AI Paper Atlas

Research map / Continual learning / Class-incremental

Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning

Tao Zhang, Qixuan Fan, Yiyuan Liang, Yanjie Wang, Song Yan, Tian Tian, Jiahuan Zhou, Luxin Yan, Sheng Zhong, Xu Zou

ICML 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 0 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 Dynamic Domain Centering (ablation)raw generative replay · CIFAR-100 (T=10)accuracy: 33.27 -> 41.02Improved
add Hierarchical Subspace Rectification (HSR) (ablation)raw generative replay · CIFAR-100 (T=10)accuracy: 33.27 -> 58.46Improved
add HSR on top of Centering (ablation)DREAM · CIFAR-100 (T=10)accuracy: 41.02 -> 67.69Improved
add RAPC on top of Centering and HSR (ablation)DREAM · CIFAR-100 (T=10)accuracy: 67.69 -> 69.73Improved
use hard projection gamma=1.0 instead of soft gamma=0.8 (ablation)DREAM · CIFAR-100 (T=10)accuracy: 69.73 -> 56.92Hurt
subspace dimension k=10 instead of 5 (ablation)DREAM · CIFAR-100 (T=10)accuracy: 69.73 -> 62.02Hurt
lambda_KD=10.0 instead of 1.0 (ablation)DREAM · CIFAR-100 (T=10)accuracy: 69.73 -> 63.78Hurt
add prototype loss lambda_Proto=0.10 (ablation)DREAM · CIFAR-100 (T=10)accuracy: 67.69 -> 69.73Improved
add task-constraint data filtering with Qwen-Image (ablation)DREAM · CIFAR-100 (T=10)accuracy: 68.67 -> 69.73Improved
add task-constraint data filtering with SD1.5 (ablation)DREAM · CIFAR-100 (T=10)accuracy: 68.08 -> 68.84Improved
swap Qwen-Image for SD1.5 generator (ablation)DREAM · CIFAR-100 (T=10)accuracy: 69.73 -> 68.84No clear effect
add DREAM to multi-source generative replayraw generative replay · CIFAR-100 (T=10)accuracy: 39.21 -> 68.06Improved

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