AI Paper Atlas

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

Understanding and Mitigating Annotation Bias in Facial Expression Recognition

Yunliang Chen, Jungseock Joo

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware facial expression recognition · 127 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 AU-calibrated triplet loss (AUC-FER)ResNet-50 baseline · ExpW to CFD happyCV discrimination score: 0.059 ± 0.035 -> 0.006 ± 0.020Improved
add AU-calibrated triplet loss (AUC-FER)MobileNetV2 baseline · ExpW to CFD happy (8,000)CV discrimination score: 0.079 ± 0.009 -> 0.028 ± 0.029Improved
add domain independent trainingResNet-50 baseline · ExpW to CFD happyCV discrimination score: 0.059 ± 0.035 -> 0.029 ± 0.015Improved
add gradient projectionResNet-50 baseline · ExpW to CFD happyCV discrimination score: 0.059 ± 0.035 -> 0.036 ± 0.014Improved
add domain discriminative trainingResNet-50 baseline · ExpW to CFD happyCV discrimination score: 0.059 ± 0.035 -> 0.076 ± 0.024Hurt
add uniform confusionMobileNetV2 baseline · ExpW to CFD happy (8,000)CV discrimination score: 0.079 ± 0.009 -> 0.085 ± 0.021Hurt
add gradient projectionMobileNetV2 baseline · ExpW to CFD happy (8,000)CV discrimination score: 0.079 ± 0.009 -> 0.070 ± 0.036No clear effect
relabel training data so happy proportion is equal across genders given AUs (ablation)ResNet-50 trained on ExpW · ExpW to CFD happyCV discrimination score: 0.0574 -> 0.0052Improved
train on web-annotated rather than lab-controlled data (annotation bias) (ablation)happy labels · AU6=1 gender gapfemale minus male happy proportion: ExpW 0.124, RAF-DB 0.153 vs CFD 0.016, KDEF 0.072Hurt
use automatic labels instead of manual labels (ablation)AffectNet · AU6=1 gender gapfemale minus male happy proportion: 0.145 -> 0.086No clear effect

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