{"id":54404,"date":"2022-08-31T14:03:19","date_gmt":"2022-08-31T12:03:19","guid":{"rendered":"https:\/\/www.iemn.fr\/articles-temporaires-anglais\/cnn-based-facial-aesthetics-analysis-through-dynamic-robust-losses-and-ensemble-regression-2.html"},"modified":"2022-09-06T10:08:36","modified_gmt":"2022-09-06T08:08:36","slug":"cnn-based-facial-aesthetics-analysis-through-dynamic-robust-losses-and-ensemble-regression-2","status":"publish","type":"post","link":"https:\/\/www.iemn.fr\/en\/newsletter\/cnn-based-facial-aesthetics-analysis-through-dynamic-robust-losses-and-ensemble-regression-2.html","title":{"rendered":"Analysis of facial aesthetics based on the CNN convolutional neural network using robust dynamic losses and ensemble regression"},"content":{"rendered":"<section  class='av_textblock_section av-l7hkjq14-c08352cfd4dcc8d7f97a640a2ded15f9'   itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/BlogPosting\" itemprop=\"blogPost\" ><div class='avia_textblock'  itemprop=\"text\" ><p style=\"text-align: center;\"><a href=\"https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-54394 size-full\" src=\"https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale.jpg\" alt=\"\" width=\"600\" height=\"145\" srcset=\"https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale.jpg 600w, https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale-300x73.jpg 300w, https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale-18x4.jpg 18w\" sizes=\"auto, (max-width: 600px) 100vw, 600px\" \/><\/a><\/p>\n<\/div><\/section>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-l7pwrrn7-d8a93e74d3e45a715a30a72bd97c2456\">\n#top .av-special-heading.av-l7pwrrn7-d8a93e74d3e45a715a30a72bd97c2456{\npadding-bottom:10px;\ncolor:#4392e8;\n}\nbody .av-special-heading.av-l7pwrrn7-d8a93e74d3e45a715a30a72bd97c2456 .av-special-heading-tag .heading-char{\nfont-size:25px;\n}\n.av-special-heading.av-l7pwrrn7-d8a93e74d3e45a715a30a72bd97c2456 .special-heading-inner-border{\nborder-color:#4392e8;\n}\n.av-special-heading.av-l7pwrrn7-d8a93e74d3e45a715a30a72bd97c2456 .av-subheading{\nfont-size:15px;\n}\n<\/style>\n<div  class='av-special-heading av-l7pwrrn7-d8a93e74d3e45a715a30a72bd97c2456 av-special-heading-h3 custom-color-heading blockquote modern-quote modern-centered  avia-builder-el-1  el_after_av_textblock  el_before_av_one_half'><h3 class='av-special-heading-tag'  itemprop=\"headline\"  >Analyse de l\u2018esth\u00e9tique faciale bas\u00e9e sur le r\u00e9seau neuronal convolutif (CNN) gr\u00e2ce \u00e0 des pertes dynamiques robustes et \u00e0 la r\u00e9gression d\u2019ensemble<\/h3><div class=\"special-heading-border\"><div class=\"special-heading-inner-border\"><\/div><\/div><\/div>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-10qf1p5-7b69d8b497882f34f319a0712b118c1d\">\n.flex_column.av-10qf1p5-7b69d8b497882f34f319a0712b118c1d{\nborder-radius:0px 0px 0px 0px;\npadding:0px 0px 20px 0px;\n}\n<\/style>\n<div  class='flex_column av-10qf1p5-7b69d8b497882f34f319a0712b118c1d av_one_half  avia-builder-el-2  el_after_av_heading  el_before_av_one_half  first flex_column_div'     ><section  class='av_textblock_section av-l7hklx67-0eb9b2c59ff6cf2fb4de0bbaa4f13db3'   itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/BlogPosting\" itemprop=\"blogPost\" ><div class='avia_textblock'  itemprop=\"text\" ><h5>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-qawvnx-7d04b1873367d0f68a2c0268a256da48\">\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48{\ncolor:#7bb0e7;\nborder-color:#7bb0e7;\n}\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48 .av-icon-char{\nfont-size:19px;\nline-height:19px;\n}\n<\/style>\n<span  class='av_font_icon av-qawvnx-7d04b1873367d0f68a2c0268a256da48 avia_animate_when_visible av-icon-style- avia-icon-pos-left avia-icon-animate'><span class='av-icon-char' aria-hidden='true' data-av_icon='\ue885' data-av_iconfont='entypo-fontello' ><\/span><\/span><\/h5>\n<p