Advertisement

Accelerating Dynamic Programs via Nested Benders Decomposition with Application to Multi-Person Pose Estimation

  • Shaofei Wang
  • Alexander Ihler
  • Konrad Kording
  • Julian Yarkony
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11218)

Abstract

We present a novel approach to solve dynamic programs (DP), which are frequent in computer vision, on tree-structured graphs with exponential node state space. Typical DP approaches have to enumerate the joint state space of two adjacent nodes on every edge of the tree to compute the optimal messages. Here we propose an algorithm based on Nested Benders Decomposition (NBD) that iteratively lower-bounds the message on every edge and promises to be far more efficient. We apply our NBD algorithm along with a novel Minimum Weight Set Packing (MWSP) formulation to a multi-person pose estimation problem. While our algorithm is provably optimal at termination it operates in linear time for practical DP problems, gaining up to 500\({\times }\) speed up over traditional DP algorithm which have polynomial complexity.

Keywords

Nested benders decomposition Column generation Multi-person pose estimation 

Supplementary material

474202_1_En_40_MOESM1_ESM.pdf (219 kb)
Supplementary material 1 (pdf 219 KB)

References

  1. 1.
    Andres, B., Kappes, J.H., Beier, T., Kothe, U., Hamprecht, F.A.: Probabilistic image segmentation with closedness constraints. In: Proceedings of ICCV (2011)Google Scholar
  2. 2.
    Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: Proceedings of CVPR (2014)Google Scholar
  3. 3.
    Bansal, N., Blum, A., Chawla, S.: Correlation clustering. J. Mach. Learn, 238–247 (2002)Google Scholar
  4. 4.
    Belanger, D., Passos, A., Riedel, S., McCallum, A.: Map inference in chains using column generation. In: Proceedings of NIPS (2012)Google Scholar
  5. 5.
    Birge, J.R.: Decomposition and partitioning methods for multistage stochastic linear programs. Oper. Res. 33(5), 989–1007 (1985)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  7. 7.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Distance transforms of sampled functions. Technical report, Cornell Computing and Information Science (2004)Google Scholar
  8. 8.
    Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. CoRR abs/1605.03170 (2016), http://arxiv.org/abs/1605.03170
  9. 9.
    Komodakis, N., Paragios, N., Tziritas, G.: MRF optimization via dual decomposition: message-passing revisited. In: Proceedings of ICCV (2007)Google Scholar
  10. 10.
    Levinkov, E., et al.: Joint graph decomposition and node labeling: problem, algorithms, applications. In: Proceedings of CVPR (2017)Google Scholar
  11. 11.
    Magnanti, T.L., Wong, R.T.: Accelerating benders decomposition: algorithmic enhancement and model selection criteria. Oper. Res. 29(3), 464–484 (1981)MathSciNetCrossRefGoogle Scholar
  12. 12.
    McAuley, J.J., Caetano, T.S.: Exploiting data-independence for fast belief-propagation. In: Proceedings of ICML (2010)Google Scholar
  13. 13.
    Murphy, J.: Benders, nested benders and stochastic programming: an intuitive introduction. arXiv preprint arXiv:1312.3158 (2013)
  14. 14.
    Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: Proceedings of CVPR (2011)Google Scholar
  15. 15.
    Pishchulin, L., et al.: DeepCut: joint subset partition and labeling for multi person pose estimation. In: Proceedings of CVPR (2016)Google Scholar
  16. 16.
    Tang, S., Andres, B., Andriluka, M., Schiele, B.: Subgraph decomposition for multi-target tracking. In: Proceedings of CVPR (2015)Google Scholar
  17. 17.
    Yang, Y., Ramanan, D.: Articulated pose estimation with flexible mixtures-of-parts. In: Proceedings of CVPR (2011)Google Scholar
  18. 18.
    Yarkony, J., Fowlkes, C., Ihler, A.: Covering trees and lower-bounds on the quadratic assignment. In: Proceedings of CVPR (2010)Google Scholar
  19. 19.
    Yarkony, J., Ihler, A., Fowlkes, C.C.: Fast planar correlation clustering for image segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 568–581. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33783-3_41CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Shaofei Wang
    • 1
  • Alexander Ihler
    • 2
  • Konrad Kording
    • 3
  • Julian Yarkony
    • 4
  1. 1.Baidu Inc.BeijingChina
  2. 2.UC IrvineIrvineUSA
  3. 3.University of PennsylvaniaPhiladelphiaUSA
  4. 4.Experian Data LabSan DiegoUSA

Personalised recommendations