Knowledge Commons of Institute of Automation,CAS
Learning Lightweight Face Detector with Knowledge Distillation | |
Jin, Haibo1,2; Zhang, Shifeng1,2![]() ![]() ![]() | |
2019 | |
会议名称 | IAPR International Conference On Biometrics |
会议日期 | 2019 |
会议地点 | 希腊 |
摘要 | Despite that face detection has progressed significantly in recent years, it is still a challenging task to get a fast face detector with competitive performance, especially on CPU based devices. In this paper, we propose a novel loss function based on knowledge distillation to boost the performance of lightweight face detectors. More specifically, a student detector learns additional soft label from a teacher detector by mimicking its classification map. To make the knowledge transfer more efficient, a threshold function is designed to assign threshold values adaptively for different objectness scores such that only the informative samples are used for mimicking. Experiments on FDDB and WIDER FACE show that the proposed method improves the performance of face detectors consistently. With the help of the proposed training method, we get a CPU real-time face detector that runs at 20 FPS while being state-of-the-art on performance among CPU based detectors. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 生物特征识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39052 |
专题 | 多模态人工智能系统全国重点实验室_生物识别与安全技术 |
作者单位 | 1.Institute of Automation Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Jin, Haibo,Zhang, Shifeng,Zhu, Xiangyu,et al. Learning Lightweight Face Detector with Knowledge Distillation[C],2019. |
条目包含的文件 | 条目无相关文件。 |
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