Greedy Structure Learning of Hierarchical Compositional Models
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11604-11613
Abstract
In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter. Existing approaches to this problem are limited by making strong a-priori assumptions about the object’s geometric structure and require seg- mented training data for learning. In this paper, we propose a novel framework for learning hierarchical compositional models (HCMs) which do not suffer from the mentioned limitations. We present a generalized formulation of HCMs and describe a greedy structure learning framework that consists of two phases: Bottom-up part learning and top-down model composition. Our framework integrates the foreground-background segmentation problem into the structure learning task via a background model. As a result, we can jointly optimize for the number of layers in the hierarchy, the number of parts per layer and a foreground- background segmentation based on class labels only. We show that the learned HCMs are semantically meaningful and achieve competitive results when compared to other generative object models at object classification on a standard transfer learning dataset.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Inference and Learning with Hierarchical Shape ModelsInternational Journal of Computer Vision, 2010
- Learning Active Basis Model for Object Detection and RecognitionInternational Journal of Computer Vision, 2009
- A Stochastic Grammar of ImagesFoundations and Trends in Computer Graphics and Vision, 2007
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995
- Matching pursuits with time-frequency dictionariesIEEE Transactions on Signal Processing, 1993
- Feature extraction from faces using deformable templatesInternational Journal of Computer Vision, 1992
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988