Quannet: Joint image compression and classification over channels with limited bandwidth

Lahiru D. Chamain, Sen Ching Samson Cheung, Zhi Ding

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

18 Scopus citations

Abstract

The performance of cloud based image classification depends critically on its allocated bandwidth. Traditional data compression methods can negatively impact classification accuracy under limited bandwidth. We investigate the design of bandwidth efficient quantization for image encoding and compression with minimum classification accuracy loss. This work develops a simple neural network framework for joint quantization and classification. The proposed 'QuanNet' can optimize the quantization intervals of JPEG2000 encoder to minimize the classification loss. We show that our quantizer optimization can achieve significant accuracy improvement for a given channel bandwidth. Similarly, significant bandwidth can be saved to achieve a desired accuracy for cloud based image classification.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019
Pages338-343
Number of pages6
ISBN (Electronic)9781538695524
DOIs
StatePublished - Jul 2019
Event2019 IEEE International Conference on Multimedia and Expo, ICME 2019 - Shanghai, China
Duration: Jul 8 2019Jul 12 2019

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2019-July
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2019 IEEE International Conference on Multimedia and Expo, ICME 2019
Country/TerritoryChina
CityShanghai
Period7/8/197/12/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

  • Classification
  • Compression
  • Learning

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Quannet: Joint image compression and classification over channels with limited bandwidth'. Together they form a unique fingerprint.

Cite this