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

Abhijit Das 1 Antitza Dantcheva 1 Francois Bremond 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01892103
Contributor : Antitza Dantcheva <>
Submitted on : Wednesday, October 10, 2018 - 12:30:41 PM
Last modification on : Friday, October 12, 2018 - 10:50:44 AM
Long-term archiving on : Friday, January 11, 2019 - 2:31:16 PM

File

DasDantchevaBremond_ECCVW_18.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01892103, version 1

Collections

Citation

Abhijit Das, Antitza Dantcheva, Francois Bremond. Mitigating Bias in Gender, Age and Ethnicity Classification: a Multi-Task Convolution Neural Network Approach. ECCVW 2018 - European Conference of Computer Vision Workshops, Sep 2018, Munich, Germany. ⟨hal-01892103⟩

Share

Metrics

Record views

159

Files downloads

2324