Learning CNNs for face recognition from weakly annotated images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00312262" target="_blank" >RIV/68407700:21230/17:00312262 - isvavai.cz</a>

Výsledek na webu

<a href="http://cmp.felk.cvut.cz/pub/cmp/articles/franc/Franc-EMSVM-FG2017.pdf" target="_blank" >http://cmp.felk.cvut.cz/pub/cmp/articles/franc/Franc-EMSVM-FG2017.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/FG.2017.115" target="_blank" >10.1109/FG.2017.115</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Learning CNNs for face recognition from weakly annotated images

Popis výsledku v původním jazyce

Supervised learning of convolutional neural networks (CNNs) for face recognition requires a large set of facial images each annotated with a single attribute label to be predicted. In this paper we propose a method for learning CNNs from weakly annotated images. The weak annotation in our setting means that a pair of an attribute label and a person identity label is assigned to a set of faces automatically detected in the image. The challenge is to link the annotation with the correct face. The weakly annotated images of this type can be collected by an automated process not requiring a human labor. We formulate learning from weakly annotated images as a maximum likelihood estimation of a parametric distribution describing the data. The ML problem is solved by an instance of EM algorithm which in its inner loop learns a CNN to perform given face recognition task. Experiments on age and gender estimation problem show that the proposed EM-CNN algorithm significantly outperforms the state-of-the-art approach for dealing with this type of data.

Název v anglickém jazyce

Learning CNNs for face recognition from weakly annotated images

Popis výsledku anglicky

Supervised learning of convolutional neural networks (CNNs) for face recognition requires a large set of facial images each annotated with a single attribute label to be predicted. In this paper we propose a method for learning CNNs from weakly annotated images. The weak annotation in our setting means that a pair of an attribute label and a person identity label is assigned to a set of faces automatically detected in the image. The challenge is to link the annotation with the correct face. The weakly annotated images of this type can be collected by an automated process not requiring a human labor. We formulate learning from weakly annotated images as a maximum likelihood estimation of a parametric distribution describing the data. The ML problem is solved by an instance of EM algorithm which in its inner loop learns a CNN to perform given face recognition task. Experiments on age and gender estimation problem show that the proposed EM-CNN algorithm significantly outperforms the state-of-the-art approach for dealing with this type of data.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

International Conference on Automatic Face and Gesture Recognition Workshops, Biometrics in the Wild

ISBN

978-1-5090-4023-0

ISSN

—

e-ISSN

2326-5396

Počet stran výsledku

8

Strana od-do

933-940

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Washington DC

Datum konání akce

30. 5. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000414287400129