Demographic bias mitigation at test-time using uncertainty estimation and human–machine partnership

Facial attribute classification algorithms frequently manifest demographic biases by obtaining differential performance across gender and racial groups. Existing bias mitigation techniques are mostly in-processing techniques, i.e., implemented during the classifier’s training stage, that often lack...

Full description

Saved in:

Bibliographic Details
Main Authors:	Anoop Krishnan Upendran Nair, Ajita Rattani
Format:	Article
Language:	English
Published:	Elsevier 2025-03-01
Series:	Machine Learning with Applications
Subjects:	Facial attribute classifier Human–machine partnership Demographic bias mitigation Continual learning Test-time methods
Online Access:	http://www.sciencedirect.com/science/article/pii/S2666827024000860
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Demographic bias mitigation at test-time using uncertainty estimation and human–machine partnership

Similar Items