AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition

Iris Dominguez-Catena, Daniel Paternain, Mikel Galar

TPAMI 2024 · Learning theory and algorithms › Fairness · approach: Post-processing and transport for fairness · 84 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
remove all female subjects from training data (representational bias) (ablation)ResNet50 on AffectNet · AffectNet gender Exp1angry recall, female group: 20% recall change between extremesHurt
remove one gender entirely from training data (ablation)ResNet50 on AffectNet · AffectNet gender Exp1recall other classes: variations up to 10%Hurt
remove female examples from happy class (ablation)ResNet50 on AffectNet · AffectNet gender Exp2female happy recall: 0.85 -> 0.4Hurt
bias happy class while other classes stay balanced (ablation)ResNet50 on AffectNet · AffectNet gender Exp2recall of unperturbed classesNo clear effect
bias happy and angry classes in opposite directions (ablation)ResNet50 on AffectNet · AffectNet gender Exp3angry recall: 0.4 -> 0.1Hurt
give group all angry examples (opposite bias) (ablation)ResNet50 on AffectNet · AffectNet gender Exp3angry recall: 0.4 -> 0.6Improved
bias two classes in opposite directions instead of one (ablation)ResNet50 on AffectNet · AffectNet gender Exp3recallNo clear effect
use BP instead of IR^-1 for dominanceRepresentational bias metrics · FER datasetsSpearman agreement: 0.85 to 0.96Improved
use Z instead of NPMI for local biasLocal stereotypical bias metrics · FER+ ageinterpretability: -1 and -0.22 vs -1 and -0.9Improved
use Cramer's V vs other chi2/NMI metricsStereotypical bias metrics · FER datasetsSpearman agreement: minimum 0.91No 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