Pair-based uncertainty and diversity promoting early active learning for Person Re-identification

Wenhe Liu, Xiaojun Chang, Ling Chen, Dinh Phung, Xiaoqin Zhang, Yi Yang, Alexander G. Hauptmann

Research output: Contribution to journalArticleResearchpeer-review

8 Citations (Scopus)

Abstract

The effective training of supervised Person Re-identification (Re-ID) models requires sufficient pairwise labeled data. However, when there is limited annotation resource, it is difficult to collect pairwise labeled data. We consider a challenging and practical problem called Early Active Learning, which is applied to the early stage of experiments when there is no pre-labeled sample available as references for human annotating. Previous early active learning methods suffer from two limitations for Re-ID. First, these instance-based algorithms select instances rather than pairs, which can result in missing optimal pairs for Re-ID. Second, most of these methods only consider the representativeness of instances, which can result in selecting less diverse and less informative pairs. To overcome these limitations, we propose a novel pair-based active learning for Re-ID. Our algorithm selects pairs instead of instances from the entire dataset for annotation. Besides representativeness, we further take into account the uncertainty and the diversity in terms of pairwise relations. Therefore, our algorithm can produce the most representative, informative, and diverse pairs for Re-ID data annotation. Extensive experimental results on five benchmark Re-ID datasets have demonstrated the superiority of the proposed pair-based early active learning algorithm.

Original languageEnglish
Article number21
Number of pages15
JournalACM Transactions on Intelligent Systems and Technology
Volume11
Issue number2
DOIs
Publication statusPublished - Jan 2020

Keywords

  • Active learning
  • Person re-identification

Cite this