{"title":"基于堆叠注意力沙漏网络的鲁棒人脸标记检测","authors":"Ying Huang, He Huang","doi":"10.1016/j.neunet.2022.10.021","DOIUrl":null,"url":null,"abstract":"<div><p><span><span><span>Deep learning based facial landmark detection (FLD) has made rapid progress. However, the accuracy and robustness of </span>FLD algorithms are degraded heavily when the face is subject to diverse expressions, posture deflection, </span>partial occlusion and other uncertain circumstances. To learn more discriminative representations and reduce the negative effect caused by outliers, a stacked attention hourglass network (SAHN) is proposed for FLD, where new </span>attention mechanism<span> is introduced. Basically, in the design of SAHN, a spatial attention residual (SAR) unit is constructed such that relevant areas of facial landmarks are specially emphasized and essential features of different scales can be well extracted, and a channel attention branch (CAB) is introduced to better guide the next-level hourglass network for feature extraction. Due to the introduction of SAR and CAB, only two hourglass networks are stacked as the proposed SAHN with fewer parameters, which is different from traditional SHNs stacked by four hourglass networks. Furthermore, a variable robustness (VR) loss function is introduced for the training of SAHN. The robustness of the proposed model for FLD is guaranteed with the help of the VR loss by adaptively adjusting a continuous parameter. Extensive experimental results on three public datasets including 300W, WFLW and COFW confirm that our method is superior to some previous ones.</span></p></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":null,"pages":null},"PeriodicalIF":6.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Stacked attention hourglass network based robust facial landmark detection\",\"authors\":\"Ying Huang, He Huang\",\"doi\":\"10.1016/j.neunet.2022.10.021\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p><span><span><span>Deep learning based facial landmark detection (FLD) has made rapid progress. However, the accuracy and robustness of </span>FLD algorithms are degraded heavily when the face is subject to diverse expressions, posture deflection, </span>partial occlusion and other uncertain circumstances. To learn more discriminative representations and reduce the negative effect caused by outliers, a stacked attention hourglass network (SAHN) is proposed for FLD, where new </span>attention mechanism<span> is introduced. Basically, in the design of SAHN, a spatial attention residual (SAR) unit is constructed such that relevant areas of facial landmarks are specially emphasized and essential features of different scales can be well extracted, and a channel attention branch (CAB) is introduced to better guide the next-level hourglass network for feature extraction. Due to the introduction of SAR and CAB, only two hourglass networks are stacked as the proposed SAHN with fewer parameters, which is different from traditional SHNs stacked by four hourglass networks. Furthermore, a variable robustness (VR) loss function is introduced for the training of SAHN. The robustness of the proposed model for FLD is guaranteed with the help of the VR loss by adaptively adjusting a continuous parameter. Extensive experimental results on three public datasets including 300W, WFLW and COFW confirm that our method is superior to some previous ones.</span></p></div>\",\"PeriodicalId\":49763,\"journal\":{\"name\":\"Neural Networks\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":6.0000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neural Networks\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0893608022004178\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0893608022004178","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
Stacked attention hourglass network based robust facial landmark detection
Deep learning based facial landmark detection (FLD) has made rapid progress. However, the accuracy and robustness of FLD algorithms are degraded heavily when the face is subject to diverse expressions, posture deflection, partial occlusion and other uncertain circumstances. To learn more discriminative representations and reduce the negative effect caused by outliers, a stacked attention hourglass network (SAHN) is proposed for FLD, where new attention mechanism is introduced. Basically, in the design of SAHN, a spatial attention residual (SAR) unit is constructed such that relevant areas of facial landmarks are specially emphasized and essential features of different scales can be well extracted, and a channel attention branch (CAB) is introduced to better guide the next-level hourglass network for feature extraction. Due to the introduction of SAR and CAB, only two hourglass networks are stacked as the proposed SAHN with fewer parameters, which is different from traditional SHNs stacked by four hourglass networks. Furthermore, a variable robustness (VR) loss function is introduced for the training of SAHN. The robustness of the proposed model for FLD is guaranteed with the help of the VR loss by adaptively adjusting a continuous parameter. Extensive experimental results on three public datasets including 300W, WFLW and COFW confirm that our method is superior to some previous ones.
期刊介绍:
Neural Networks is a platform that aims to foster an international community of scholars and practitioners interested in neural networks, deep learning, and other approaches to artificial intelligence and machine learning. Our journal invites submissions covering various aspects of neural networks research, from computational neuroscience and cognitive modeling to mathematical analyses and engineering applications. By providing a forum for interdisciplinary discussions between biology and technology, we aim to encourage the development of biologically-inspired artificial intelligence.