Latent hierarchical structural learning for object detection
Name
Freeman-Latent hierarchical.pdf
Size
1.69 MB
Format
Adobe PDF
Checksum (MD5)
83fb0f8f3702bfa059bf77f80367eb4e
Author(s)
Zhu, Long
Chen, Yuanhao
Yuille, Alan
Freeman, William T.
Date Issued
August 2010
Journal
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
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
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.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR.2010.5540096
