AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization

Luyao Tang, Jiewei Zheng, Kunze Huang, Chaoqi Chen, Yue Huang, Cheng Chen

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 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 column-normalized primitive competition (ablation)CoGe-GCD (SimGCD) · CUB-200All accuracy: 62.6 -> 63.9Improved
add column-normalized primitive competition (ablation)CoGe-GCD (SimGCD) · FGVC-AircraftAll accuracy: 56.1 -> 57.9Improved
add column-normalized primitive competition (ablation)CoGe-GCD (SimGCD) · CIFAR-100All accuracy: 78.5 -> 80.1Improved
add column-normalized primitive competition (ablation)CoGe-GCD (SimGCD) · ImageNet-100All accuracy: 82.0 -> 83.0Improved
add geometric structure preserving calibration (ablation)CoGe-GCD (SimGCD) · CUB-200All accuracy: 62.4 -> 63.9Improved
add geometric structure preserving calibration (ablation)CoGe-GCD (SimGCD) · FGVC-AircraftAll accuracy: 54.1 -> 57.9Improved
add geometric structure preserving calibration (ablation)CoGe-GCD (SimGCD) · CIFAR-100All accuracy: 76.0 -> 80.1Improved
add geometric structure preserving calibration (ablation)CoGe-GCD (SimGCD) · ImageNet-100All accuracy: 81.6 -> 83.0Improved
add CoGe-GCD plug-in to four GCD baselinesSimGCD, LegoGCD, CMS, SelEx · fine-grained average (CUB, Aircraft, Cars)All accuracy: +4.03Improved
add CoGe-GCD plug-in to SimGCDSimGCD · fine-grained CUB-200 Known accuracyKnown accuracy: 66.4 -> 65.5Hurt
add CoGe-GCD plug-in to baselinesSimGCD, LegoGCD, SimGCD on coarse · coarse-grained (CIFAR-10/100, ImageNet-100)All accuracy: +1.07Improved
add CoGe-GCD to SimGCD on ImageNet-100SimGCD · ImageNet-100Known accuracy: 93.1 -> 92.4Hurt

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