World Wide Web

, Volume 19, Issue 2, pp 199–215

Active domain adaptation with noisy labels for multimedia analysis

  • Gaowen Liu
  • Yan Yan
  • Ramanathan Subramanian
  • Jingkuan Song
  • Guoyu Lu
  • Nicu Sebe
Article

DOI: 10.1007/s11280-015-0343-3

Cite this article as:
Liu, G., Yan, Y., Subramanian, R. et al. World Wide Web (2016) 19: 199. doi:10.1007/s11280-015-0343-3
  • 481 Downloads

Abstract

Supervised learning methods require sufficient labeled examples to learn a good model for classification or regression. However, available labeled data are insufficient in many applications. Active learning (AL) and domain adaptation (DA) are two strategies to minimize the required amount of labeled data for model training. AL requires the domain expert to label a small number of highly informative examples to facilitate classification, while DA involves tuning the source domain knowledge for classification on the target domain. In this paper, we demonstrate how AL can efficiently minimize the required amount of labeled data for DA. Since the source and target domains usually have different distributions, it is possible that the domain expert may not have sufficient knowledge to answer each query correctly. We exploit our active DA framework to handle incorrect labels provided by domain experts. Experiments with multimedia data demonstrate the efficiency of our proposed framework for active DA with noisy labels.

Keywords

Active learning Domain adaptation Noisy labels Multimedia analysis 

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Gaowen Liu
    • 1
  • Yan Yan
    • 1
  • Ramanathan Subramanian
    • 2
  • Jingkuan Song
    • 1
  • Guoyu Lu
    • 3
  • Nicu Sebe
    • 1
  1. 1.Department of Computer Science and Information EngineeringUniversity of TrentoTrentoItaly
  2. 2.Advanced Digital Sciences Center, UIUCSingaporeSingapore
  3. 3.Department of Computer ScienceUniversity of DelawareNewarkUSA

Personalised recommendations