AI Paper Atlas

Research map / Continual learning / Class-incremental

NAPA-VQ: Neighborhood-Aware Prototype Augmentation with Vector Quantization for Continual Learning

Tamasha Malepathirana, Damith Senanayake, Saman Halgamuge

ICCV 2023 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 19 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 categorical cross-entropy with distance-based cross-entropy (DCE) (ablation)KD baseline · CIFAR-100 (T=10)Average accuracy: 16.70 -> 32.90Improved
add neighborhood-adaptation loss L_NA to DCE and KD (ablation)KD + DCE · CIFAR-100 (T=20)Average forgetting: 81.71 -> 30.09Improved
add neighborhood-adaptation loss L_NA to DCE and KD (ablation)KD + DCE · CIFAR-100 (T=5)Average accuracy: 49.83 -> 49.31No clear effect
add Gaussian-noise prototype augmentation to NA-VQ (ablation)KD + NA-VQ · CIFAR-100 (T=20)Average accuracy: 42.13 -> 62.39Improved
replace Gaussian prototype augmentation with neighborhood-aware NA-PA (ablation)NAPA-VQ · CIFAR-100 (T=20)Average accuracy: 62.39 -> 67.42Improved
replace Gaussian prototype augmentation with neighborhood-aware NA-PA (ablation)NAPA-VQ · CIFAR-100 (T=20)Average forgetting: 18.30 -> 9.08Improved
increase connectivity factor K (2 to 50) (ablation)NA-VQ · CIFAR-100accuracy and running timeMixed
NAPA-VQ vs SSRE on ImageNet-Subset (T=10) forgettingNAPA-VQ · ImageNet-Subset (T=10)Average forgetting: 8.30 -> 9.67Hurt
NAPA-VQ vs SOTA NECIL on accuracyNAPA-VQ · CIFAR-100, TinyImageNet, ImageNet-SubsetAverage accuracy: avg +5%, +2%, +4%Improved

Later papers that compared with this method

1 later accepted paper reports NAPA-VQ as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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