Minimal difference sampling for active learning image classification

Jian Wu, Sheng Li Sheng, Peng Peng Zhao, Zhi Ming Cui

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Aiming at the problem of measuring the voting disagreement of committee, a minimal difference sampling method for image classification was proposed. It selects the sample with the minimal difference of two highest class probabilities voted by committee. The experimental results show that this method effectively enhances the classification accuracy compared with EQB and nEQB. Furthermore, the influence of the number of models in the decision-making committee was analyzed and discussed. The experimental results show that the proposed method always outperforms nEQB with the same number of models.

Original languageEnglish
Pages (from-to)107-114
Number of pages8
JournalTongxin Xuebao/Journal on Communications
Issue number1
StatePublished - Jan 2014


  • Active learning
  • Committee voting
  • Image classification
  • Minimal difference
  • Sampling strategy


Dive into the research topics of 'Minimal difference sampling for active learning image classification'. Together they form a unique fingerprint.

Cite this