Multi-label active learning for image classification

Jian Wu, Victor S. Sheng, Jing Zhang, Pengpeng Zhao, Zhiming Cui

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Scopus citations

Abstract

Multi-label image data is becoming ubiquitous. Image semantic understanding is typically formulated as a classification problem. This paper focuses on multi-label active learning for image classification. It first extends a traditional example based active learning method for multilabel active learning for image classification. Since the traditional example based active method doesn't work well, we propose a novel example-label based multi-label active learning method. Our experimental results on two image datasets demonstrate that the proposed method significantly reduces the labeling workload and improves the performance of the built classifier. Additionally, we conduct experiments on two other types of multi-label datasets for validating the versatility of our proposed method, and the experimental results show the consistent effect.

Original languageEnglish
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5227-5231
Number of pages5
ISBN (Electronic)9781479957514
DOIs
StatePublished - Jan 28 2014

Publication series

Name2014 IEEE International Conference on Image Processing, ICIP 2014

    Fingerprint

Keywords

  • Multi-label
  • active learning
  • example-label pair
  • image classification

Cite this

Wu, J., Sheng, V. S., Zhang, J., Zhao, P., & Cui, Z. (2014). Multi-label active learning for image classification. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 5227-5231). [7026058] (2014 IEEE International Conference on Image Processing, ICIP 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7026058