Large-scale knowledge transfer for object localization in ImageNet

M. Guillaumin, V. Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution


ImageNet is a large-scale database of object classes with millions of images. Unfortunately only a small fraction of them is manually annotated with bounding-boxes. This prevents useful developments, such as learning reliable object detectors for thousands of classes. In this paper we propose to automatically populate ImageNet with many more bounding-boxes, by leveraging existing manual annotations. The key idea is to localize objects of a target class for which annotations are not available, by transferring knowledge from related source classes with available annotations. We distinguish two kinds of source classes: ancestors and siblings. Each source provides knowledge about the plausible location, appearance and context of the target objects, which induces a probability distribution over windows in images of the target class. We learn to combine these distributions so as to maximize the location accuracy of the most probable window. Finally, we employ the combined distribution in a procedure to jointly localize objects in all images of the target class. Through experiments on 0.5 million images from 219 classes we show that our technique (i) annotates a wide range of classes with bounding-boxes; (ii) effectively exploits the hierarchical structure of ImageNet, since all sources and types of knowledge we propose contribute to the results; (iii) scales efficiently.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Number of pages8
ISBN (Electronic)978-1-4673-1227-1
Publication statusPublished - 1 Jun 2012


  • knowledge management
  • object detection
  • statistical distributions
  • visual databases
  • ImageNet
  • ancestor source class
  • bounding-boxes
  • large-scale database
  • large-scale knowledge transfer
  • object class
  • object localization
  • probability distribution
  • sibling source class
  • target object appearance
  • target object context
  • target object location
  • Airplanes
  • Context
  • Prototypes
  • Support vector machines
  • Training
  • Vehicles
  • Visualization


Dive into the research topics of 'Large-scale knowledge transfer for object localization in ImageNet'. Together they form a unique fingerprint.

Cite this