Deep Learning for Facial Beauty Prediction
Facial beauty prediction (FBP) is a burgeoning issue for attractiveness evaluation, which aims to make assessment consistent with human opinion. Since FBP is a regression problem, to handle this issue, there are data-driven methods for finding the relations between facial features and beauty assessm...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/11/8/391 |
| _version_ | 1797559302553075712 |
|---|---|
| author | Kerang Cao Kwang-nam Choi Hoekyung Jung Lini Duan |
| author_facet | Kerang Cao Kwang-nam Choi Hoekyung Jung Lini Duan |
| author_sort | Kerang Cao |
| collection | DOAJ |
| description | Facial beauty prediction (FBP) is a burgeoning issue for attractiveness evaluation, which aims to make assessment consistent with human opinion. Since FBP is a regression problem, to handle this issue, there are data-driven methods for finding the relations between facial features and beauty assessment. Recently, deep learning methods have shown its amazing capacity for feature representation and analysis. Convolutional neural networks (CNNs) have shown tremendous performance on facial recognition and comprehension, which are proved as an effective method for facial feature exploration. Lately, there are well-designed networks with efficient structures investigated for better representation performance. However, these designs concentrate on the effective block but do not build an efficient information transmission pathway, which led to a sub-optimal capacity for feature representation. Furthermore, these works cannot find the inherent correlations of feature maps, which also limits the performance. In this paper, an elaborate network design for FBP issue is proposed for better performance. A residual-in-residual (RIR) structure is introduced to the network for passing the gradient flow deeper, and building a better pathway for information transmission. By applying the RIR structure, a deeper network can be established for better feature representation. Besides the RIR network design, an attention mechanism is introduced to exploit the inner correlations among features. We investigate a joint spatial-wise and channel-wise attention (SCA) block to distribute the importance among features, which finds a better representation for facial information. Experimental results show our proposed network can predict facial beauty closer to a human’s assessment than state-of-the-arts. |
| first_indexed | 2024-03-10T17:43:24Z |
| format | Article |
| id | doaj.art-0ac6b20907934e40a12c2b9cab92c094 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-10T17:43:24Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-0ac6b20907934e40a12c2b9cab92c0942023-11-20T09:36:42ZengMDPI AGInformation2078-24892020-08-0111839110.3390/info11080391Deep Learning for Facial Beauty PredictionKerang Cao0Kwang-nam Choi1Hoekyung Jung2Lini Duan3Department of Computer Science and Engineering, Shenyang University of Chemical Technology, Shenyang 110000, ChinaNTIS Center, Korea Institute of Science and Technology Information, Seoul 34113, KoreaDepartment of Computer Engineering, Paichai University, Daejeon 35345, KoreaDepartment of Computer Science and Engineering, Shenyang University of Chemical Technology, Shenyang 110000, ChinaFacial beauty prediction (FBP) is a burgeoning issue for attractiveness evaluation, which aims to make assessment consistent with human opinion. Since FBP is a regression problem, to handle this issue, there are data-driven methods for finding the relations between facial features and beauty assessment. Recently, deep learning methods have shown its amazing capacity for feature representation and analysis. Convolutional neural networks (CNNs) have shown tremendous performance on facial recognition and comprehension, which are proved as an effective method for facial feature exploration. Lately, there are well-designed networks with efficient structures investigated for better representation performance. However, these designs concentrate on the effective block but do not build an efficient information transmission pathway, which led to a sub-optimal capacity for feature representation. Furthermore, these works cannot find the inherent correlations of feature maps, which also limits the performance. In this paper, an elaborate network design for FBP issue is proposed for better performance. A residual-in-residual (RIR) structure is introduced to the network for passing the gradient flow deeper, and building a better pathway for information transmission. By applying the RIR structure, a deeper network can be established for better feature representation. Besides the RIR network design, an attention mechanism is introduced to exploit the inner correlations among features. We investigate a joint spatial-wise and channel-wise attention (SCA) block to distribute the importance among features, which finds a better representation for facial information. Experimental results show our proposed network can predict facial beauty closer to a human’s assessment than state-of-the-arts.https://www.mdpi.com/2078-2489/11/8/391deep learningfacial beauty predictionconvolutional neural network |
| spellingShingle | Kerang Cao Kwang-nam Choi Hoekyung Jung Lini Duan Deep Learning for Facial Beauty Prediction Information deep learning facial beauty prediction convolutional neural network |
| title | Deep Learning for Facial Beauty Prediction |
| title_full | Deep Learning for Facial Beauty Prediction |
| title_fullStr | Deep Learning for Facial Beauty Prediction |
| title_full_unstemmed | Deep Learning for Facial Beauty Prediction |
| title_short | Deep Learning for Facial Beauty Prediction |
| title_sort | deep learning for facial beauty prediction |
| topic | deep learning facial beauty prediction convolutional neural network |
| url | https://www.mdpi.com/2078-2489/11/8/391 |
| work_keys_str_mv | AT kerangcao deeplearningforfacialbeautyprediction AT kwangnamchoi deeplearningforfacialbeautyprediction AT hoekyungjung deeplearningforfacialbeautyprediction AT liniduan deeplearningforfacialbeautyprediction |