Attention-based Gender Recognition on Masked Faces

Vincenzo Carletti, Antonio Greco, Alessia Saggese, Mario Vento

2022

Abstract

Gender recognition from face images can be profitably used in several vertical markets, such as targeted advertising and cognitive robotics. However, in the last years, due to the COVID-19 pandemic, the unreliability of such systems when dealing with faces covered by a mask has emerged. In this paper, we propose a novel architecture based on attention layers and trained with a domain specific data augmentation technique for reliable gender recognition of masked faces. The proposed method has been experimentally evaluated on a huge dataset, namely VGGFace2-M, a masked version of the well known VGGFace2 dataset, and the achieved results confirm an improvement of around 4% with respect to traditional gender recognition algorithms, while preserving the performance on unmasked faces.

Paper Citation

in Harvard Style

Carletti V., Greco A., Saggese A. and Vento M. (2022). Attention-based Gender Recognition on Masked Faces. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 672-678. DOI: 10.5220/0010978700003124

in Bibtex Style

@conference{visapp22,
author={Vincenzo Carletti and Antonio Greco and Alessia Saggese and Mario Vento},
title={Attention-based Gender Recognition on Masked Faces},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={672-678},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010978700003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - Attention-based Gender Recognition on Masked Faces
SN - 978-989-758-555-5
AU - Carletti V.
AU - Greco A.
AU - Saggese A.
AU - Vento M.
PY - 2022
SP - 672
EP - 678
DO - 10.5220/0010978700003124
PB - SciTePress