Fine-Grained Face Annotation Using Deep Multi-Task CNN.
Sensors (Basel)
; 18(8)2018 Aug 14.
Article
em En
| MEDLINE
| ID: mdl-30110891
ABSTRACT
We present a multi-task learning-based convolutional neural network (MTL-CNN) able to estimate multiple tags describing face images simultaneously. In total, the model is able to estimate up to 74 different face attributes belonging to three distinct recognition tasks age group, gender and visual attributes (such as hair color, face shape and the presence of makeup). The proposed model shares all the CNN's parameters among tasks and deals with task-specific estimation through the introduction of two components (i) a gating mechanism to control activations' sharing and to adaptively route them across different face attributes; (ii) a module to post-process the predictions in order to take into account the correlation among face attributes. The model is trained by fusing multiple databases for increasing the number of face attributes that can be estimated and using a center loss for disentangling representations among face attributes in the embedding space. Extensive experiments validate the effectiveness of the proposed approach.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Redes Neurais de Computação
/
Face
Tipo de estudo:
Prognostic_studies
Idioma:
En
Revista:
Sensors (Basel)
Ano de publicação:
2018
Tipo de documento:
Article
País de afiliação:
Itália