 43.8Improved
add projection layers (ablation)ALICE · CIFAR100 5-shot, last sessionaverage accuracy: 49.5 -> 49.5No clear effect
add two augmentations of each input image (data augmentation) (ablation)ALICE · CIFAR100 5-shot, last sessionaverage accuracy: 49.5 -> 51.3Improved
add two augmentations of each input image (data augmentation) (ablation)ALICE · CIFAR100 5-shot, last sessionharmonic accuracy: 43.8 -> 47.4Improved
add class augmentation by mixing class pairs (ablation)ALICE · CIFAR100 5-shot, last sessionaverage accuracy: 51.3 -> 54.1Improved
add class augmentation by mixing class pairs (ablation)ALICE · CIFAR100 5-shot, last sessionharmonic accuracy: 47.4 -> 50.6Improved
use balanced data (same number of base samples) for prototypes (ablation)cross-entropy model · CIFAR100 5-shot, last sessionharmonic accuracy: 27.4 -> 31.4Improved
use balanced data for prototypes (ablation)angular penalty model · CIFAR100 5-shot, last sessionharmonic accuracy: 22.3 -> 25.2Improved
add class augmentation on fine-grained data (ablation)ALICE · CUB200accuracyHurt
replace CEC with ALICECEC · CIFAR100 1-shot, last sessionharmonic accuracy: 13.0 -> 26.5Improved

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