Weak labeled multi-label active learning for image classification

Shiquan Zhao, Jian Wu, Victor S. Sheng, Chen Ye, Peng Peng Zhao, Zhiming Cui

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

8 Scopus citations

Abstract

In order to achieve better classification performance with even fewer labeled images, active learning is suitable for these situations. Several active learning methods have been proposed for multi-label image classification, but all of them assume that all training images with complete labels. However, as a matter of fact, it is very difficult to get complete labels for each example, especially when the size of labels in a multi-label domain is huge. Usually, only partial labels are available. This is one kind of "weak label" problems. This paper proposes an ingeniously solution to this "weak label" problem on multi-label active learning for image classification (called WLMAL). It explores label correlation on the weak label problem with the help of input features, and then utilizes label correlation to evaluate the informativeness of each example-label pair in a multi-label dataset for active sampling. Our experimental results on three real-world datasets show that our proposed approach WLMAL consistently outperforms existing approaches significantly.

Original languageEnglish
Title of host publicationMM 2015 - Proceedings of the 2015 ACM Multimedia Conference
PublisherAssociation for Computing Machinery, Inc
Pages1127-1130
Number of pages4
ISBN (Electronic)9781450334594
DOIs
StatePublished - Oct 13 2015
Event23rd ACM International Conference on Multimedia, MM 2015 - Brisbane, Australia
Duration: Oct 26 2015Oct 30 2015

Publication series

NameMM 2015 - Proceedings of the 2015 ACM Multimedia Conference

Conference

Conference23rd ACM International Conference on Multimedia, MM 2015
Country/TerritoryAustralia
CityBrisbane
Period10/26/1510/30/15

Keywords

  • Label Correlation
  • Label Dependence.
  • Multi-Label Active Learning
  • Multi-Label Image Classification
  • Weak Label

Fingerprint

Dive into the research topics of 'Weak labeled multi-label active learning for image classification'. Together they form a unique fingerprint.

Cite this