style=\"font-weight: 400;\">La recherche de la beaut\u00e9 a \u00e9t\u00e9 poursuivie par l&rsquo;humanit\u00e9 depuis ses d\u00e9buts. La tentative de percer le secret de la beaut\u00e9 a \u00e9t\u00e9 un objectif pour les philosophes, les artistes et les scientifiques tout au long de l&rsquo;histoire de l&rsquo;humanit\u00e9. Aujourd&rsquo;hui, la beaut\u00e9 du visage suscite encore plus d&rsquo;int\u00e9r\u00eat en raison du d\u00e9veloppement rapide de la chirurgie plastique et de l&rsquo;industrie cosm\u00e9tique. <strong>Au cours de la derni\u00e8re d\u00e9cennie, plusieurs \u00e9tudes ont montr\u00e9 que l&rsquo;attractivit\u00e9 du visage peut \u00eatre apprise par des machines.<\/strong> En effet, la pr\u00e9diction de la beaut\u00e9 du visage est une t\u00e2che sophistiqu\u00e9e, m\u00eame pour l&rsquo;homme, car pour un m\u00eame visage, diff\u00e9rentes personnes peuvent donner des notes de beaut\u00e9 diff\u00e9rentes. Ainsi, la pr\u00e9diction de la beaut\u00e9 du visage (FBP) a un biais subjectif \u00e9lev\u00e9. D&rsquo;autre part, de grandes donn\u00e9es \u00e9tiquet\u00e9es sont n\u00e9cessaires pour cr\u00e9er un syst\u00e8me efficace d&rsquo;apprentissage automatique pour la pr\u00e9diction de la beaut\u00e9 faciale, en particulier pour les m\u00e9thodes d&rsquo;apprentissage profond.<\/p>\n<h5>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-qawvnx-7d04b1873367d0f68a2c0268a256da48\">\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48{\ncolor:#7bb0e7;\nborder-color:#7bb0e7;\n}\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48 .av-icon-char{\nfont-size:19px;\nline-height:19px;\n}\n<\/style>\n<span  class='av_font_icon av-qawvnx-7d04b1873367d0f68a2c0268a256da48 avia_animate_when_visible av-icon-style- avia-icon-pos-left avia-icon-animate'><span class='av-icon-char' aria-hidden='true' data-av_icon='\ue885' data-av_iconfont='entypo-fontello' ><\/span><\/span><\/h5>\n<p style=\"font-weight: 400;\">L&rsquo;objectif de ce travail est de tirer parti des progr\u00e8s des architectures de Deep Learning pour fournir une estimation stable et pr\u00e9cise de la beaut\u00e9 des visages\u00a0\u00e0 partir d&rsquo;images de visages statiques.<\/p>\n<h5>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-qawvnx-7d04b1873367d0f68a2c0268a256da48\">\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48{\ncolor:#7bb0e7;\nborder-color:#7bb0e7;\n}\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48 .av-icon-char{\nfont-size:19px;\nline-height:19px;\n}\n<\/style>\n<span  class='av_font_icon av-qawvnx-7d04b1873367d0f68a2c0268a256da48 avia_animate_when_visible av-icon-style- avia-icon-pos-left avia-icon-animate'><span class='av-icon-char' aria-hidden='true' data-av_icon='\ue885' data-av_iconfont='entypo-fontello' ><\/span><\/span><\/h5>\n<p style=\"font-weight: 400;\"><strong>Dans ce travail, nous proposons un syst\u00e8me qui exploite la diversit\u00e9 des apprenants comme le montre la figure 1. Nous pr\u00e9sentons deux propositions principales. Premi\u00e8rement, nous proposons de combiner deux architectures CNN diff\u00e9rentes en une seule architecture (appel\u00e9e architecture \u00e0 deux branches) qui est form\u00e9e de bout en bout. Deuxi\u00e8mement, nous proposons de construire un ensemble de r\u00e9gressions o\u00f9 la pr\u00e9diction finale est donn\u00e9e par la moyenne de toutes les pr\u00e9dictions. Cette derni\u00e8re solution n&rsquo;a pas besoin d&rsquo;\u00eatre entra\u00een\u00e9e sur de nouveaux ensembles de validation. Plus pr\u00e9cis\u00e9ment, nous proposons des r\u00e9gressions d&rsquo;ensemble utilisant des architectures \u00e0 une branche (ResneXt-50 et Inception-v3) et notre architecture \u00e0 deux branches (REX-INCEP) entra\u00een\u00e9es avec diff\u00e9rentes fonctions de perte.<\/strong> Quatre fonctions de perte sont utilis\u00e9es dans notre approche, \u00e0 savoir MSE, ParamSmoothL1 dynamique, Huber dynamique et Tukey dynamique.