A multiple kernel learning approach to joint multi-class object detection

C. Lampert, M. Blaschko, in:, Springer, 2008, pp. 31–40.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published
Author
Lampert, ChristophIST Austria ; Blaschko,Matthew B
Series Title
LNCS
Abstract
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.
Publishing Year
Date Published
2008-07-07
Volume
5096
Page
31 - 40
Conference
DAGM: German Association For Pattern Recognition
IST-REx-ID

Cite this

Lampert C, Blaschko M. A multiple kernel learning approach to joint multi-class object detection. In: Vol 5096. Springer; 2008:31-40. doi:10.1007/978-3-540-69321-5_4
Lampert, C., & Blaschko, M. (2008). A multiple kernel learning approach to joint multi-class object detection (Vol. 5096, pp. 31–40). Presented at the DAGM: German Association For Pattern Recognition, Springer. https://doi.org/10.1007/978-3-540-69321-5_4
Lampert, Christoph, and Matthew Blaschko. “A Multiple Kernel Learning Approach to Joint Multi-Class Object Detection,” 5096:31–40. Springer, 2008. https://doi.org/10.1007/978-3-540-69321-5_4.
C. Lampert and M. Blaschko, “A multiple kernel learning approach to joint multi-class object detection,” presented at the DAGM: German Association For Pattern Recognition, 2008, vol. 5096, pp. 31–40.
Lampert C, Blaschko M. 2008. A multiple kernel learning approach to joint multi-class object detection. DAGM: German Association For Pattern Recognition, LNCS, vol. 5096. 31–40.
Lampert, Christoph, and Matthew Blaschko. A Multiple Kernel Learning Approach to Joint Multi-Class Object Detection. Vol. 5096, Springer, 2008, pp. 31–40, doi:10.1007/978-3-540-69321-5_4.

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar