AI Paper Atlas

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

Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts

Haiyang Zheng, Nan Pu, Wenjing Li, Nicu Sebe, Zhun Zhong

IJCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 3 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 instance-level representation learning to concept-level DCCL (ablation)DCCL · CUB, Stanford Cars, Fungi, Herbarium 19, NABirdsAll ACC: surpassing DCCL by 7.5% in All ACCImproved
add concept-level learning to instance-level-only training (ablation)Variant I (IRL only) · CUB, Stanford Cars, Fungi, Herbarium 19, NABirdsAll ACC: surpassing Variant I by 2.2% in All ACCImproved
add multi-expert conceptual learning (ME) (ablation)MGCE · five fine-grained datasetsAll ACC / New ACC: 2.6% and 3.3% in All ACC and New ACCImproved
add collaborative learning among experts (CL) (ablation)MGCE · five fine-grained datasetsAll ACC / New ACC: 0.9% and 1.2% in All ACC and New ACCImproved
add collaborative learning on NABirds (variant III to IV) (ablation)MGCE · NABirds (known K_U)Old ACC: 75.1 -> 73.2Hurt
add coarse-grained expert (ablation)MGCE · CUB, Animalia, MolluscaAll ACC: average drop of 1.4% in All ACC when removedImproved
add fine-grained expert (ablation)MGCE · CUB, Animalia, MolluscaAll ACC: drop of 2.7% when removedImproved
add extra fine-grained experts (R=0.4) beyond three experts (ablation)MGCE · CUB, Animalia, MolluscaAll ACC: decreases All ACC by 0.5% on averageHurt
add extra coarse-grained experts (R=0.4) beyond three experts (ablation)MGCE · CUB, Animalia, MolluscaAll ACC: decreases it by 0.7%Hurt
use 2-layer projection head instead of 1-layer head (ablation)MGCE · CUB, Stanford CarsAll ACC: improving All ACC by 1.8% over the 1-layer headImproved
use 2-layer projection head instead of 3-layer head (ablation)MGCE · CUB, Stanford CarsAll ACC: by 1.1% over the 3-layer headImproved
add projection head before Semi-Infomap and concept contrastive learning (ablation)MGCE · CUBAll ACC: 67.9 -> 70.4Improved

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