<\/p>\n<\/div><\/section><\/div>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-qmiwrd-62499ca73b245e58b24e71429a88049a\">\n.flex_column.av-qmiwrd-62499ca73b245e58b24e71429a88049a{\nborder-radius:0px 0px 0px 0px;\npadding:0px 0px 0px 0px;\n}\n<\/style>\n<div  class='flex_column av-qmiwrd-62499ca73b245e58b24e71429a88049a av_one_half  avia-builder-el-7  el_after_av_one_half  el_before_av_textblock  flex_column_div av-zero-column-padding'     ><section  class='av_textblock_section av-l7hklx67-0eb9b2c59ff6cf2fb4de0bbaa4f13db3'   itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/BlogPosting\" itemprop=\"blogPost\" ><div class='avia_textblock'  itemprop=\"text\" ><h5>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-qawvnx-7d04b1873367d0f68a2c0268a256da48\">\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48{\ncolor:#7bb0e7;\nborder-color:#7bb0e7;\n}\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48 .av-icon-char{\nfont-size:19px;\nline-height:19px;\n}\n<\/style>\n<span  class='av_font_icon av-qawvnx-7d04b1873367d0f68a2c0268a256da48 avia_animate_when_visible av-icon-style- avia-icon-pos-left avia-icon-animate'><span class='av-icon-char' aria-hidden='true' data-av_icon='\ue885' data-av_iconfont='entypo-fontello' ><\/span><\/span><\/h5>\n<p>Notre approche est \u00e9valu\u00e9e sur la <a href=\"https:\/\/arxiv.org\/abs\/1801.06345\" target=\"_blank\" rel=\"noopener\">base de donn\u00e9es SCUT-FBP5500<\/a> en utilisant les deux sc\u00e9narios d&rsquo;\u00e9valuation fournis par les cr\u00e9ateurs de la base de donn\u00e9es : 60 %-40 % et validation crois\u00e9e \u00e0 cinq reprises. Dans les deux sc\u00e9narios d&rsquo;\u00e9valuation, notre approche surpasse l&rsquo;\u00e9tat de l&rsquo;art sur plusieurs m\u00e9triques. Ces comparaisons soulignent l&rsquo;efficacit\u00e9 des solutions propos\u00e9es pour la FBP. Elles montrent \u00e9galement que les pertes dynamiques robustes propos\u00e9es conduisent \u00e0 des estimateurs plus flexibles et plus pr\u00e9cis (<a href=\"https:\/\/github.com\/faresbougourzi\/CNN-ER_for_FBP\" target=\"_blank\" rel=\"noopener\">https:\/\/github.com\/faresbougourzi\/CNN-ER_for_FBP<\/a>).<\/p>\n<h5>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-qawvnx-7d04b1873367d0f68a2c0268a256da48\">\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48{\ncolor:#7bb0e7;\nborder-color:#7bb0e7;\n}\n.av_font_icon.av-qawvnx-7d04b1873367d0f68a2c0268a256da48 .av-icon-char{\nfont-size:19px;\nline-height:19px;\n}\n<\/style>\n<span  class='av_font_icon av-qawvnx-7d04b1873367d0f68a2c0268a256da48 avia_animate_when_visible av-icon-style- avia-icon-pos-left avia-icon-animate'><span class='av-icon-char' aria-hidden='true' data-av_icon='\ue885' data-av_iconfont='entypo-fontello' ><\/span><\/span><\/h5>\n<p><span style=\"color: #4392e8;\">Ce travail collaboratif est r\u00e9alis\u00e9 par plusieurs \u00e9quipes de recherche de :<\/span><\/p>\n<ul>\n<li>Institut des sciences appliqu\u00e9es et des syst\u00e8mes intelligents, Conseil national de la recherche d&rsquo;Italie, Lecce, 73100, Italie. ( Dr Fares Bougourzi, PostDoc)<\/li>\n<li>Universit\u00e9 du Pays Basque UPV\/EHU, San Sebastian 20018, Pays Basque, Espagne, IKERBASQUE, Fondation Basque pour la Science, Bilbao, 48012, Pays Basque, Espagne (Pr Fadi Dornaika).<\/li>\n<li>Universit\u00e9 Polytechnique Hauts-de-France, Universit\u00e9 de Lille, CNRS, UMR 8520, Valenciennes, 59313, Hauts-de-France, France ( Pr Abdelmalik Taleb-Ahmed).<\/li>\n<\/ul>\n<p>L&rsquo;approche d\u00e9velopp\u00e9e et les premiers r\u00e9sultats obtenus ont \u00e9t\u00e9 publi\u00e9s dans la r\u00e9f\u00e9rence [1].<br \/>\n<em>\u00a0[1] F. Bougourzi, F. Dornaika, A. Taleb-Ahmed, Deep learning based face beauty prediction via dynamic robust losses and ensemble regression, Knowledge-Based Systems, Vol 242, pp 108246, 2022.