Assemble new object detector with few examples

© 2011 IEEE

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 20(2011), 12 vom: 01. Dez., Seite 3341-9
1. Verfasser: Yang, Kuiyuan (VerfasserIn)
Weitere Verfasser: Wang, Meng, Hua, Xian-Sheng, Yan, Shuicheng, Zhang, Hong-Jiang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2011
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
Beschreibung
Zusammenfassung:© 2011 IEEE
Learning a satisfactory object detector generally requires sufficient training data to cover the most variations of the object. In this paper, we show that the performance of object detector is severely degraded when training examples are limited. We propose an approach to handle this issue by exploring a set of pretrained auxiliary detectors for other categories. By mining the global and local relationships between the target object category and auxiliary objects, a robust detector can be learned with very few training examples. We adopt the deformable part model proposed by Felzenszwalb and simultaneously explore the root and part filters in the auxiliary object detectors under the guidance of the few training examples from the target object category. An iterative solution is introduced for such a process. The extensive experiments on the PASCAL VOC 2007 challenge data set show the encouraging performance of the new detector assembled from those related auxiliary detectors
Beschreibung:Date Completed 19.03.2012
Date Revised 22.11.2011
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1941-0042
DOI:10.1109/TIP.2011.2158231