Learning in Gibbsian fields: How accurate and how fast can it be?

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 24, Issue 7, 2002, Pages 1001-1006

  Zhu, Song Chun ^a   Liu, Xiuwen ^b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b Florida State University   (United States)

Author keywords

Importance sampling; Markov chain Monte Carlo; Markov random fields; Maximum likelihood estimate; Minimax entropy learning; Texture modeling

Indexed keywords

ALGORITHMS; COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; INTEGRATION; MARKOV PROCESSES; MAXIMUM LIKELIHOOD ESTIMATION; MONTE CARLO METHODS; TEXTURES;

GIBBSIAN FILEDS; IMPORTANCE SAMPLING; MARKOV RANDOM FIELDS; MINIMAX ENTROPY LEARNING; TEXTURE MODELING;

IMAGE ANALYSIS;

EID: 0036647281     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2002.1017626     Document Type: Article

References (23)

1. A variational method for estimating the parameters of MRF from complete and incomplete data
2. Statistical models of image texture
3. Spatial interaction and the statistical analysis of lattice systems (with discussion)
4. Efficiency of pseudo-likelihood estimation for simple Gaussian fields
5. Minutemax: A fast approximation for minimax learning
6. Markov random field texture models
7. Modeling and segmentation of noisy and textured images using Gibbs random fields
8. Maximum likelihood estimation of Markov random field parameters using Markov chain Monte Carlo algorithms
9. Bayesian images analysis: An application to single photon emission tomography
10. Statistical methods for tomographic image reconstruction
11. Constrained Monte Carlo maximum likelihood for dependent data
12. On the convergence of Monte Carlo maximum likelihood calculations
13. Consistency of maximum likelihood and pseudo-likelihood estimators for Gibbs distributions
14. Polynomial-time approximation algorithms for the ising model
15. Partition function estimation of Gibbs random field images using Monte Carlo simulations
16. Stochastic approximation algorithms for partition function estimation of Gibbs random fields
17. A stochastic approximation method
18. Minimax entropy and learning by diffusion
19. Equivalence of Gibbs and Julesz ensembles
20. Estimation and annealing for Gibbsian fields
21. Minimax entropy principle and its application to texture modeling
22. Exploring Julesz ensembles by efficient Markov chain Monte Carlo