ATTENTION-GUIDED KNOWLEDGE DISTILLATION FOR EFFICIENT SINGLE-STAGE DETECTOR
Wang, Tong1,2; Zhu, Yousong1,3; Zhao, Chaoyang1; Zhao, Xu1; Wang, Jinqiao1,2,4; Tang, Ming1
2021-07
会议名称IEEE International Conference on Multimedia & Expo(ICME)
页码1-6
会议日期2021-7-5
会议地点Online
摘要

Knowledge distillation has been successfully applied in image classification for model acceleration. There are also some works employing this technique to object detection, but they all treat different feature regions equally when performing feature mimic. In this paper, we propose an end-to-end attention-guided knowledge distillation method to train efficient single-stage detectors with much smaller backbones.
More specifically, we introduce an attention mechanism to prioritize the transfer of important knowledge by focusing on a sparse set of hard samples, leading to a more thorough distillation process. In addition, the proposed distillation method also provides an easy way to train efficient detectors without tedious ImageNet pre-training procedure. Extensive experiments on PASCAL VOC and CityPersons datasets demonstrate the effectiveness of the proposed approach. We achieve 57.96% and 69.48% mAP on VOC07 with the backbone of 1/8 VGG16 and 1/4 VGG16, greatly outperforming their ImageNet pre-trained counterparts by 11.7% and 7.1% respectively.
 

学科领域模式识别
学科门类工学::计算机科学与技术(可授工学、理学学位)
收录类别EI
资助项目National Natural Science Foundation of China[61806200] ; National Nature Science Foundation of China[61876086] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61772527] ; National Nature Science Foundation of China[61876086] ; National Natural Science Foundation of China[61806200]
语种英语
七大方向——子方向分类目标检测、跟踪与识别
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/47417
专题模式识别国家重点实验室_图像与视频分析
作者单位1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
3.ObjectEye Inc., Beijing, China
4.NEXWISE Co., Ltd, Guangzhou, China
第一作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Wang, Tong,Zhu, Yousong,Zhao, Chaoyang,et al. ATTENTION-GUIDED KNOWLEDGE DISTILLATION FOR EFFICIENT SINGLE-STAGE DETECTOR[C],2021:1-6.
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
ATTENTION-GUIDED KNO(574KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Tong]的文章
[Zhu, Yousong]的文章
[Zhao, Chaoyang]的文章
百度学术
百度学术中相似的文章
[Wang, Tong]的文章
[Zhu, Yousong]的文章
[Zhao, Chaoyang]的文章
必应学术
必应学术中相似的文章
[Wang, Tong]的文章
[Zhu, Yousong]的文章
[Zhao, Chaoyang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ATTENTION-GUIDED KNOWLEDGE DISTILLATION FOR EFFICIENT SINGLE-STAGE-ICME2021.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。