Latent hierarchical structural learning for object detection
Author(s)
Zhu, Long; Chen, Yuanhao; Yuille, Alan; Freeman, William T.
DownloadFreeman-Latent hierarchical.pdf (1.687Mb)
PUBLISHER_POLICY
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
We present a latent hierarchical structural learning method for object detection. An object is represented by a mixture of hierarchical tree models where the nodes represent object parts. The nodes can move spatially to allow both local and global shape deformations. The models can be trained discriminatively using latent structural SVM learning, where the latent variables are the node positions and the mixture component. But current learning methods are slow, due to the large number of parameters and latent variables, and have been restricted to hierarchies with two layers. In this paper we describe an incremental concave-convex procedure (iCCCP) which allows us to learn both two and three layer models efficiently. We show that iCCCP leads to a simple training algorithm which avoids complex multi-stage layer-wise training, careful part selection, and achieves good performance without requiring elaborate initialization. We perform object detection using our learnt models and obtain performance comparable with state-of-the-art methods when evaluated on challenging public PASCAL datasets. We demonstrate the advantages of three layer hierarchies - outperforming Felzenszwalb et al.'s two layer models on all 20 classes.
Date issued
2010-08Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer ScienceJournal
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Zhu, Long (Leo) et al. “Latent Hierarchical Structural Learning for Object Detection.” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010. 1062–1069. © Copyright 2010 IEEE
Version: Final published version
ISBN
978-1-4244-6984-0
ISSN
1063-6919