nach oben

Erschienen in:

2017 | OriginalPaper | Buchkapitel

Joint Training of Generic CNN-CRF Models with Stochastic Optimization

verfasst von : A. Kirillov, D. Schlesinger, S. Zheng, B. Savchynskyy, P. H. S. Torr, C. Rother

Erschienen in: Computer Vision – ACCV 2016

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

We propose a new CNN-CRF end-to-end learning framework, which is based on joint stochastic optimization with respect to both Convolutional Neural Network (CNN) and Conditional Random Field (CRF) parameters. While stochastic gradient descent is a standard technique for CNN training, it was not used for joint models so far. We show that our learning method is (i) general, i.e. it applies to arbitrary CNN and CRF architectures and potential functions; (ii) scalable, i.e. it has a low memory footprint and straightforwardly parallelizes on GPUs; (iii) easy in implementation. Additionally, the unified CNN-CRF optimization approach simplifies a potential hardware implementation. We empirically evaluate our method on the task of semantic labeling of body parts in depth images and show that it compares favorably to competing techniques.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Efficient Model Averaging for Deep Neural Networks

Nächstes Kapitel Object-Aware Dictionary Learning with Deep Features

http://host.robots.ox.ac.uk:8080/leaderboard.

We use the commonly adopted terminology from the CNN literature for technical details, to allow reproducibility of our results.

Lin, G., Shen, C., Reid, I.D., van den Hengel, A.: Efficient piecewise training of deep structured models for semantic segmentation. preprint arXiv:1504.01013 (2015)

Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML, pp. 282–289 (2001)

Chen, L., Schwing, A.G., Yuille, A.L., Urtasun, R.: Learning deep structured models. In: ICML, pp. 1785–1794 (2015)

Nowozin, S., Rother, C., Bagon, S., Sharp, T., Yao, B., Kohli, P.: Decision tree fields. In: ICCV (2011)

Sethi, I.K.: Entropy nets: from decision trees to neural networks. Proc. IEEE 78, 1605–1613 (1990)CrossRef

Richmond, D.L., Kainmueller, D., Yang, M.Y., Myers, E.W., Rother, C.: Relating cascaded random forests to deep convolutional neural networks for semantic segmentation. preprint arXiv:1507.07583 (2015)

Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. preprint arXiv:1411.4038 (2014)

Farabet, C., Couprie, C., Najman, L., LeCun, Y.: Learning hierarchical features for scene labeling. TPAMI 35, 1915–1929 (2013)CrossRef

Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. preprint arXiv:1412.7062 (2014)

10.

Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. In: NIPS (2011)

11.

Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.H.S.: Conditional random fields as recurrent neural networks. In: Proceedings of ICCV (2015)

12.

Schwing, A.G., Urtasun, R.: Fully connected deep structured networks. preprint arXiv:1503.02351 (2015)

13.

Adams, A., Baek, J., Davis, M.A.: Fast high-dimensional filtering using the permutohedral lattice. In: Computer Graphics Forum, vol. 29. Wiley Online Library (2010)

14.

Domke, J.: Learning graphical model parameters with approximate marginal inference. TPAMI 35, 2454–2467 (2013)

15.

Kiefel, M., Gehler, P.V.: Human pose estimation with fields of parts. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 331–346. Springer, Heidelberg (2014). doi:10.1007/978-3-319-10602-1_22

16.

Barbu, A.: Training an active random field for real-time image denoising. IEEE Trans. Image Process. 18, 2451–2462 (2009)MathSciNetCrossRef

17.

Ross, S., Munoz, D., Hebert, M., Bagnell, J.A.: Learning message-passing inference machines for structured prediction. In: Proceedings of CVPR (2011)

18.

Stoyanov, V., Ropson, A., Eisner, J.: Empirical risk minimization of graphical model parameters given approximate inference, decoding, and model structure. In: Proceedings of AISTATS (2011)

19.

Tompson, J.J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: Proceedings of NIPS (2014)

20.

Liu, Z., Li, X., Luo, P., Loy, C.C., Tang, X.: Semantic image segmentation via deep parsing network. In: Proceedings of ICCV (2015)

21.

Sutton, C., McCallum, A.: Piecewise training of undirected models. In: Conference on Uncertainty in Artificial Intelligence (UAI) (2005)

22.

He, X., Zemel, R.S., Carreira-perpiñán, M.Á.: Multiscale conditional random fields for image labeling. In: CVPR. Citeseer (2004)

23.

Wainwright, M.J., Jordan, M.I.: Graphical models, exponential families, and variational inference. Found. Trends\({\textregistered }\) Mach. Learn. 1, 1–305 (2008)

24.

Geman, S., Geman, D.: Stochastic relaxation, gibbs distributions, and the Bayesian restoration of images. TPAMI 6, 721–741 (1984)CrossRefMATH

25.

Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 400–407 (1951)

26.

Spall, J.C.: Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control, vol. 65. Wiley, Hoboken (2005)MATH

27.

Geyer, C.J.: Practical Markov chain Monte Carlo. Stat. Sci. 473–483 (1992)

28.

Lauritzen, S.L.: Graphical Models. Oxford University Press, Oxford (1996)MATH

29.

Gonzalez, J., Low, Y., Gretton, A., Guestrin, C.: Parallel Gibbs sampling: from colored fields to thin junction trees. In: International Conference on Artificial Intelligence and Statistics. pp. 324–332 (2011)

30.

Hinton, G.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14, 1771–1800 (2002)CrossRefMATH

31.

Yuille, A.L.: The convergence of contrastive divergences. In: NIPS (2004)

32.

Tieleman, T.: Training restricted Boltzmann machines using approximations to the likelihood gradient. In: ICML. ACM, New York (2008)

33.

Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC 2012) Results

34.

Hariharan, B., Arbelaez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: International Conference on Computer Vision (ICCV) (2011)

35.

Denil, M., Matheson, D., de Freitas, N.: Consistency of online random forests. In: ICML (2013)

36.

Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates Inc., New York (2012)

37.

Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)

38.

Ren, S., Cao, X., Wei, Y., Sun, J.: Global refinement of random forest. In: CVPR (2015)

39.

Cheng, M.M., Prisacariu, V.A., Zheng, S., Torr, P.H.S., Rother, C.: Densecut: densely connected CRFs for realtime Grabcut. Comput. Graph. Forum 34, 193–201 (2015)CrossRef

Titel: Joint Training of Generic CNN-CRF Models with Stochastic Optimization
verfasst von: A. Kirillov
D. Schlesinger
S. Zheng
B. Savchynskyy
P. H. S. Torr
C. Rother
Verlag: Springer International Publishing
Buch: Computer Vision – ACCV 2016
Print ISBN: 978-3-319-54183-9

Electronic ISBN: 978-3-319-54184-6

Copyright-Jahr: 2017
DOI: https://doi.org/10.1007/978-3-319-54184-6_14

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner