Weak-Labeled Active Learning With Conditional Label Dependence for Multilabel Image Classification

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

Research output: Contribution to journalArticlepeer-review

27 Scopus citations


Multilabel image classification has been a hot topic in the field of computer vision and image understanding in recent years. To achieve better classification performance with fewer labeled images, multilabel active learning is used for this scenario. Several active learning methods have been proposed for multilabel image classification. However, all of them assume that either all training images have complete labels or label correlations are given at the beginning. These two assumptions are unrealistic. In fact, it is very difficult to obtain complete labels for each example, in particular when the size of labels in a multilabel dataset is very large. Typically, only partial labels are available. This is one type of "weak label" problem. To solve this weak label problem inside multilabel active learning, this paper proposes a novel solution called AE-WLMAL. AE-WLMAL explores conditional label correlations on the weak label problem with the help of input features and then utilizes label correlations to construct a unified sampling strategy and evaluate the informativeness of each example-label pair in a multilabel dataset for active sampling. In addition, a pruning strategy is adopted to further improve its computation efficiency. Moreover, AE-WLAML exploits label correlations to infer labels for unlabeled images, which further reduces human labeling cost. Our experimental results on seven real-world datasets show that AE-WLMAL consistently outperforms existing approaches.

Original languageEnglish
Article number7814308
Pages (from-to)1156-1169
Number of pages14
JournalIEEE Transactions on Multimedia
Issue number6
StatePublished - Jun 2017


  • Multilabel active learning
  • conditional label dependence
  • image classification
  • label correlation
  • weak label


Dive into the research topics of 'Weak-Labeled Active Learning With Conditional Label Dependence for Multilabel Image Classification'. Together they form a unique fingerprint.

Cite this