Multi-label active learning for image classification with asymmetrical conditional dependence

Jian Wu, Shiquan Zhao, Victor S. Sheng, Pengpeng Zhao, Zhiming Cui

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

3 Scopus citations

Abstract

Image classification is a hot topic of pattern recognition in computer vision. In order to achieve high accuracy of classification, a certain amount of high quality pictures are needed. As a matter of fact, high quality pictures are scarce. Active learning can solve such a problem. Label dependences play an important role in multi-label active learning for image classification. The interdependences between different labels are usually different and asymmetrical. This paper first brings the asymmetrical conditional label dependences into a novel active learning method for multi-label image classification based on the asymmetrical conditional label dependence, called ACDAL. Our extensive experimental results on three image and two non-image datasets show that our new approach ACDAL significantly outperforms existing approaches.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Multimedia and Expo, ICME 2016
PublisherIEEE Computer Society
ISBN (Electronic)9781467372589
DOIs
StatePublished - Aug 25 2016
Event2016 IEEE International Conference on Multimedia and Expo, ICME 2016 - Seattle, United States
Duration: Jul 11 2016Jul 15 2016

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2016-August
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2016 IEEE International Conference on Multimedia and Expo, ICME 2016
Country/TerritoryUnited States
CitySeattle
Period07/11/1607/15/16

Keywords

  • Active learning
  • asymmetrical label dependence
  • label correlation
  • multi-label image classification

Fingerprint

Dive into the research topics of 'Multi-label active learning for image classification with asymmetrical conditional dependence'. Together they form a unique fingerprint.

Cite this