Knowledge Commons of Institute of Automation,CAS
YuNet: A Tiny Millisecond-level Face Detector | |
Wei Wu1; Hanyang Peng2; Shiqi Yu1 | |
发表期刊 | Machine Intelligence Research |
ISSN | 2731-538X |
2023 | |
卷号 | 20期号:5页码:656-665 |
摘要 | 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-the art 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. |
关键词 | Face detection, object detection, computer version, lightweight, inference efficiency, anchor-free mechanism |
DOI | 10.1007/s11633-023-1423-y |
七大方向——子方向分类 | 其他 |
国重实验室规划方向分类 | 其他 |
是否有论文关联数据集需要存交 | 否 |
中文导读 | https://mp.weixin.qq.com/s/7uMElM6dPvsa59pO6Z8yfQ |
视频解析 | https://www.bilibili.com/video/BV1D94y1c7Eo/ |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56001 |
专题 | 学术期刊_Machine Intelligence Research |
作者单位 | 1.Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China 2.Pengcheng Laboratory, Shenzhen 518066, China |
推荐引用方式 GB/T 7714 | Wei Wu,Hanyang Peng,Shiqi Yu. YuNet: A Tiny Millisecond-level Face Detector[J]. Machine Intelligence Research,2023,20(5):656-665. |
APA | Wei Wu,Hanyang Peng,&Shiqi Yu.(2023).YuNet: A Tiny Millisecond-level Face Detector.Machine Intelligence Research,20(5),656-665. |
MLA | Wei Wu,et al."YuNet: A Tiny Millisecond-level Face Detector".Machine Intelligence Research 20.5(2023):656-665. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
MIR-2022-09-275.pdf(4720KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论