Empirical minimum bayes risk prediction: How to extract an extra few % performance from vision models with just three more parameters

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Volumn , Issue , 2014, Pages 1043-1050

  Premachandran, Vittal ^a   Tarlow, Daniel ^b   Batra, Dhruv ^c  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

^b MICROSOFT RESEARCH   (United States)

^c VIRGINIA POLYTECHNIC INSTITUTE AND STATE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

IMAGE SEGMENTATION; PATTERN RECOGNITION;

COMPLEX MEASURES; EVALUATION MEASURES; IMPROVING PERFORMANCE; META-ALGORITHMS; MINIMUM BAYES RISK; RESEARCH CHALLENGES; STATE-OF-THE-ART ALGORITHMS; VISION SYSTEMS;

FORECASTING;

EID: 84911413891     PISSN: 10636919     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CVPR.2014.137     Document Type: Conference Paper

References (32)

1. A. Barbu and S.-C. Zhu. Generalizing Swendsen-Wang to sampling arbitrary posterior probabilities. IEEE Trans. Pattern Anal. Mach. Intell., 27:1239-1253, August 2005.
2. D. Batra. An Efficient Message-Passing Algorithm for the M-Best MAP Problem. In Uncertainty in Artificial Intelligence, 2012.
3. D. Batra, P. Yadollahpour, A. Guzman-Rivera, and G. Shakhnarovich. Diverse M-Best Solutions in Markov Random Fields. In ECCV, 2012.
4. J. Carreira, R. Caseiro, J. Batista, and C. Sminchisescu. Semantic segmentation with second-order pooling. In ECCV, pages 430-443, 2012.
5. J. Carreira and C. Sminchisescu. Constrained parametric min-cuts for automatic object segmentation. In CVPR, 2010.
6. M. Eichner, M. Marin-Jimenez, A. Zisserman, and V. Ferrari. Articulated hu man pose estimation and search in (almost) unconstrained still images. Techni cal report, ETHZ, 2010.
7. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html.
8. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The Pascal Visual Object Classes (VOC) Challenge. IJCV, 88(2):303-338, June 2010.
9. A. Guzman-Rivera, D. Batra, and P. Kohli. Multiple Choice Learning: Learning to Produce Multiple Structured Outputs. In Proc. NIPS, 2012.
10. A. Guzman-Rivera, P. Kohli, D. Batra, and R. Rutenbar. Efficiently enforcing diversity in multi-output structured prediction. In AISTATS, 2014.
11. P. Hammer. Some network flow problems solved with pseudo-boolean programming. Operations Research, 13:388-399, 1965.
12. F. Huszár and D. Duvenaud. Optimally-weighted herding is bayesian quadrature. arXiv preprint arXiv:1204.1664, 2012.
13. V. Kolmogorov and R. Zabih. What energy functions can be minimized via graph cuts? PAMI, 26(2):147-159, 2004.
14. J. Munkres. Algorithms for the assignment and transportation problems. Journal of the Society of Industrial and Applied Mathematics, 5(1):32-38, March 1957.
15. A. Niculescu-Mizil and R. Caruana. Predicting good probabilities with supervised learning. In Proceedings of the 22nd international conference on Machine learning, pages 625-632. ACM, 2005.
16. D. Nilsson. An efficient algorithm for finding the M most probable configurations in probabilistic expert systems. Statistics and Computing, 8:159-173, 1998. 10.1023/A:1008990218483.
17. G. Papandreou and A. Yuille. Perturb-and-map random fields: Using discrete optimization to learn and sample from energy models. In ICCV, pages 193-200, Nov. 2011.
18. D. Park and D. Ramanan. N-best maximal decoders for part models. In ICCV, 2011.
19. J. Pearl. Reverend bayes on inference engines: A distributed hierarchical approach. In AAAI, 1982.
20. J. C. Platt. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In Advances In Large Margin Classifiers, 1999.
21. J. Porway and S.-C. Zhu. C4: Exploring multiple solutions in graphical models by cluster sampling. PAMI, 33(9):1713-1727, 2011.
22. S. E. Shimony. Finding MAPs for belief networks is NP-hard. Artificial Intelligence, 68(2):399-410, August 1994.
23. D. Tarlow and R. S. Zemel. Structured output learning with high order loss functions. In AISTATS, 2012.
24. M. Taylor, J. Guiver, S. Robertson, and T. Minka. Softrank: optimizing non-smooth rank metrics. In Proceedings of the 2008 International Conference on Web Search and Data Mining, pages 77-86. ACM, 2008.
25. Z. Tu and S.-C. Zhu. Image segmentation by data-driven Markov Chain Monte Carlo. IEEE Trans. Pattern Anal. Mach. Intell., 24:657-673, May 2002.
26. L. Valiant. The complexity of computing the permanent. Theoretical Computer Science, 8(2):189-201, 1979.
27. M. Welling. Herding dynamical weights to learn. In Proceedings of the 26th Annual International Conference on Machine Learning, pages 1121-1128. ACM, 2009.
28. P. Yadollahpour, D. Batra, and G. Shakhnarovich. Discriminative re-ranking of diverse segmentations. In CVPR, 2013.
29. Y. Yang and D. Ramanan. Articulated pose estimation with flexible mixtures-of-parts. PAMI, To Appear.
30. C. Yanover and Y. Weiss. Finding the M most probable configurations using loopy belief propagation. In NIPS, 2003.
31. B. Zadrozny and C. Elkan. Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers. In In Proceedings of the Eighteenth International Conference on Machine Learning (ICML), 2001.
32. B. Zadrozny and C. Elkan. Transforming classifier scores into accurate mul-ticlass probability estimates. In Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 694-699. ACM, 2002.