Learning CNNs from Weakly Annotated Facial Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00324147" target="_blank" >RIV/68407700:21230/18:00324147 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1016/j.imavis.2018.06.011" target="_blank" >https://doi.org/10.1016/j.imavis.2018.06.011</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.imavis.2018.06.011" target="_blank" >10.1016/j.imavis.2018.06.011</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Learning CNNs from Weakly Annotated Facial Images

Popis výsledku v původním jazyce

Learning of convolutional neural networks (CNNs) to perform a face recognition task requires a large set of facial images each annotated with a 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 (ML) estimation of a parametric distribution describing the weakly annotated images. The ML problem is solved by an instance of the EM algorithm which in its inner loop learns a CNN to predict attribute label from facial images. Experiments on age and gender estimation problem show that the proposed algorithm significantly outperforms the existing heuristic approach for dealing with this type of data. A practical outcome of our paper is a new annotation of the IMDB database [26] containing 300 k faces each one annotated by biological age, gender and identity labels.

Název v anglickém jazyce

Learning CNNs from Weakly Annotated Facial Images

Popis výsledku anglicky

Learning of convolutional neural networks (CNNs) to perform a face recognition task requires a large set of facial images each annotated with a 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 (ML) estimation of a parametric distribution describing the weakly annotated images. The ML problem is solved by an instance of the EM algorithm which in its inner loop learns a CNN to predict attribute label from facial images. Experiments on age and gender estimation problem show that the proposed algorithm significantly outperforms the existing heuristic approach for dealing with this type of data. A practical outcome of our paper is a new annotation of the IMDB database [26] containing 300 k faces each one annotated by biological age, gender and identity labels.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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

2018

Kód důvěrnosti údajů

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

Název periodika

Image and Vision Computing

ISSN

0262-8856

e-ISSN

1872-8138

Svazek periodika

77

Číslo periodika v rámci svazku

September

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

11

Strana od-do

10-20

Kód UT WoS článku

000446282900002

EID výsledku v databázi Scopus

2-s2.0-85049924723