Deep learning for semantic description of visual human traits

Abstract : The recent progress in artificial neural networks (rebranded as deep learning) has significantly boosted the state-of-the-art in numerous domains of computer vision. In this PhD study, we explore how deep learning techniques can help in the analysis of gender and age from a human face. In particular, two complementary problem settings are considered: (1) gender/age prediction from given face images, and (2) synthesis and editing of human faces with the required gender/age attributes.Firstly, we conduct a comprehensive study which results in an empirical formulation of a set of principles for optimal design and training of gender recognition and age estimation Convolutional Neural Networks (CNNs). As a result, we obtain the state-of-the-art CNNs for gender/age prediction according to the three most popular benchmarks, and win an international competition on apparent age estimation. On a very challenging internal dataset, our best models reach 98.7% of gender classification accuracy and an average age estimation error of 4.26 years.In order to address the problem of synthesis and editing of human faces, we design and train GA-cGAN, the first Generative Adversarial Network (GAN) which can generate synthetic faces of high visual fidelity within required gender and age categories. Moreover, we propose a novel method which allows employing GA-cGAN for gender swapping and aging/rejuvenation without losing the original identity in synthetic faces. Finally, in order to show the practical interest of the designed face editing method, we apply it to improve the accuracy of an off-the-shelf face verification software in a cross-age evaluation scenario.
Complete list of metadatas

Cited literature [266 references]  Display  Hide  Download

https://pastel.archives-ouvertes.fr/tel-01725853
Contributor : Abes Star <>
Submitted on : Wednesday, March 7, 2018 - 4:35:08 PM
Last modification on : Wednesday, May 15, 2019 - 12:46:15 PM
Long-term archiving on : Friday, June 8, 2018 - 2:53:08 PM

File

Antipov_PhD_Manuscript_2017-12...
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01725853, version 1

Collections

Citation

Grigory Antipov. Deep learning for semantic description of visual human traits. Neural and Evolutionary Computing [cs.NE]. Télécom ParisTech, 2017. English. ⟨NNT : 2017ENST0071⟩. ⟨tel-01725853⟩

Share

Metrics

Record views

1168

Files downloads

1338