Latent hierarchical structural learning for object detection
Authors:
- 1 June 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1062-1069
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.Keywords
This publication has 8 references indexed in Scilit:
- Multiple kernels for object detection2009
- Discriminative models for multi-class object layout2009
- Learning structural SVMs with latent variables2009
- Discriminative structure learning of hierarchical representations for object detection2009
- Deformable Template As Active Basis2007
- Histograms of Oriented Gradients for Human Detection2005
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004
- Support vector machine learning for interdependent and structured output spaces2004