Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben
Erschienen in:
Reflection Symmetry Detection via Appearance of Structure Descriptor Kapitel lesen Erstes Kapitel lesen

2016 | OriginalPaper | Buchkapitel

Learning Diverse Models: The Coulomb Structured Support Vector Machine

verfasst von : Martin Schiegg, Ferran Diego, Fred A. Hamprecht

Erschienen in: Computer Vision – ECCV 2016

Verlag: Springer International Publishing

Einloggen

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

search-config
loading …

Abstract

In structured prediction, it is standard procedure to discriminatively train a single model that is then used to make a single prediction for each input. This practice is simple but risky in many ways. For instance, models are often designed with tractability rather than faithfulness in mind. To hedge against such model misspecification, it may be useful to train multiple models that all are a reasonable fit to the training data, but at least one of which may hopefully make more valid predictions than the single model in standard procedure. We propose the Coulomb Structured SVM (CSSVM) as a means to obtain at training time a full ensemble of different models. At test time, these models can run in parallel and independently to make diverse predictions. We demonstrate on challenging tasks from computer vision that some of these diverse predictions have significantly lower task loss than that of a single model, and improve over state-of-the-art diversity encouraging approaches.

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 Abundant Inverse Regression Using Sufficient Reduction and Its Applications
Nächstes Kapitel Pose Hashing with Microlens Arrays
Fußnoten
1
Note that this is almost always true once we have a sufficient number of independent features, see the function counting theorem [23].
 
