Title :
Shared parts for deformable part-based models
Author :
Ott, Patrick ; Everingham, Mark
Author_Institution :
Sch. of Comput., Univ. of Leeds, Leeds, UK
Abstract :
The deformable part-based model (DPM) proposed by Felzenszwalb et al. has demonstrated state-of-the-art results in object localization. The model offers a high degree of learnt invariance by utilizing viewpoint-dependent mixture components and movable parts in each mixture component. One might hope to increase the accuracy of the DPM by increasing the number of mixture components and parts to give a more faithful model, but limited training data prevents this from being effective. We propose an extension to the DPM which allows for sharing of object part models among multiple mixture components as well as object classes. This results in more compact models and allows training examples to be shared by multiple components, ameliorating the effect of a limited size training set. We (i) reformulate the DPM to incorporate part sharing, and (ii) propose a novel energy function allowing for coupled training of mixture components and object classes. We report state-of-the-art results on the PASCAL VOC dataset.
Keywords :
object detection; solid modelling; PASCAL VOC dataset; deformable part based models; learnt invariance; object localization; shared parts; viewpoint dependent mixture components; Computational modeling; Deformable models; Detectors; Feature extraction; Support vector machines; Training; Training data;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4577-0394-2
DOI :
10.1109/CVPR.2011.5995357