Who killed the directed model?
Authors:
- 1 June 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
Abstract
Prior distributions are useful for robust low-level vision, and undirected models (e.g. Markov Random Fields) have become a central tool for this purpose. Though sometimes these priors can be specified by hand, this becomes difficult in large models, which has motivated learning these models from data. However, maximum likelihood learning of undirected models is extremely difficult- essentially all known methods require approximations and/or high computational cost. Conversely, directed models are essentially trivial to learn from data, but have not received much attention for low-level vision. We compare the two formalisms of directed and undirected models, and conclude that there is no a priori reason to believe one better represents low-level vision quantities. We formulate two simple directed priors, for natural images and stereo disparity, to empirically test if the undirected formalism is superior. We find in both cases that a simple directed model can achieve results similar to the best learnt undirected models with significant speedups in training time, suggesting that directed models are an attractive choice for tractable learning.Keywords
This publication has 16 references indexed in Scilit:
- 3-D Depth Reconstruction from a Single Still ImageInternational Journal of Computer Vision, 2007
- Learning Gaussian Conditional Random Fields for Low-Level Vision2007
- Learning Conditional Random Fields for Stereo2007
- What makes a good model of natural images?2007
- Utilizing Variational Optimization to Learn Markov Random Fields2007
- Fields of Experts: A Framework for Learning Image Priors2005
- Recovering intrinsic images from a single imageIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002
- Image inpainting2000
- Prior learning and Gibbs reaction-diffusionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997