cvpr cvpr2013 cvpr2013-180 cvpr2013-180-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Neill D.F. Campbell, Kartic Subr, Jan Kautz
Abstract: Conditional Random Fields (CRFs) are used for diverse tasks, ranging from image denoising to object recognition. For images, they are commonly defined as a graph with nodes corresponding to individual pixels and pairwise links that connect nodes to their immediate neighbors. Recent work has shown that fully-connected CRFs, where each node is connected to every other node, can be solved efficiently under the restriction that the pairwise term is a Gaussian kernel over a Euclidean feature space. In this paper, we generalize the pairwise terms to a non-linear dissimilarity measure that is not required to be a distance metric. To this end, we propose a density estimation technique to derive conditional pairwise potentials in a nonparametric manner. We then use an efficient embedding technique to estimate an approximate Euclidean feature space for these potentials, in which the pairwise term can still be expressed as a Gaussian kernel. We demonstrate that the use of non-parametric models for the pairwise interactions, conditioned on the input data, greatly increases expressive power whilst maintaining efficient inference.
[1] A. Adams, J. Baek, and M. A. Davis. Fast high-dimensional filtering using the permutohedral lattice. In Computer Graphics Forum (Eurographics Proceedings), 2012. 3
[2] E. Borenstein and S. Ullman. Class-specific, top-down segmentation. In Proc. 7th Europ. Conf. on Computer Vision, pages 109–124, 2002. 6
[3] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell., 23(1 1): 1222–1239, November 2001. 1
[4] V. de Silva and J. B. Tenenbaum. Global versus local methods in nonlinear dimensionality reduction. Advances in Neural Information Processing Systems 15., 2002. 4
[5] A. Hosni, C. Rhemann, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. IEEE Trans. Pattern Anal. Mach. Intell. , 99, 2012. 2
[6] J. Jancsary, S. Nowozin, T. Sharp, and C. Rother. Regression tree fields - an efficient, non-parametric approach to image labeling problems. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pages 2376–2383, 2012. 2, 5, 6, 7
[7] V. Kolmogorov. Convergent tree-reweighted message passing for energy minimization. IEEE Trans. Pattern Anal. Mach. Intell., 28(10): 1568–1583, October 2006. 1
[8] N. Komodakis, N. Paragios, and G. Tziritas. MRF energy minimization and beyond via dual decomposition. IEEE Trans. Pattern Anal. Mach. Intell., 33(3):531–552, 2011. 1
[9] P. Kornprobst, J. Tumblin, and F. Durand. Bilateral filtering: Theory and applications. Foundations and Trends in Computer Graphics and Vision, 4(1): 1–74, 2009. 2
[10] P. Kr ¨ahenb u¨hl and V. Koltun. Efficient inference in fully connected CRFs with gaussian edge potentials. In NIPS, pages 109–1 17, 2011. 1, 2, 3, 6, 7
[11] P. Kr ¨ahenb u¨hl and V. Koltun. Efficient nonlocal regularization for optical flow. In Proc. 12th Europ. Conf. on Computer Vision, pages
[12]
[13]
[14]
[15]
[16]
[17]
[18] 356–369, 2012. 2, 3 J. D. Lafferty, A. McCallum, and F. C. N. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the 18th International Conference on Machine Learning, ICML ’01, pages 282–289, San Francisco, CA, USA, 2001. Morgan Kaufmann Publishers Inc. 1 S. Nowozin, C. Rother, S. Bagon, T. Sharp, B. Yao, and P. Kohli. Decision tree fields. In Proc. 13th Intl. Conf. on Computer Vision, pages 1668–1675, 2011. 2, 5, 6, 7 K. Subr, S. Paris, C. Soler, and J. Kautz. Accurate binary image selection from inaccurate user input. In Computer Graphics Forum (Eurographics Proceedings), 2012. 2, 4, 6, 7 R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, and C. Rother. A comparative study of energy minimization methods for markov random fields with smoothness-based priors. IEEE Trans. Pattern Anal. Mach. Intell., 30(6): 1068–1080, June 2008. 1 V. Vineet, J. Warrell, P. Sturgess, and P. Torr. Improved initialization and gaussian mixture pairwise terms for dense random fields with mean-field inference. In Proc. 23rd British Machine Vision Conference, pages 73.1–73.1 1, 2012. 1, 2, 3 V. Vineet, J. Warrell, and P. H. S. Torr. Filter-based mean-field inference for random fields with higher-order terms and product labelspaces. In Proc. 12th Europ. Conf. on Computer Vision, pages 3 1 44, 2012. 2 Y. Weiss. Comparing the mean field method and belief propagation for approximate inference in MRFs. MIT Press, 2001. 2 111666666533