AI Paper Atlas

Research map / Continual learning / Class-incremental

Learning a Fix and Explore Framework for Continuous Generalized Category Discovery

Chunming Li, Shidong Wang, Haofeng Zhang

AAAI 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 1 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
FaE vs Happy at Stage-5C-GCD · CIFAR-100ACC (All): 59.99 -> 65.20Improved
FaE vs Happy at Stage-5C-GCD · Tiny-ImageNetACC (All): 54.56 -> 63.65Improved
FaE vs Happy at Stage-1C-GCD · CUB-200ACC (All): 81.40 -> 80.80Hurt
FaE vs Happy maximum forgettingC-GCD · CIFAR-100Mf: 11.22 -> 6.82Improved
add graph regularization (full FaE vs distill-only) (ablation)FaE · CIFAR-100ACC (All): 72.44 -> 73.34Improved
graph distill on new + cosine distill on old instead of cosine for both (ablation)FaE · Tiny-ImageNetACC (All): 65.58 -> 70.35Improved
cosine on old and graph on new vs graph for both (ablation)FaE · CIFAR-100ACC (All): 69.95 -> 72.44Improved
extend to 10 stages vs HappyC-GCD · Tiny-ImageNetACC (All) at Stage-10: 50.69 -> 61.83Improved

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