skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Acceleration of Target Detection Based on Forced Knowledge Distillation

IOP conference series. Materials Science and Engineering, 2019-10, Vol.612 (3), p.32007 [Peer Reviewed Journal]

Published under licence by IOP Publishing Ltd ;2019. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;ISSN: 1757-8981 ;EISSN: 1757-899X ;DOI: 10.1088/1757-899X/612/3/032007

Full text available

Citations Cited by
  • Title:
    Acceleration of Target Detection Based on Forced Knowledge Distillation
  • Author: Wen, Jing ; Gong, Chenggui
  • Subjects: Computer vision ; Distillation ; Feature extraction ; Machine learning ; Natural language processing ; Target detection ; Task complexity
  • Is Part Of: IOP conference series. Materials Science and Engineering, 2019-10, Vol.612 (3), p.32007
  • Description: In recent years, deep learning has achieved outstanding results on many problems such as computer vision, natural language processing and so on. The research of network model compression and acceleration can make the network model run efficiently on resource-constrained devices by greatly reducing the amount of computation of the network when the performance of the network decreases slightly. At present, knowledge distillation has achieved good results in classification tasks, but it shows strong limitations in the face of more complex tasks like detection. In this work, we propose a forced knowledge distillation framework, which focuses on improving the ability of feature extraction in detection. The whole model can be compact and fast without losing much accuracy. We use PASCAL VOC, KITTI and MSCOCO data sets to make a comprehensive evaluation. The results show that the forced knowledge distillation framework can fully learn the knowledge of teacher networks and achieve better detection results in smaller student networks.
  • Publisher: Bristol: IOP Publishing
  • Language: English
  • Identifier: ISSN: 1757-8981
    EISSN: 1757-899X
    DOI: 10.1088/1757-899X/612/3/032007
  • Source: Geneva Foundation Free Medical Journals at publisher websites
    IOPscience (Open Access)
    Institute of Physics IOP eJournals Open Access
    ProQuest Central
Back to results list
Go to Previous pagePrevious Result  4 NextGo to Next page
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait