Hierarchical Object Representations for Visual Recognition via Weakly Supervised Learning

  • Tianzhu Zhang
  • Rui Cai
  • Zhiwei Li
  • Lei Zhang
  • Hanqing Lu
Conference paper

DOI: 10.1007/978-3-642-37331-2_36

Part of the Lecture Notes in Computer Science book series (LNCS, volume 7724)
Cite this paper as:
Zhang T., Cai R., Li Z., Zhang L., Lu H. (2013) Hierarchical Object Representations for Visual Recognition via Weakly Supervised Learning. In: Lee K.M., Matsushita Y., Rehg J.M., Hu Z. (eds) Computer Vision – ACCV 2012. ACCV 2012. Lecture Notes in Computer Science, vol 7724. Springer, Berlin, Heidelberg

Abstract

In this paper, we propose a weakly supervised approach to learn hierarchical object representations for visual recognition. The learning process is carried out in a bottom-up manner to discover latent visual patterns in multiple scales. To relieve the disturbance of complex backgrounds in natural images, bounding boxes of foreground objects are adopted as weak knowledge in the learning stage to promote those visual patterns which are more related to the target objects. The difference between the patterns of foreground objects and backgrounds is relatively vague at low-levels, but becomes more distinct along with the feature transformations to high-levels. In the test stage, an input image is verified against the learnt patterns level-by-level, and the responses at each level construct a hierarchy of representations which indicates the occurring possibilities of the target object at various scales. Experiments on two PASCAL datasets showed encouraging results for visual recognition.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Tianzhu Zhang
    • 1
  • Rui Cai
    • 2
  • Zhiwei Li
    • 2
  • Lei Zhang
    • 2
  • Hanqing Lu
    • 1
  1. 1.Institute of AutomationChinese Academy of SciencesBeijingP.R. China
  2. 2.Microsoft Research AsiaBeijingP.R. China

Personalised recommendations