<\/em><\/p>\n<\/div><\/section><\/div>\n<section  class='av_textblock_section av-l7hl59i2-d18b1e5bf72b6ce34b57363f1ea293c9'   itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/BlogPosting\" itemprop=\"blogPost\" ><div class='avia_textblock'  itemprop=\"text\" ><p style=\"font-weight: 400; text-align: center;\"><strong><span style=\"color: #4392e8;\">Figure 1 : Notre proposition d&rsquo;approche EN-CNN.<\/span><\/strong><\/p>\n<p><a href=\"https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale2.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-54401 size-full\" src=\"https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale2.jpg\" alt=\"\" width=\"746\" height=\"1024\" srcset=\"https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale2.jpg 746w, https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale2-219x300.jpg 219w, https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale2-9x12.jpg 9w, https:\/\/www.iemn.fr\/wp-content\/uploads\/2022\/08\/beaute_faciale2-514x705.jpg 514w\" sizes=\"auto, (max-width: 746px) 100vw, 746px\" \/><\/a><\/p>\n<\/div><\/section>\n<section  class='av_textblock_section av-l7hks5zq-06080fdc6519ab5f0b783c3c3cb38845'   itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/BlogPosting\" itemprop=\"blogPost\" ><div class='avia_textblock'  itemprop=\"text\" ><p style=\"text-align: center;\"><div  class='avia-button-wrap av-rpqvoq-721f891c0eafd9f18b1e661271382e60-wrap avia-button-left  avia-builder-el-13  el_before_av_button  avia-builder-el-first'><a href='mailto:abdelmalik.taleb-ahmed@uphf.fr'  class='avia-button av-rpqvoq-721f891c0eafd9f18b1e661271382e60 av-link-btn avia-icon_select-yes-left-icon avia-size-small avia-position-left avia-color-silver'   aria-label=\"abdelmalik.taleb-ahmed@uphf.fr\"><span class='avia_button_icon avia_button_icon_left' aria-hidden='true' data-av_icon='\ue805' data-av_iconfont='entypo-fontello'><\/span><span class='avia_iconbox_title' >abdelmalik.taleb-ahmed@uphf.fr<\/span><\/a><\/div> \u00a0 <div  class='avia-button-wrap av-rpqvoq-316ac125ef0360b26d43ad706a9a5989-wrap avia-button-left  avia-builder-el-14  el_after_av_button  el_before_av_button'><a href='mailto:fares.bougourzi@isasi.cnr.it'  class='avia-button av-rpqvoq-316ac125ef0360b26d43ad706a9a5989 av-link-btn avia-icon_select-yes-left-icon avia-size-small avia-position-left avia-color-silver'   aria-label=\"fares.bougourzi@isasi.cnr.it\"><span class='avia_button_icon avia_button_icon_left' aria-hidden='true' data-av_icon='\ue805' data-av_iconfont='entypo-fontello'><\/span><span class='avia_iconbox_title' >fares.bougourzi@isasi.cnr.it<\/span><\/a><\/div> \u00a0 <div  class='avia-button-wrap av-rpqvoq-41e6be86e86262070df21f6ce6f24080-wrap avia-button-left  avia-builder-el-15  el_after_av_button  avia-builder-el-last'><a href='mailto:fadi.dornaika@ehu.eus'  class='avia-button av-rpqvoq-41e6be86e86262070df21f6ce6f24080 av-link-btn avia-icon_select-yes-left-icon avia-size-small avia-position-left avia-color-silver'   aria-label=\"fadi.dornaika@ehu.eus\"><span class='avia_button_icon avia_button_icon_left' aria-hidden='true' data-av_icon='\ue805' data-av_iconfont='entypo-fontello'><\/span><span class='avia_iconbox_title' >fadi.dornaika@ehu.eus<\/span><\/a><\/div><\/p>\n<\/div><\/section>","protected":false},"excerpt":{"rendered":"","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[297],"tags":[],"class_list":["post-54404","post","type-post","status-publish","format-standard","hentry","category-newsletter"],"_links":{"self":[{"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/posts\/54404","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/comments?post=54404"}],"version-history":[{"count":0,"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/posts\/54404\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/media?parent=54404"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/categories?post=54404"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.iemn.fr\/en\/wp-json\/wp\/v2\/tags?post=54404"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}