AI Paper Atlas

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

Learning Intrinsic Hierarchy for Generalized Category Discovery

Yu Duan, Junzhi He, Zhanxuan Hu, Mengda Ji, Rong Wang, Quanxue Gao

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 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 LEAH (pruner and constructor) to SimGCDSimGCD · Stanford Cars (All)clustering accuracy: 53.8 -> 65.5Improved
add LEAH to SimGCDSimGCD · Stanford Cars (New)clustering accuracy: 45.0 -> 58.2Improved
add LEAH to SimGCDSimGCD · CIFAR-10 (All)clustering accuracy: 97.1 -> 97.5No clear effect
add LEAH to SimGCDSimGCD · CUB (Old)clustering accuracy: 65.6 -> 76.3Mixed
add the pruner to baselines (ablation)GCD and SimGCD · fine-grained and generic benchmarksaccuracyImproved
add the constructor on top of the pruner (ablation)LEAH · GCD benchmarksaccuracyImproved
make alpha_in learnable instead of fixed at 0.9 (ablation)SimGCD+LEAH · CUB (All)clustering accuracy: 68.6 -> 69.4Improved
make both alpha_in and alpha_out learnable (ablation)SimGCD+LEAH · CUB (New)clustering accuracy: 64.5 -> 65.9Improved
fix all cone thresholds (ablation)SimGCD+LEAH · CUB (Old)clustering accuracy: 76.3 -> 76.5No clear effect
retain 40 instead of 20 key-object tokens (ablation)SimGCD+LEAH · CUB (All)clustering accuracy: 55.0 -> 69.4Improved
retain 60 instead of 40 key-object tokens (ablation)SimGCD+LEAH · Stanford Cars (All)clustering accuracy: 61.6 -> 65.5Improved
retain 60 instead of 40 key-object tokens (ablation)SimGCD+LEAH · CUB (All)clustering accuracy: 69.4 -> 67.7Hurt

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