Abstract
This paper introduces a novel approach to uncertainty quantification of image labelings determined by assignment flows. Local uncertainties caused by ambiguous data and noise are estimated by fitting Dirichlet distributions and pushed forward to the tangent space. The resulting first- and second-order moments are then propagated using a linear ODE parametrization of assignment flows. The corresponding moment evolution equations can be solved in closed form and numerically evaluated using iterative Krylov subspace techniques and low-rank approximation. This results in a faithful representation and quantification of uncertainty in the output space of image labelings, which is important in all applications where confidence in pixelwise decisions matters.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Abdar, M., et al.: A review of uncertainty quantification in deep learning: techniques, applications and challenges. Inf. Fusion 76, 243–297 (2021)
Amari, S.I., Nagaoka, H.: Methods of Information Geometry. American Mathematical Society and Oxford University Press, Oxford (2000)
Ambrosio, L., Tortorelli, V.M.: Approximation of functional depending on jumps by elliptic functional via \(\Gamma \)-convergence. Comm. Pure Appl. Math. 43(8), 999–1036 (1990)
Åström, F., Petra, S., Schmitzer, B., Schnörr, C.: Image labeling by assignment. J. Math. Imaging Vis. 58(2), 211–238 (2017). https://doi.org/10.1007/s10851-016-0702-4
Barndorff-Nielsen, O.E.: Information and Exponential Families in Statistical Theory. Wiley, Chichester (1978)
Behr, M., Benner, P., Heiland, J.: Solution formulas for differential Sylvester and Lyapunov equations. Calcolo 56(4), 1–33 (2019)
Bertozzi, A., Luo, X., Stuart, A., Zygalakis, K.: Uncertainty quantification in graph-based classification of high dimensional data. SIAM/ASA J. Uncertain. Quantif. 6(2), 568–595 (2018)
Bishop, C.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)
Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians. J. Am. Stat. Assoc. 112(518), 859–877 (2017)
Brown, L.D.: Fundamentals of Statistical Exponential Families. Institute of Mathematical Statistics, Hayward (1986)
Buades, A., Coll, B., Morel, J.M.: Image denoising methods. A new nonlocal principle. SIAM Rev. 52(1), 113–147 (2010)
Chung, F.: Spectral Graph Theory. American Mathematical Society (1997)
Grünwald, P., van Ommen, T.: Inconsistency of Bayesian inference for misspecified linear models, and a proposal for repairing it. Bayesian Anal. 12(4), 1069–1103 (2017)
Hochbruck, M., Lubich, C.: On Krylov Subspace approximations to the matrix exponential operator. SIAM J. Numer. Anal. 34(5), 1911–1925 (1997)
Huang, J.: Maximum likelihood estimation of Dirichlet distribution parameters. CMU Technique report (2005)
Johnson, N.L., Kemp, A.W., Kotz, S.: Univariate Discrete Distributions, 3rd edn. Wiley-Interscience, Hoboken (2005)
Kotz, S., Balakrishnan, N., Johnson, N.L.: Continuous Multivariate Distributions: Models and Applications, vol. 1, 2nd edn. Wiley, Hoboken (2000)
Marzouk, Y., Moselhy, T., Parno, M., Spantini, A.: An introduction to sampling via measure transport. In: Handbook of Uncertainty Quantification, pp. 1–41. Springer, Heidelberg (2017)
Minaee, S., Boykov, Y.Y., Porikli, F., Plaza, A.J., Kehtarnavaz, N., Terzopoulos, D.: Image segmentation using deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https://ieeexplore.ieee.org/document/9356353
Owhadi, H., Scovel, C.: Brittleness of Bayesian inference under finite information in a continuous world. Electr. J. Stat. 9, 1–79 (2015)
Papamakarios, G., Nalisnick, E., Rezende, D.J., Mohamed, S., Lakshminarayanan, B.: Normalizing flows for probabilistic modeling and inference. J. Mach. Learn. Res. 22(57), 1–64 (2021)
Pätz, T., Kirby, R.M., Preusser, T.: Ambrosio-Tortorelli segmentation of stochastic images: model extensions, theoretical investigations and numerical methods. Int. J. Comput. Vis. 103, 190–212 (2013)
Rasmussen, C.E., Williams, C.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)
Risken, H.: The Fokker-Planck Equation: Methods of Solution and Applications, 2nd edn. Springer, Heidelberg (1989)
Ronning, G.: Maximum likelihood estimation of Dirichlet distributions. J. Stat. Comput. Simul. 32(4), 215–221 (1989)
Rue, H., Held, L.: Gaussian Markov Random Fields: Theory and Applications. CRC Press (2005)
Saad, Y.: Analysis of some Krylov subspace approximations to the matrix exponential operator. SIAM J. Numer. Anal. 29(1), 209–228 (1992)
Särkkä, S., Solin, A.: Applied Stochastic Differential Equations, vol. 10. Cambridge University Press, Cambridge (2019)
Savarino, F., Schnörr, C.: Continuous-domain assignment flows. Eur. J. Appl. Math. 32(3), 570–597 (2021)
Schnörr, C.: Assignment flows. In: Grohs, P., Holler, M., Weinmann, A. (eds.) Variational Methods for Nonlinear Geometric Data and Applications, pp. 235–260. Springer, Heidelberg (2020)
Sitenko, D., Boll, B., Schnörr, C.: Assignment flow for order-constrained OCT segmentation. In: GCPR (2020)
Sitenko, D., Boll, B., Schnörr, C.: Assignment flow for order-constrained OCT segmentation. Int. J. Comput. Vis. 129, 3088–3118 (2021). https://link.springer.com/content/pdf/10.1007/s11263-021-01520-5.pdf
Teschl, G.: Ordinary Differential Equations and Dynamical Systems, Grad. Studies Mathematics, vol. 140. American Mathematical Society (2012)
Van Loan, C.F.: The ubiquitous Kronecker product. J. Comput. Appl. Math. 123, 85–100 (2000)
Wainwright, M., Jordan, M.: Graphical models, exponential families, and variational inference. Found. Trends Mach. Learn. 1(1–2), 1–305 (2008)
Xiu, D., Karniadakis, G.E.: The Wiener-Askey polynomial chaos for stochastic differential equations. SIAM J. Sci. Comput. 24(2), 619–644 (2002)
Zeilmann, A., Petra, S., Schnörr, C.: Learning linear assignment flows for image labeling via exponential integration. In: Elmoataz, A., Fadili, J., Quéau, Y., Rabin, J., Simon, L. (eds.) SSVM 2021. LNCS, vol. 12679, pp. 385–397. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-75549-2_31
Zeilmann, A., Savarino, F., Petra, S., Schnörr, C.: Geometric numerical integration of the assignment flow. Inverse Probl. 36(3), 034004 (2020). (33pp)
Acknowledgement
This work is supported by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy EXC 2181/1 - 390900948 (the Heidelberg STRUCTURES Excellence Cluster).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Gonzalez-Alvarado, D., Zeilmann, A., Schnörr, C. (2021). Quantifying Uncertainty of Image Labelings Using Assignment Flows. In: Bauckhage, C., Gall, J., Schwing, A. (eds) Pattern Recognition. DAGM GCPR 2021. Lecture Notes in Computer Science(), vol 13024. Springer, Cham. https://doi.org/10.1007/978-3-030-92659-5_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-92659-5_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92658-8
Online ISBN: 978-3-030-92659-5
eBook Packages: Computer ScienceComputer Science (R0)