Facial Beauty Prediction Combined with Multi-Task Learning of Adaptive Sharing Policy and Attentional Feature Fusion
Facial beauty prediction (FBP) is a leading research subject in the field of artificial intelligence (AI), in which computers make facial beauty judgments and predictions similar to those of humans. At present, the methods are mainly based on deep neural networks. However, there still exist some pro...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/1/179 |
| _version_ | 1797358950977372160 |
|---|---|
| author | Junying Gan Heng Luo Junling Xiong Xiaoshan Xie Huicong Li Jianqiang Liu |
| author_facet | Junying Gan Heng Luo Junling Xiong Xiaoshan Xie Huicong Li Jianqiang Liu |
| author_sort | Junying Gan |
| collection | DOAJ |
| description | Facial beauty prediction (FBP) is a leading research subject in the field of artificial intelligence (AI), in which computers make facial beauty judgments and predictions similar to those of humans. At present, the methods are mainly based on deep neural networks. However, there still exist some problems such as insufficient label information and overfitting. Multi-task learning uses label information from multiple databases, which increases the utilization of label information and enhances the feature extraction ability of the network. Attentional feature fusion (AFF) combines semantic information and introduces an attention mechanism to reduce the risk of overfitting. In this study, the multi-task learning of an adaptive sharing policy combined with AFF is presented based on the adaptive sharing (AdaShare) network in FBP. First, an adaptive sharing policy is added to multi-task learning with ResNet18 as the backbone network. Second, the AFF is introduced at the short skip connections of the network. The proposed method improves the accuracy of FBP by solving the problems of insufficient label information and overfitting issues. The experimental results based on the large-scale Asia facial beauty database (LSAFBD) and SCUT-FBP5500 databases show that the proposed method outperforms the single-database single-task baseline and can be applied extensively in image classification and other fields. |
| first_indexed | 2024-03-08T15:08:38Z |
| format | Article |
| id | doaj.art-9e72772fced44d9398340dc35cd45f76 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-08T15:08:38Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-9e72772fced44d9398340dc35cd45f762024-01-10T14:54:59ZengMDPI AGElectronics2079-92922023-12-0113117910.3390/electronics13010179Facial Beauty Prediction Combined with Multi-Task Learning of Adaptive Sharing Policy and Attentional Feature FusionJunying Gan0Heng Luo1Junling Xiong2Xiaoshan Xie3Huicong Li4Jianqiang Liu5Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, ChinaFaculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, ChinaFaculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, ChinaFaculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, ChinaFaculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, ChinaFaculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, ChinaFacial beauty prediction (FBP) is a leading research subject in the field of artificial intelligence (AI), in which computers make facial beauty judgments and predictions similar to those of humans. At present, the methods are mainly based on deep neural networks. However, there still exist some problems such as insufficient label information and overfitting. Multi-task learning uses label information from multiple databases, which increases the utilization of label information and enhances the feature extraction ability of the network. Attentional feature fusion (AFF) combines semantic information and introduces an attention mechanism to reduce the risk of overfitting. In this study, the multi-task learning of an adaptive sharing policy combined with AFF is presented based on the adaptive sharing (AdaShare) network in FBP. First, an adaptive sharing policy is added to multi-task learning with ResNet18 as the backbone network. Second, the AFF is introduced at the short skip connections of the network. The proposed method improves the accuracy of FBP by solving the problems of insufficient label information and overfitting issues. The experimental results based on the large-scale Asia facial beauty database (LSAFBD) and SCUT-FBP5500 databases show that the proposed method outperforms the single-database single-task baseline and can be applied extensively in image classification and other fields.https://www.mdpi.com/2079-9292/13/1/179attentional feature fusionfacial beauty predictionimage classificationmulti-task learning |
| spellingShingle | Junying Gan Heng Luo Junling Xiong Xiaoshan Xie Huicong Li Jianqiang Liu Facial Beauty Prediction Combined with Multi-Task Learning of Adaptive Sharing Policy and Attentional Feature Fusion Electronics attentional feature fusion facial beauty prediction image classification multi-task learning |
| title | Facial Beauty Prediction Combined with Multi-Task Learning of Adaptive Sharing Policy and Attentional Feature Fusion |
| title_full | Facial Beauty Prediction Combined with Multi-Task Learning of Adaptive Sharing Policy and Attentional Feature Fusion |
| title_fullStr | Facial Beauty Prediction Combined with Multi-Task Learning of Adaptive Sharing Policy and Attentional Feature Fusion |
| title_full_unstemmed | Facial Beauty Prediction Combined with Multi-Task Learning of Adaptive Sharing Policy and Attentional Feature Fusion |
| title_short | Facial Beauty Prediction Combined with Multi-Task Learning of Adaptive Sharing Policy and Attentional Feature Fusion |
| title_sort | facial beauty prediction combined with multi task learning of adaptive sharing policy and attentional feature fusion |
| topic | attentional feature fusion facial beauty prediction image classification multi-task learning |
| url | https://www.mdpi.com/2079-9292/13/1/179 |
| work_keys_str_mv | AT junyinggan facialbeautypredictioncombinedwithmultitasklearningofadaptivesharingpolicyandattentionalfeaturefusion AT hengluo facialbeautypredictioncombinedwithmultitasklearningofadaptivesharingpolicyandattentionalfeaturefusion AT junlingxiong facialbeautypredictioncombinedwithmultitasklearningofadaptivesharingpolicyandattentionalfeaturefusion AT xiaoshanxie facialbeautypredictioncombinedwithmultitasklearningofadaptivesharingpolicyandattentionalfeaturefusion AT huicongli facialbeautypredictioncombinedwithmultitasklearningofadaptivesharingpolicyandattentionalfeaturefusion AT jianqiangliu facialbeautypredictioncombinedwithmultitasklearningofadaptivesharingpolicyandattentionalfeaturefusion |