CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Mask Guided Knowledge Distillation for Single Shot Detector
Zhu Yousong1,2; Zhao Chaoyang1,2; Han Chenxia3; Wang Jinqiao1,2; Lu Hanqing1,2
2019
Conference Name2019 IEEE International Conference on Multimedia and Expo (ICME)
Conference Date2019-7-8
Conference PlaceShanghai, China
PublisherIEEE
Abstract

In this paper, we explore the idea of distilling small networks
for object detection task. More specifically, we propose a twostage approach to learn more compact and efficient detectors
under the single-shot object detection framework by leveraging knowledge distillation. During the 1st stage, we learn the
feature maps of the student model for each of the prediction
head from the teacher model. Instead of fitting the whole feature map directly, here we propose the mask guided structure
including not only the entire feature map (i.e. global features)
but also region features covered by the object (i.e. local features), which can significantly improve the performance of
the student network. For the 2nd stage, the ground-truth is
used to further refine the performance. Experimental results
on PASCAL VOC and KITTI dataset demonstrate the effectiveness of our proposed approach. We achieve 56.88% mAP
on VOC2007 at 143 FPS with the backbone of 1/8 VGG16.

KeywordObject Detection Knowledge Distillation
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23586
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorZhu Yousong
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Wuhan University
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhu Yousong,Zhao Chaoyang,Han Chenxia,et al. Mask Guided Knowledge Distillation for Single Shot Detector[C]:IEEE,2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
567-camera-ready-val(1512KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhu Yousong]'s Articles
[Zhao Chaoyang]'s Articles
[Han Chenxia]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu Yousong]'s Articles
[Zhao Chaoyang]'s Articles
[Han Chenxia]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu Yousong]'s Articles
[Zhao Chaoyang]'s Articles
[Han Chenxia]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 567-camera-ready-validated.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.