AI Paper Atlas

Research map / Continual learning / Class-incremental

Masked Autoencoders are Efficient Class Incremental Learners

Jiang-Tian Zhai, Xialei Liu, Andrew D. Bagdanov, Ke Li, Ming-Ming Cheng

ICCV 2023 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 24 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 MAE-generated replay data (ablation)Bilateral MAE baseline · CIFAR-100 10 tasksAvg accuracy: 73.40 -> 75.88Improved
add self-supervised reconstruction loss (ablation)MAE with replay · CIFAR-100 10 tasksAvg accuracy: 75.88 -> 77.48Improved
add bilateral detailed branch (ablation)MAE with replay and reconstruction · CIFAR-100 10 tasksAvg accuracy: 77.48 -> 79.12Improved
masking ratio 0.75 versus 0.60 or 0.90 (ablation)Bilateral MAE · CIFAR-100 10 tasksAvg accuracy: 77.50 / 77.12 -> 79.12Improved
replace real-image replay with MAE-generated replay of equal storage (ablation)Bilateral MAE · CIFAR-100 10 tasksAvg accuracy: 79.57 -> 79.12No clear effect
apply detail loss in frequency domain instead of spatial domain (ablation)Bilateral MAE · CIFAR-100 10 tasksLast accuracy: 65.93 -> 68.40Improved
give DyTox the same 80 masked exemplars (ablation)DyTox · CIFAR-100 10 tasksLast accuracy: 62.10 -> 65.46Improved
reduce MLP size from 1536 to 768 (fewer parameters) (ablation)Bilateral MAE · CIFAR-100 10 tasksLast accuracy: 68.40 -> 67.52Hurt
use MAE patch replay instead of JPEG compression or down-scalingmemory-efficient replay · CIFAR-100 10 tasksLast accuracy: 61.32 -> 68.40Improved

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