Ecole d'ingénieur et centre de recherche en Sciences du numérique

Minimalistic CNN-based ensemble model for gender prediction from face images

Antipov, Grigory; Berrani, Sid-Ahmed; Dugelay, Jean-Luc

Pattern Recognition Letters, 15 January 2016, Vol.70

Despite being extensively studied in the literature, the problem of gender recognition from face images remains difficult when dealing with unconstrained images in a cross-dataset protocol. In this work, we propose a convolutional neural network ensemble model to improve the state-of-the-art accuracy of gender recognition from face images on one of the most challenging face image datasets today, LFW (Labeled Faces in the Wild). We find that convolutional neural networks need significantly less training data to obtain the state-of-the-art performance than previously proposed methods. Furthermore, our ensemble model is deliberately designed in a way that both its memory requirements and running time are minimized. This allows us to envision a potential usage of the constructed model in embedded devices or in a cloud platform for an intensive use on massive image databases.

Document Doi Hal Bibtex

Titre:Minimalistic CNN-based ensemble model for gender prediction from face images
Mots Clés:Gender recognition from face images; Convolutional neural networks
Type:Journal
Langue:English
Ville:
Date:
Département:Sécurité numérique
Eurecom ref:4768
Copyright: © Elsevier. Personal use of this material is permitted. The definitive version of this paper was published in Pattern Recognition Letters, 15 January 2016, Vol.70 and is available at : http://dx.doi.org/10.1016/j.patrec.2015.11.011
Bibtex: @article{EURECOM+4768, doi = {http://dx.doi.org/10.1016/j.patrec.2015.11.011}, year = {2016}, month = {01}, title = {{M}inimalistic {CNN}-based ensemble model for gender prediction from face images}, author = {{A}ntipov, {G}rigory and {B}errani, {S}id-{A}hmed and {D}ugelay, {J}ean-{L}uc}, journal = {{P}attern {R}ecognition {L}etters, 15 {J}anuary 2016, {V}ol.70 }, url = {http://www.eurecom.fr/publication/4768} }
Voir aussi: