AI Paper Atlas

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

LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition

Jinghan You, Shanglin Li, Yuanrui Sun, Jiangchuan Wei, Mingyu Guo, Chao Feng, Jiao Ran

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 13 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 PCO stage 1 (feature alignment with negative sub-sampling) (ablation)ViT-L · MFR-Ongoing MR-Allaccuracy: 97.27 -> 97.52Improved
add PCO stage 2 (centroid stabilization) (ablation)ViT-L · MFR-Ongoing MR-Allaccuracy: 97.52 -> 98.22Improved
add PCO stage 3 (boundary refinement without NCS) (ablation)ViT-L · MFR-Ongoing MR-Allaccuracy: 98.22 -> 98.49Improved
add PCO to ArcFace loss (ablation)ViT-B · IJB-C TAR@FAR=1e-5TAR: 96.11 -> 96.68Improved
add PCO to CosFace loss (ablation)ViT-B · IJB-C TAR@FAR=1e-5TAR: 96.15 -> 97.00Improved
use CosFace instead of ArcFace as base loss with PCO (ablation)LVFace ViT-B · IJB-C TAR@FAR=1e-5TAR: 96.68 -> 97.00Improved
scale backbone from Tiny to Base on Glint360K (ablation)LVFace · IJB-C TAR@FAR=1e-5TAR: 95.63 -> 97.00Improved
scale backbone from Base to Large on Glint360K (ablation)LVFace · IJB-C TAR@FAR=1e-5TAR: 97.00 -> 97.02No clear effect
train ViT-L on WebFace42M instead of Glint360K (ablation)LVFace-L · IJB-C TAR@FAR=1e-5TAR: 97.02 -> 97.25Improved
use LVFace-L versus TopoFR on Mask subsetLVFace · MFR-Ongoing Maskaccuracy: 93.96 -> 93.56Hurt
LVFace-L versus TransFace-L at IJB-C 1e-6 (ablation)LVFace-L · IJB-C TAR@FAR=1e-6 (Glint360K)TAR: 89.71 -> 89.51No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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