International Journal of Computer Vision

, Volume 100, Issue 3, pp 275–293

Weakly Supervised Localization and Learning with Generic Knowledge

Article

DOI: 10.1007/s11263-012-0538-3

Cite this article as:
Deselaers, T., Alexe, B. & Ferrari, V. Int J Comput Vis (2012) 100: 275. doi:10.1007/s11263-012-0538-3
  • 1.3k Downloads

Abstract

Learning a new object class from cluttered training images is very challenging when the location of object instances is unknown, i.e. in a weakly supervised setting. Many previous works require objects covering a large portion of the images. We present a novel approach that can cope with extensive clutter as well as large scale and appearance variations between object instances. To make this possible we exploit generic knowledge learned beforehand from images of other classes for which location annotation is available. Generic knowledge facilitates learning any new class from weakly supervised images, because it reduces the uncertainty in the location of its object instances. We propose a conditional random field that starts from generic knowledge and then progressively adapts to the new class. Our approach simultaneously localizes object instances while learning an appearance model specific for the class. We demonstrate this on several datasets, including the very challenging Pascal VOC 2007. Furthermore, our method allows training any state-of-the-art object detector in a weakly supervised fashion, although it would normally require object location annotations.

Keywords

Object detection Weakly supervised learning Transfer learning Conditional random fields 

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Thomas Deselaers
    • 1
    • 2
  • Bogdan Alexe
    • 1
  • Vittorio Ferrari
    • 1
  1. 1.Computer Vision LaboratoryETH ZurichZurichSwitzerland
  2. 2.GoogleZurichSwitzerland

Personalised recommendations