AI Paper Atlas

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

Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery

Jizhou Han, Chenhao Ding, Yuhang He, Qiang Wang, Shaokun Wang, SongLin Dong, Yihong Gong

CVPR 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
attach AL-GCD (ATCG)SelEx-CLIP · CUBaccuracy (All): 74.2 -> 84.1Improved
attach AL-GCD (ATCG)SimGCD-CLIP · Stanford Carsaccuracy (All): 69.4 -> 78.3Improved
attach AL-GCD (ATCG)CMS-CLIP · FGVC Aircraftaccuracy (All): 50.3 -> 54.8Improved
attach AL-GCD (ATCG)SelEx-CLIP · CIFAR100accuracy (All): 77.2 -> 80.4Improved
attach AL-GCD (ATCG)SelEx-CLIP · CIFAR100novel accuracy: 77.6 -> 69.8Hurt
attach AL-GCD across all pipelinesCLIP-based GCD pipelines · All-datasets average (K known)accuracy (All): avg +5.0Improved
attach AL-GCDCMS-CLIP · All datasets (K unknown)accuracy (All): 65.8 -> 69.8Improved
add ATCG initial layer (ablation)SimGCD-CLIP · CIFAR100novel accuracy: 75.2 -> 82.7Improved
add ATCG stacked layers on top of initial layer (ablation)SimGCD-CLIP + ATCG · ImageNet100accuracy (All): 90.4 -> 92.6Improved
add ATCG stacked layers on top of initial layer (ablation)SimGCD-CLIP + ATCG · Stanford Carsaccuracy (All): 74.9 -> 78.3Improved
increase ATCG depth from 2 to 4/6 layers (ablation)SimGCD-CLIP + ATCG · CUBaccuracy (All): 74.73 -> 74.80 (4) / 74.69 (6)No clear effect
increase vision weight alpha from 0.4 to 0.7 (ablation)AL-GCD · Stanford Carsold / new accuracy: old +1.8, new -1.7Mixed

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