CNN based facial aesthetics analysis through dynamic robust losses and ensemble regression

Archive ouverte : Article de revue

Bougourzi, Fares | Dornaika, Fadi | Barrena, Nagore | Distante, Cosimo | Taleb-Ahmed, Abdelmalik

Edité par HAL CCSD ; Springer Verlag (Germany)

International audience. In recent years, estimating beauty of faces has attracted growing interest in the fields of computer vision and machine learning. This is due to the emergence of face beauty datasets (such as SCUT-FBP, SCUT-FBP5500 and KDEF-PT) and the prevalence of deep learning methods in many tasks. The goal of this work is to leverage the advances in Deep Learning architectures to provide stable and accurate face beauty estimation from static face images. To this end, our proposed approach has three main contributions. To deal with the complicated high-level features associated with the FBP problem by using more than one pre-trained Convolutional Neural Network (CNN) model, we propose an architecture with two backbones (2B-IncRex). In addition to 2B-IncRex, we introduce a parabolic dynamic law to control the behavior of the robust loss parameters during training. These robust losses are ParamSmoothL1, Huber, and Tukey. As a third contribution, we propose an ensemble regression based on five regressors, namely Resnext-50, Inception-v3 and three regressors based on our proposed 2B-IncRex architecture. These models are trained with the following dynamic loss functions: Dynamic ParamSmoothL1, Dynamic Tukey, Dynamic ParamSmoothL1, Dynamic Huber, and Dynamic Tukey, respectively. To evaluate the performance of our approach, we used two datasets: SCUT-FBP5500 and KDEF-PT. The dataset SCUT-FBP5500 contains two evaluation scenarios provided by the database developers: 60-40% split and five-fold cross-validation. Our approach outperforms state-of-the-art methods on several metrics in both evaluation scenarios of SCUT-FBP5500. Moreover, experiments on the KDEF-PT dataset demonstrate the efficiency of our approach for estimating facial beauty using transfer learning, despite the presence of facial expressions and limited data. These comparisons highlight the effectiveness of the proposed solutions for FBP. They also show that the proposed Dynamic robust losses lead to more flexible and accurate estimators.

Consulter en ligne

Suggestions

Du même auteur

Facial Beauty Prediction Using Hybrid CNN Architectures and Dynamic Robust Loss Function | Dornaika, Fadi

Facial Beauty Prediction Using Hybrid CNN Architectures and Dynamic Robust ...

Archive ouverte: Communication dans un congrès

Dornaika, Fadi | 2022-08-21

oral. International audience

ILC-Unet++ for Covid-19 Infection Segmentation | Bougourzi, Fares

ILC-Unet++ for Covid-19 Infection Segmentation

Archive ouverte: Communication dans un congrès

Bougourzi, Fares | 2022-05-23

International audience. Since the appearance of Covid-19 pandemic, in the end of 2019, Medical Imaging has been widely used to analysis this disease. In fact, CT-scans of the Lung can help to diagnosis, detect and q...

Per-COVID-19: A Benchmark Dataset for COVID-19 Percentage Estimation from CT-Scans | Bougourzi, Fares

Per-COVID-19: A Benchmark Dataset for COVID-19 Percentage Estimation from C...

Archive ouverte: Article de revue

Bougourzi, Fares | 2021

International audience. COVID-19 infection recognition is a very important step in the fight against the COVID-19 pandemic. In fact, many methods have been used to recognize COVID-19 infection including Reverse Tran...

Du même sujet

Reading History of Science as a Physics and Mathematics Framework for Newton Geneva Edition (1822) | Pisano, Raffaele

Reading History of Science as a Physics and Mathematics Framework for Newto...

Archive ouverte: Communication dans un congrès

Pisano, Raffaele | 2017-04-19

International audience

On Mechanics and Thermodynamics Analogies in History of Physics-Mathematics and Teaching Science | Pisano, Raffaele

On Mechanics and Thermodynamics Analogies in History of Physics-Mathematics...

Archive ouverte: Communication dans un congrès

Pisano, Raffaele | 2017-05-12

International audience

On the epistemic interplay between physics and mathematics such as a dynamical framework within nos–research teaching science | Pisano, Raffaele

On the epistemic interplay between physics and mathematics such as a dynami...

Archive ouverte: Communication dans un congrès

Pisano, Raffaele | 2017-06-12

International audience

A CMOS Compatible Thermoelectric Device made of Crystalline Silicon Membranes with Nanopores | Bah, Thierno-Moussa

A CMOS Compatible Thermoelectric Device made of Crystalline Silicon Membran...

Archive ouverte: Article de revue

Bah, Thierno-Moussa | 2022-12-10

International audience. Herein, we report the use of nanostructured crystalline silicon as a thermoelectric material and its integration into thermoelectric devices. The proof-of-concept relies on the partial suppre...

Effet de l'angle de charge sur les harmoniques d'efforts magnétiques dans les machines synchrones à aimants permanents surfaciques | Le Besnerais, Jean

Effet de l'angle de charge sur les harmoniques d'efforts magnétiques dans l...

Archive ouverte: Communication dans un congrès

Le Besnerais, Jean | 2016-06-07

International audience. Cet article étudie l'effet de l'angle de charge sur les efforts harmoniques de Maxwell (tangentiels et radiaux) et les bruits et vibrations d'origine magnétique dans deux machines synchrones ...

Further investigation of convolutional neural networks applied in computational electromagnetism under physics‐informed consideration | Gong, Ruohan

Further investigation of convolutional neural networks applied in computati...

Archive ouverte: Article de revue

Gong, Ruohan | 2022-04-07

International audience. Convolutional neural networks (CNN) have shown great potentials and have been proven to be an effective tool for some image-based deep learning tasks in the field of computational electromagn...

Chargement des enrichissements...