Header logo is ei

A Multiple Kernel Learning Approach to Joint Multi-Class Object Detection


Conference Paper


Most current methods for multi-class object classification and localization work as independent 1-vs-rest classifiers. They decide whether and where an object is visible in an image purely on a per-class basis. Joint learning of more than one object class would generally be preferable, since this would allow the use of contextual information such as co-occurrence between classes. However, this approach is usually not employed because of its computational cost. In this paper we propose a method to combine the efficiency of single class localization with a subsequent decision process that works jointly for all given object classes. By following a multiple kernel learning (MKL) approach, we automatically obtain a sparse dependency graph of relevant object classes on which to base the decision. Experiments on the PASCAL VOC 2006 and 2007 datasets show that the subsequent joint decision step clearly improves the accuracy compared to single class detection.

Author(s): Lampert, C. and Blaschko, MB.
Book Title: DAGM 2008
Journal: Pattern Recognition: Proceedings of the 30th DAGM Symposium
Pages: 31-40
Year: 2008
Month: June
Day: 0
Editors: Rigoll, G.
Publisher: Springer

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1007/978-3-540-69321-5_4
Event Name: 30th Annual Symposium of the German Association for Pattern Recognition
Event Place: München, Germany

Address: Berlin, Germany
Digital: 0
Institution: German Association for Pattern Recognition
Language: en
Note: Main Award DAGM 2008
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {A Multiple Kernel Learning Approach to Joint Multi-Class Object Detection},
  author = {Lampert, C. and Blaschko, MB.},
  journal = {Pattern Recognition: Proceedings of the 30th DAGM Symposium},
  booktitle = {DAGM 2008},
  pages = {31-40},
  editors = {Rigoll, G. },
  publisher = {Springer},
  organization = {Max-Planck-Gesellschaft},
  institution = {German Association for Pattern Recognition},
  school = {Biologische Kybernetik},
  address = {Berlin, Germany},
  month = jun,
  year = {2008},
  note = {Main Award DAGM 2008},
  month_numeric = {6}