AI Paper Atlas

Research map / Continual learning / Class-incremental

MetaGCD: Learning to Continually Learn in Generalized Category Discovery

Yanan Wu, Zhixiang Chi, Yang Wang, Songhe Feng

ICCV 2023 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 41 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 candidate neighbors as positives in contrastive learning (ablation)VanillaGCD baseline · C-GCD CIFAR100mean All accuracy: 73.67 -> 74.92Improved
add soft positiveness weights to neighbors (ablation)VanillaGCD + candidate neighbors · C-GCD CIFAR100mean New accuracy: 62.89 -> 64.55Improved
add meta-learning bi-level optimization on pseudo incremental sessions (ablation)MetaGCD without meta-learning · C-GCD CIFAR100mean All accuracy: 75.66 -> 77.06Improved
use non-parametric identity mapping instead of learned projections in attention module (ablation)soft positiveness · C-GCD CIFAR100accuracyImproved
set neighbor similarity threshold to 0.85 rather than lower or higher (ablation)MetaGCD · C-GCD CIFAR100accuracyMixed
sample more novel classes in meta-training sequences (ablation)MetaGCD · C-GCD CIFAR100accuracyImproved
MetaGCD versus GM on new-class discoveryGM · C-GCD Tiny-ImageNetfinal New accuracy: 50.90 -> 58.46Improved
MetaGCD versus GM on old-class retentionGM · C-GCD Tiny-ImageNetfinal Old accuracy: 72.08 vs 71.53Hurt

Later papers that compared with this method

5 later accepted papers report MetaGCD as a baseline in their results tables; 5 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