Control Systems and Computers

https://doi.org/10.15407/csc.2023.03.005

Control Systems and Computers, 2023, Issue 3 (303), pp. 5-14

UDC 004.932

V.M. Krygin, Junior Researcher, International Research and Training Centre for Information Technologies and Systems of the NAS and MES of Ukraine, Glushkov ave., 40, Kyiv, 03187, Ukraine, ORCID: https://orcid.org/0000-0002-9000-1685, valeriy.krygin@gmail.com

USING GIBBS SAMPLING TO ESTIMATE THE SOLUTION OF THE UNPAIRED LRARNING PROBLEM

The article describes unpaired learning using Monte Carlo Markov Chain on the example of a stereo vision problem. The description includes the inference of the algorithm, the application of the stochastic gradient method, and some implementation details. Multiple penalty functions are considered, and quantitative results are presented. The results of the experiments expose new insights into weights for graphical models for stereo vision problems.

Download full text! (On English)

Keywords: unpaired learning, Gibbs sampling, Monte Carlo Markov Chain, stereo vision.

1. Resales, R., Achan, K., Frey, B., 2003. “Unsupervised image translation”. Proc. of Ninth IEEE Interna-tional Conference of Computer Vision, 2003. Vol. 4. pp. 472-478. DOI: https://doi.org/10.1109/ICCV.2003.1238384
2. Zhu, J.-Y. et al., 2017. “Unpaired image-to-image translation using cycle-consistent adversarial networks”. Proceedings of the IEEE international conference on computer vision, pp. 2223-2232.
   https://doi.org/10.1109/ICCV.2017.244
3. Geman, S., Geman, D, 1984. “Stochastic relaxation, gibbs distributions, and the bayesian restoration of images”. IEEE Transactions on pattern analysis and machine intelligence, 6, pp. 721-741.
   https://doi.org/10.1109/TPAMI.1984.4767596
4. Kindermann, R., Snell, L., 1980. “Markov random fields and their applications”. American Mathematical Society, Vol. 1, pp. 4-7. DOI: https://doi.org/10.1090/conm/001
5. Lafferty, J.D., McCallum, A., Pereira, F.C.N., 2001. “Conditional random fields: Probabilistic models for segmenting and labeling sequence data”. Proceedings of the eighteenth international conference on machine learning. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., pp. 282-289.
6. Descombes, X. et al., 1999. “Estimation of markov random field prior parameters using markov chain monte carlo maximum likelihood”. IEEE Transactions on Image Processing, Vol. 8, n 7, pp. 954-963.
   https://doi.org/10.1109/83.772239
7. Shlezinger, M.I., 1968. “The interaction of learning and self-organization in pattern recognition”. Cybernetics. Vol. 4, N 2, pp. 66-71.
   https://doi.org/10.1007/BF01073742
8. Schlesinger, M, Hlavac, V., 2002. Ten Lectures on Statistical and Structural Pattern Recognition. Computational Imaging and Vision, Vol. 24. Kluwer Academic Publishers – Dordrecht/Boston/London, 520 p.
   https://doi.org/10.1007/978-94-017-3217-8
9. Robbins, H., Monro, S., 1951. “A Stochastic Approximation Method”. The Annals of Mathematical Statistics. Institute of Mathematical Statistics, Vol. 22, N 3, pp. 400-407.
   https://doi.org/10.1214/aoms/1177729586
10. Szeliski, R, 2022. Computer vision – algorithms and applications. 2nd ed. 2022 Edition. Springer. 1232 p. ISBN 978-3030343712.
11. Duda, R.O., Hart, P.E., 1973. “Pattern classification and scene analysis”. Wiley, pp. I-XVII, 1-482.
12. Schlesinger, D., 2003. “Gibbs probability distributions for stereo reconstruction”. Pattern recognition / ed. Michaelis B., Krell G. Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 394-401.
    https://doi.org/10.1007/978-3-540-45243-0_51
13. Nickolls, J., Buck, I., Garland, M., Skadron, K., 2008. Scalable parallel programming with CUDA: Is cuda the parallel programming model that application developers have been waiting for? Queue, 6(2), pp. 40-53. DOI: https://doi.org/10.1145/1365490.1365500
14. Scharstein, D., Szeliski, R., 2002. “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms”. International Journal of Computer Vision. Kluwer Academic Publishers, Vol. 47, N 1-3, pp. 7-42.
15. Boykov, Y., Kolmogorov, V., 2004. “An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision”. IEEE Trans. Pattern Anal. Mach. Intell. USA: IEEE Computer Society, Vol. 26, N 9, pp. 1124-1137.
    https://doi.org/10.1109/TPAMI.2004.60
16. Kolmogorov, V., 2005. “Convergent tree-reweighted message passing for energy minimization”. International workshop on artificial intelligence and statistics PMLR, pp. 182-189.
17. Schlesinger, M.I., Antoniuk, K.V., 2011.”Diffusion algorithms and structural recognition optimization problems,” Cybern. Syst. Analysis, Vol. 47, No. 2, pp. 175-192. (In Russian).
    https://doi.org/10.1007/s10559-011-9300-z

Received 28.07.2023