 |
    |
Multi-component Models for Object Detection
Chunhui Gu1, Pablo Arbeláez2, Yuanqing Lin3, Kai Yu4, and Jitendra Malik2
1Google Inc., Mountain View, CA, USA
chunhui@google.com
2UC Berkeley, Berkeley, CA, USA
arbelaez@eecs.berkeley.edu
malik@eecs.berkeley.edu
3NEC Labs America, Cupertino, CA, USA
ylin@sv.nec-labs.com
4Baidu Inc., Beijing, China
yukai@baidu.com
Abstract. In this paper, we propose a multi-component approach for object detection. Rather than attempting to represent an object category with a monolithic model, or pre-defining a reduced set of aspects, we form visual clusters from the data that are tight in appearance and configuration spaces. We train individual classifiers for each component, and then learn a second classifier that operates at the category level by aggregating responses from multiple components. In order to reduce computation cost during detection, we adopt the idea of object window selection, and our segmentation-based selection mechanism produces fewer than 500 windows per image while preserving high object recall. When compared to the leading methods in the challenging VOC PASCAL 2010 dataset, our multi-component approach obtains highly competitive results. Furthermore, unlike monolithic detection methods, our approach allows the transfer of finer-grained semantic information from the components, such as keypoint location and segmentation masks.
LNCS 7575, p. 445 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012