Mitigating Bias in Gender, Age and Ethnicity Classification: a Multi-Task Convolution Neural Network Approach

Creators: Das, Abhijit; Dantcheva, Antitza; Bremond, Francois

Others:: Spatio-Temporal Activity Recognition Systems (STARS) ; Inria Sophia Antipolis - Méditerranée (CRISAM) ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria); A. Das was supported by the research program FER4HM funded by Inria and CAS. A. Dantcheva was supported by the French Government (National Research Agency, ANR) under grant agreement ANR-17-CE39-0002.; ANR-17-CE39-0002,ENVISION,Analyse Holistique automatique d'individus par des techniques de vision par ordinateur(2017)

Description

This work explores joint classification of gender, age and race. Specifically, we here propose a Multi-Task Convolution Neural Network (MTCNN) employing joint dynamic loss weight adjustment towards classification of named soft biometrics, as well as towards mitigation of soft biometrics related bias. The proposed algorithm achieves promising results on the UTKFace and the Bias Estimation in Face Analytics (BEFA) datasets and was ranked first in the the BEFA Challenge of the European Conference of Computer Vision (ECCV) 2018.

Abstract

International audience

Mitigating Bias in Gender, Age and Ethnicity Classification: a Multi-Task Convolution Neural Network Approach

Description

Abstract

Additional details