Abstract
Recent research shows that estimating labels and graph structures simultaneously in Markov random Fields can be achieved via solving LP problems. The scalability is a bottleneck that prevents applying such technique to larger problems such as image segmentation and object detection. Here we present a fast message passing algorithm based on the mixed-integer bilinear programming formulation of the original problem. We apply our algorithm to both synthetic data and real-world applications. It compares favourably with previous methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
To compute these features, we need low-level image descriptors. All evaluating methods using the potential function (18) use the same descriptors extracted by us.
References
Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context. IJCV 81, 2–23 (2009)
Pearl, J.: Reverend bayes on inference engines: A distributed hierarchical approach. In: AAAI, pp. 133–136 (1982)
Nowozin, S., Rother, C., Bagon, S., Sharp, T., Yao, B., Kohli, P.: Decision tree fields. In: ICCV (2011)
Lan, T., Wang, Y., Mori, G.: Beyond actions: Discriminative models for contextual group activities. In: NIPS (2010)
Wang, Z., Shi, Q., Shen, C., van den Hengel, A.: Bilinear programming for human activity recognition with unknown mrf graphs. In: CVPR (2013)
Adams, W.P., Sherali, H.D.: Mixed-integer bilinear programming problems. Math. Program. 59, 279–305 (1993)
Hiroshi, K.: Bilinear Programming: Part I. An Algorithm for Solving Bilinear Programs. Technical Report No. 71-9, Operations Research House, Stanford University (1971)
Globerson, A., Jaakkola, T.: Fixing max-product: Convergent message passing algorithms for map lp-relaxations. In: NIPS (2007)
Andersen, E., Andersen, K.: Mosek (version 7). Academic version (2013). www.mosek.com
Ravikumar, P., Lafferty, J.: Quadratic programming relaxations for metric labeling and markov random field map estimation. In: ICML (2006)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: CVPR, pp. 3354–3361 (2012)
Sengupta, S., Greveson, E., Shahrokni, A., Torr, P.H.: Urban 3d semantic modelling using stereo vision. In: International Conference on Robotics and Automation, pp. 580–585 (2013)
Cadena, C., Košecká, J.: Semantic segmentation with heterogeneous sensor coverages. In: International Conference on Robotics and Automation (2014)
Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008). http://www.vlfeat.org/
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)
Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. JMLR 6, 1453–1484 (2006)
Acknowledgement
We thank Qinfeng Shi for his suggestion on the exposition of this paper. We thank Cesar Dario Cadena Lerma for his help on using the KITTI dataset. This work was supported by a grant from the National High Technology Research and Development Program of China (863 Program) (No. 2013AA10230402), and a grant from the Fundamental Research Funds of Northwest A&F University (No. QN2013056).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, Z., Zhang, Z., Geng, N. (2015). A Message Passing Algorithm for MRF Inference with Unknown Graphs and Its Applications. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9006. Springer, Cham. https://doi.org/10.1007/978-3-319-16817-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-16817-3_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16816-6
Online ISBN: 978-3-319-16817-3
eBook Packages: Computer ScienceComputer Science (R0)