AI Paper Atlas

Research map / Continual learning / Class-incremental

Decouple Your Discovery and Memory in Continual Generalized Category Discovery

Jiawei Yu, Zijian Gao, Xingxing Zhang, Xuan Liu, Huaimin Wang, Kele Xu

CVPR 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention

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 class-group entropic regularization (L_GER) (ablation)discovery branch · CIFAR100 (6 stages)new-class accuracy (%): 3.90 -> 42.06Improved
add class-group entropic regularization (L_GER) (ablation)discovery branch · CUB (6 stages)new-class accuracy (%): 4.81 -> 9.22Improved
add clustering-guided initialization (Init) (ablation)discovery branch · CUB (6 stages)new-class accuracy (%): 4.81 -> 35.33Improved
combine L_GER and Init (ablation)discovery branch · CIFAR100 (6 stages)All accuracy (%): 59.66 -> 64.00Improved
add recursive analytic memory branch (ablation)DYDM without memory · CIFAR100 (6 stages)All accuracy (%): 64.00 -> 78.96Improved
add knowledge rehearsal distillation (L_KD) from memory branch (ablation)DYDM · CUB (6 stages)new-class accuracy (%): 50.85 -> 56.61Improved
add knowledge rehearsal distillation (L_KD) from memory branch (ablation)DYDM · CIFAR100 (6 stages)All accuracy (%): 78.96 -> 79.72Improved
plug DYDM memory branch into HappyHappy · CIFAR100 (6 stages)Md novel discovery (%): 50.20 -> 68.74Improved
plug DYDM memory branch into SimGCD*SimGCD* · CIFAR100 (6 stages)F_base forgetting (%): 12.96 -> 2.52Improved
use feature distillation or Happy-style anti-forgetting versus finetuningC-GCD baselines · CIFAR100plasticityHurt
increase expansion size of analytic classifier from 1k to 9k (ablation)memory branch · CIFAR100 (6 stages)All accuracy (%): 77.98 -> 80.11Improved
increase expansion size of analytic classifier from 1k to 9k (ablation)memory branch · CUB200 (6 stages)All accuracy (%): 73.49 -> 52.25Hurt

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