AI Paper Atlas

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

Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction

Luyao Tang, Kunze Huang, Chaoqi Chen, Yuxuan Yuan, Chenxin Li, Xiaotong Tu, Xinghao Ding, Yue Huang

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 9 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 ConGCDSelEx (DINOv1) · CUB-200clustering accuracy All: 78.7 -> 81.7Improved
add ConGCDSimGCD (DINOv1) · CUB-200clustering accuracy All: 60.3 -> 61.6Improved
add ConGCD to four GCD baselinesSimGCD, LegoGCD, SPTNet, SelEx (DINOv1) · fine-grained averageclustering accuracy All: +1.18Improved
add ConGCD to four GCD baselinesfour baselines (DINOv1) · fine-grained averageclustering accuracy Novel: +1.98Improved
add ConGCDSelEx (DINOv2) · FGVC-Aircraftclustering accuracy All: 82.1 -> 81.7Hurt
add ConGCDSelEx (DINOv2) · Stanford-Carsclustering accuracy All: 80.5 -> 79.8Hurt
add ConGCDSelEx (DINOv1) · CIFAR-10clustering accuracy All: 94.1 -> 95.7Improved
add ConGCDSPTNet (DINOv1) · ImageNet-100clustering accuracy All: 85.4 -> 85.9Improved
add ConGCDcoarse-grained baselines · CIFAR-100clustering accuracy Novel: +0.98Improved
use multiplex consensus instead of conventional MoE (ablation)ConGCD · CUB-200clustering accuracy All: 78.2 -> 81.7Improved
add dominant consensus units (ablation)ConGCD · CUB-200clustering accuracy All: 81.1 -> 81.7Improved
add contextual consensus units (ablation)ConGCD · CUB-200clustering accuracy All: 80.4 -> 81.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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