Great progress has been made toward accurate face detection in recent years.However,the heavy model and expensive computation costs make it difficult to deploy many detectors on mobile and embedded devices where model...Great progress has been made toward accurate face detection in recent years.However,the heavy model and expensive computation costs make it difficult to deploy many detectors on mobile and embedded devices where model size and latency are highly constrained.In this paper,we present a millisecond-level anchor-free face detector,YuNet,which is specifically designed for edge devices.There are several key contributions in improving the efficiency-accuracy trade-off.First,we analyse the influential state-of-theart face detectors in recent years and summarize the rules to reduce the size of models.Then,a lightweight face detector,YuNet,is introduced.Our detector contains a tiny and efficient feature extraction backbone and a simplified pyramid feature fusion neck.To the best of our knowledge,YuNet has the best trade-off between accuracy and speed.It has only 75856 parameters and is less than 1/5 of other small-size detectors.In addition,a training strategy is presented for the tiny face detector,and it can effectively train models with the same distribution of the training set.The proposed YuNet achieves 81.1%mAP(single-scale)on the WIDER FACE validation hard track with a high inference efficiency(Intel i7-12700K:1.6ms per frame at 320×320).Because of its unique advantages,the repository for YuNet and its predecessors has been popular at GitHub and gained more than 11K stars at https://github.com/ShiqiYu/libfacedetection.Keywords:Face detection,object detection,computer version,lightweight,inference efficiency,anchor-free mechanism.展开更多
文摘目的基于2018版肝脏影像报告及数据系统(LI-RADS v2018),探讨CT及MRI对乙肝肝硬化背景下长径≤3 cm肝细胞性肝癌(hepatocellular carcinoma,HCC)的诊断价值。材料与方法回顾性分析本院2009年1月至2020年12月间73例有乙肝肝硬化病史且经病理证实占位长径≤3 cm HCC的患者,并在1个月内行CT及MRI检查。依据LI-RADS v2018,对每个病灶的CT及MRI图像的主次要征象及分级进行评估及比较。比较CT及MRI对长径≤3 cm HCC的诊断准确率。结果主要征象中的"包膜"表现在MRI中识别率高于CT(P<0.001)。次要征象中的扩散受限征象(86.3%)在MRI中具有最高识别率,而在CT的次要征象中马赛克征(25.0%)的识别率最高。CT及MRI检查的LI-RADS v2018分级差异有统计学意义(P<0.001)。MRI在以LR-4/5标准诊断HCC的准确率优于CT(P=0.046)。结论基于LI-RADS v2018,MRI检查对长径≤3 cm HCC的部分征象的识别率及HCC诊断准确率均高于CT检查。
基金supported in part by National Natural Science Foundation of China(No.61976144)the Stable Support Plan Program of Shenzhen Natural Science Fund,China(No.20200925155017002)the National Key Research and Development Program of China(No.2020 AAA0140000).
文摘Great progress has been made toward accurate face detection in recent years.However,the heavy model and expensive computation costs make it difficult to deploy many detectors on mobile and embedded devices where model size and latency are highly constrained.In this paper,we present a millisecond-level anchor-free face detector,YuNet,which is specifically designed for edge devices.There are several key contributions in improving the efficiency-accuracy trade-off.First,we analyse the influential state-of-theart face detectors in recent years and summarize the rules to reduce the size of models.Then,a lightweight face detector,YuNet,is introduced.Our detector contains a tiny and efficient feature extraction backbone and a simplified pyramid feature fusion neck.To the best of our knowledge,YuNet has the best trade-off between accuracy and speed.It has only 75856 parameters and is less than 1/5 of other small-size detectors.In addition,a training strategy is presented for the tiny face detector,and it can effectively train models with the same distribution of the training set.The proposed YuNet achieves 81.1%mAP(single-scale)on the WIDER FACE validation hard track with a high inference efficiency(Intel i7-12700K:1.6ms per frame at 320×320).Because of its unique advantages,the repository for YuNet and its predecessors has been popular at GitHub and gained more than 11K stars at https://github.com/ShiqiYu/libfacedetection.Keywords:Face detection,object detection,computer version,lightweight,inference efficiency,anchor-free mechanism.
