AI Paper Atlas

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

AllGCD: Leveraging All Unlabeled Data for Generalized Category Discovery

Xinzi Cao, Ke Chen, Feidiao Yang, Xiawu Zheng, Yonghong Tian, Yutong Lu

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 5 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 Intra-CL to SimGCD (ablation)SimGCD · CUBAll ACC: 60.3 -> 65.2Improved
add Inter-CU to SimGCD (ablation)SimGCD · CUBAll ACC: 60.3 -> 67.1Improved
combine Intra-CL and Inter-CU (ablation)AllGCD · CUBAll ACC: 67.1 -> 68.4Improved
add Intra-CL to SimGCD (ablation)SimGCD · CIFAR100New ACC: 77.8 -> 79.6Improved
add Inter-CU to SimGCD (ablation)SimGCD · CIFAR100New ACC: 77.8 -> 81.7Improved
raise Intra-CL confidence from 0.75 to 0.90 (ablation)AllGCD · CUBAll ACC: 68.4 -> 66.2Hurt
raise Intra-CL confidence from 0.70 to 0.85 (ablation)AllGCD · CIFAR100All ACC: 80.8 -> 82.3Improved
raise Inter-CU threshold from 0.65 to 0.80 (ablation)AllGCD · Stanford CarsAll ACC: 60.5 -> 57.6Hurt
raise Inter-CU threshold from 0.60 to 0.70 (ablation)AllGCD · ImageNet-100All ACC: 85.6 -> 86.5Improved
use AllGCD instead of SimGCD with ground-truth KAllGCD · Stanford CarsNew ACC: 45.0 -> 52.5Improved
start Inter-CU at later epoch (e=80 vs earlier) for hard fine-grained sets (ablation)AllGCD · Stanford Cars/FGVC-AircraftNew ACCImproved
use AllGCD vs CMS on Old ACCAllGCD · CIFAR100Old ACC: 85.7 -> 82.3Hurt

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