AI Paper Atlas

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

Adaptive Label Noise Cleaning With Meta-Supervision for Deep Face Recognition

Yaobin Zhang, Weihong Deng, Yaoyao Zhong, Jiani Hu, Xian Li, Dongyue Zhao, Dongchao Wen

ICCV 2021 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 12 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 adaptive threshold adapter on top of meta-learning (Simulation source) (ablation)AMC cleaner · CASIA-WebFace cleaned, IJB-C TPR@FPR=1e-5TPR (%): 71.93 -> 73.59Improved
add adaptive threshold adapter on top of meta-learning (MS1M source) (ablation)AMC cleaner · CASIA-WebFace cleaned, IJB-C TPR@FPR=1e-5TPR (%): 72.42 -> 73.78Improved
add adaptive threshold adapter on top of meta-learning (ablation)AMC cleaner · MC-mini cleaned, IJB-C TPR@FPR=1e-5TPR (%): 92.14 -> 92.36Improved
add meta-learning instead of fine-tuning (MS1M source) (ablation)cleaner · CASIA-WebFace cleaned, IJB-C TPR@FPR=1e-5TPR (%): 72.69 -> 72.42 for fine-tune vs meta; source 71.63 -> 72.42Mixed
add meta-learning instead of fine-tuning (Simulation source) (ablation)cleaner · CASIA-WebFace cleaned, IJB-C TPR@FPR=1e-5TPR (%): 72.49 -> 71.93Hurt
add fine-tuning on pseudo-labeled target data to source-trained cleaner (ablation)cleaner · MC-mini cleaned, IJB-C TPR@FPR=1e-5TPR (%): 92.33 -> 91.95Hurt
add fine-tuning on target data to source-trained cleaner (MS1M source) (ablation)cleaner · CASIA-WebFace cleaned, IJB-B TPR@FPR=1e-5TPR (%): 62.84 -> 64.27Improved
use real noisy MS1M source instead of simulated source for AMCAMC · CASIA-WebFace cleaned, IJB-C TPR@FPR=1e-5TPR (%): 73.59 -> 73.78Improved
use AMC cleaning instead of FaceGraphArcFace ResNet-34 · CASIA-WebFace cleaned, IJB-C TPR@FPR=1e-5TPR (%): 72.74 -> 73.78Improved
use AMC cleaning instead of FaceGraphArcFace ResNet-50 · MegaFace Challenge 1verification TPR (%): 97.76 -> 98.15Improved
use AMC cleaning instead of FaceGraphArcFace ResNet-50 · MC-mini cleaned, IJB-C TPR@FPR=1e-5TPR (%): 91.92 -> 92.36Improved
add manual cleaning to CASIA-WebFaceArcFace ResNet-34 · CASIA-WebFace, CFP-FPaccuracy (%): 94.73 -> 94.11Hurt

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