AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Noise-Robust Face Recognition via Non-target Similarity Distribution Guided Sample Selection

Fanglong Wu, Youqiang Gui, Cheng Peng

ECCV 2026 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods

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 progressive threshold schedule instead of a fixed upper threshold (ablation)DDLN · Simulated #40-20-20 (CosFace)precision / F1: 67.72 -> 99.39 precision, 80.70 -> 99.42 F1Improved
use rank k=10 instead of k=1 for the upper-tail estimate (ablation)DDLN · Simulated #40-20-20F1: 98.93 -> 99.14Improved
use rank k=10 instead of k=50 (ablation)DDLN · Simulated #40-20-20F1: 98.56 -> 99.14Improved
add slack alpha=0.02 (ablation)DDLN · Simulated #40-20-20F1: 99.14 -> 99.42Improved
vary schedule length nmax among 8, 9, 10 (ablation)DDLN · Simulated #40-20-20F1: 99.38, 99.42, 99.39No clear effect
vary EMA factor lambda over 0.005 to 0.1 (ablation)DDLN · Simulated #40-20-20F1: 99.32, 99.42, 99.30, 99.29No clear effect
use k=1 instead of default k=10 under heavy noise (ablation)DDLN · Simulated #80-40-40Avg: 78.11 -> 71.97Hurt
use k=50 instead of default k=10 under heavy noise (ablation)DDLN · Simulated #80-40-40Avg: 78.11 -> 70.68Hurt
replace OTSU threshold (RVFace) with DDLNCosFace · Simulated #80-40-40Avg: 60.06 -> 78.11Improved
replace OTSU threshold with DDLN: FNR at 60% noiseCosFace · Simulated 60% noiseFNR: 7.26 -> 1.24Improved
add DDLN to CosFace on WebFace2M-NoiseCosFace · WebFace2M-Noiseaverage over 8 benchmarks: 77.02 -> 84.43Improved
add DDLN to CosFace on CASIA-WebFaceCosFace · CASIA-WebFace IJB-CTAR@FAR=1e-5: 67.97 -> 82.29Improved

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