Parameter learning and convergent inference for dense random fields

30th International Conference on Machine Learning, ICML 2013

Volumn , Issue PART 2, 2013, Pages 1550-1558

  Krähenbühl, Philipp ^a   Koltun, Vladlen ^a  

^a Stanford University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; INFERENCE ENGINES; LEARNING SYSTEMS;

COMPUTER VISION APPLICATIONS; INFERENCE ALGORITHM; LEARNING PARAMETERS; LOSS FUNCTIONS; MARGINALS; MEAN FIELD; PARAMETER LEARNING; RANDOM FIELDS;

PARAMETER ESTIMATION;

EID: 84897536915     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (26)

1. Blake, Andrew, Kohli, Pushmeet, and Rother, Carsten. Markov Random Fields for Vision and Image Processing. MIT Press, 2011.
2. Domke, Justin. Learning graphical model parameters with approximate marginal inference. PA MI, 2013. To appear.
3. Eaton, Frederik and Ghahramani, Zoubin. Choosing a variable to clamp. JMLR, 5:145-152, 2009.
4. He, Xuming, Zemel, Richard S., and Carreira-Perpinan, Miguel A. Multiscale conditional random fields for image labeling. In CVPR, 2004.
5. Kohli, Pushmeet, Ladický, Lubor, and Torr, Philip H. S. Robust higher order potentials for enforcing label consistency. IJCV, 82(3), 2009.
6. Roller, Daphne and Friedman, Nir. Probabilistic Graphical Models: Principles and Techniques. MIT Press, 2009.
7. Krähenbühl, Philipp and Koltun, Vladlen. Efficient inference in fully connected CRFs with Gaussian edge potentials. In NIPS, 2011.
8. Kulesza, Alex and Pereira, Fernando. Structured learning with approximate inference. In NIPS, 2007.
9. Kumar, Sanjiv, August, Jonas, and Hebert, Martial. Exploiting inference for approximate parameter learning in discriminative fields. In Energy Minimization Methods in Computer Vision and Pattern Recognition. 2005.
10. LeCun, Yann, Chopra, Sumit, Hadsell, Raia, Ranzato, Marc'Aurelio, and Huang, Fu Jie. A tutorial on energy-based learning. In Predicting Structured Data. MIT Press, 2006.
11. Levin, Anat and Weiss, Yair. Learning to combine bottom-up and top-down segmentation. IJCV, 81: 105-118, 2009.
12. Pal, Christopher J., Weinman, Jerod J., Tran, Lam C., and Scharstein, Daniel. On learning conditional random fields for stereo. IJCV, 99(3):319-337, 2012.
13. Roth, Stefan and Black, Michael J. Fields of experts. IJCV, 82(2):205-229, 2009.
14. Samuel, Kegan G. G. and Tappen, Marshall F. Learning optimized MAP estimates in continuously-valued MRF models. In CVPR, 2009.
15. Shotton, Jamie, Winn, John M., Rother, Carsten, and Criminisi, Antonio. Textonboost for image understanding. IJCV, 81(1), 2009.
16. Sriperumbudur, Bharath K. and Lanckriet, Gert R. G. On the convergence of the concave-convex procedure. In NIPS, 2009.
17. Sutton, Charles A. and McCallum, Andrew. Piecewise training for undirected models. In UAI, 2005.
18. Tappen, Marshall F. Utilizing variational optimization to learn Markov random fields. In CVPR, 2007.
19. Tappen, Marshall F. Learning parameters in continuous-valued Markov random fields. In Markov Random Fields For Vision And Image Processing. MIT Press, 2011.
20. Vineet, Vibhav, Warrell, Jonathan, Sturgess, Paul, and Torr, Philip H. S. Improved initialization and Gaussian mixture pairwise terms for dense random fields with mean-field inference. In BMVC, 2012a.
21. Vineet, Vibhav, Warrell, Jonathan, and Torr, Philip H. S. Filter-based mean-field inference for random fields with higher-order terms and product labelspaces. In ECCV, 2012b.
22. Vishwanathan, S. V. N., Schraudolph, Nicol N., Schmidt, Mark W., and Murphy, Kevin P. Accelerated training of conditional random fields with stochastic gradient methods. In ICML, 2006.
23. Wainwright, Martin J. Estimating the "wrong" graphical model: Benefits in the computation-limited setting. JMLR, 7:1829-1859, 2006.
24. Wainwright, Martin J. and Jordan, Michael I. Graphical models, exponential families, and variational inference. Foundations and Trends in Machine Learning, 1(1-2), 2008.
25. Wainwright, Martin J., Jaakkola, Tommi S., and Willsky, Alan S. Tree-reweighted belief propagation algorithms and approximate ML estimation by pseudo-moment matching. In Proc. Workshop on Artificial Intelligence and Statistics, 2003.
26. Yuille, Alan L. and Rangarajan, Anand. The concave-convex procedure (CCCP). In NIPS, 2001.