2
Note that we want to approximate this problem in a high dimensional space instead of only 3 dimensions.
 
3
Note that we assume electrostatic charges on the parameters, and not the training samples as done in [37].
 
Literatur
1.
Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. JMLR 6, 1453–1484 (2005)MathSciNetMATH
2.
Nowozin, S., Lampert, C.H.: Structured learning and prediction in computer vision. Found. Trends Comput. Graph. Vis. 6(3–4), 185–365 (2011)MATH
3.
Yanover, C., Weiss, Y.: Finding the M most probable configurations in arbitrary graphical models. In: NIPS 2003, pp. 289–296 (2003)
4.
Papandreou, G., Yuille, A.L.: Perturb-and-map random fields: using discrete optimization to learn and sample from energy models. In: ICCV (2011)
5.
Batra, D., Yadollahpour, P., Guzman-Rivera, A., Shakhnarovich, G.: Diverse M-best solutions in Markov random fields. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 1–16. Springer, Heidelberg (2012)
6.
Guzman-Rivera, A., Batra, D., Kohli, P.: Multiple choice learning: learning to produce multiple structured outputs. In: NIPS, pp. 1808–1816 (2012)
7.
Guzman-Rivera, A., Kohli, P., Batra, D., Rutenbar, R.A.: Efficiently enforcing diversity in multi-output structured prediction. In: AISTATS (2014)
8.
Gane, A., Hazan, T., Jaakkola, T.: Learning with maximum a-posteriori perturbation models. In: AISTATS, pp. 247–256 (2014)
9.
Yadollahpour, P., Batra, D., Shakhnarovich, G.: Discriminative re-ranking of diverse segmentations. In: CVPR (2013)
10.
Gimpel, K., Batra, D., Dyer, C., Shakhnarovich, G.: A systematic exploration of diversity in machine translation. In: EMNLP (2013)
11.
Roig, G., Boix, X., de Nijs, R., Ramos, S., Kühnlenz, K., Van Gool, L.: Active MAP inference in CRFs for efficient semantic segmentation. In: ICCV (2013)
12.
Maji, S., Hazan, T., Jaakkola, T.: Active boundary annotation using random map perturbations. In: AISTATS (2014)
13.
Premachandran, V., Tarlow, D., Batra, D.: Empirical minimum bayes risk prediction: how to extract an extra few % performance from vision models with just three more parameters. In: CVPR (2014)
14.
Kirillov, A., Savchynskyy, B., Schlesinger, D., Vetrov, D., Rother, C.: Inferring m-best diverse labelings in a single one. In: ICCV, pp. 1814–1822 (2015)
15.
Hazan, T., Maji, S., Jaakkola, T.: On sampling from the Gibbs distribution with random maximum a-posteriori perturbations. In: NIPS, pp. 1268–1276 (2013)
16.
Chen, C., Kolmogorov, V., Zhu, Y., Metaxas, D., Lampert, C.: Computing the M most probable modes of a graphical model. In: AISTATS, pp. 161–169 (2013)
17.
Chen, C., Liu, H., Metaxas, D., Zhao, T.: Mode estimation for high dimensional discrete tree graphical models. In: NIPS, pp. 1323–1331 (2014)
18.
19.
Lucchi, A., Li, Y., Smith, K., Fua, P.: Structured image segmentation using kernelized features. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 400–413. Springer, Heidelberg (2012)
20.
Lou, X., Hamprecht, F.A.: Structured learning for cell tracking. In: NIPS (2011)
21.
Li, Y.F., Zhou, Z.H.: Towards making unlabeled data never hurt. IEEE Trans. PAMI 37(1), 175–188 (2015)CrossRef
22.
Lampert, C.H.: Maximum margin multi-label structured prediction. In: NIPS, pp. 289–297 (2011)
23.
Cover, T.M.: Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Trans. Electron. Comput. EC–14(3), 326–334 (1965)CrossRefMATH
24.
Mitchell, T.M.: Machine Learning, 1st edn. McGraw-Hill Inc., New York (1997)MATH
25.
Herbrich, R., Graepel, T., Williamson, R.C.: The structure of version space. Technical report MSR-TR-2004-63, Microsoft Research, July 2004
26.
27.
Graepel, T., Herbrich, R.: The kernel Gibbs sampler. In: NIPS, pp. 514–520 (2001)
28.
Sacks, J., Welch, W.J., Mitchell, T.J., Wynn, H.P.: Design and analysis of computer experiments. Stat. Sci. 4, 409–423 (1989)MathSciNetCrossRefMATH
29.
Hardin, R., Sloane, N.: A new approach to the construction of optimal designs. J. Stat. Plann. Infer. 37(3), 339–369 (1993)MathSciNetCrossRefMATH
30.
Conway, J.H., Sloane, N.J.A.: Sphere-packings, Lattices, and Groups. Springer, New York (1987)MATH
31.
32.
33.
Claxton, T., Benson, G.: Stereochemistry and seven coordination. Can. J. Chem. 44(2), 157–163 (1966)CrossRef
34.
Erber, T., Hockney, G.: Equilibrium configurations of n equal charges on a sphere. J. Phys. A: Math. Gen. 24(23), L1369 (1991)CrossRef
35.
Lakhbab, H., EL Bernoussi, S., EL Harif, A.: Energy minimization of point charges on a sphere with a spectral projected gradient method. Int. J. Sci. Eng. Res. 3(5) (2012)
36.
37.
Hochreiter, S., Mozer, M.C., Obermayer, K.: Coulomb classifiers: generalizing support vector machines via an analogy to electrostatic systems. In: NIPS, pp. 561–568 (2003)
38.
Ratliff, N.D., Bagnell, J.A., Zinkevich, M.A.: (Online) Subgradient methods for structured prediction. In: AISTATS (2007)
39.
Prasad, A., Jegelka, S., Batra, D.: Submodular meets structured: finding diverse subsets in exponentially-large structured item sets. In: NIPS, pp. 2645–2653 (2014)
40.
Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T.: iCoseg: interactive co-segmentation with intelligent scribble guidance. In: CVPR (2010)
41.
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge. Int. J. Comput. Vis. 88, 303–338 (2010)CrossRef
42.
Tsai, Y.H., Yang, J., Yang, M.H.: Decomposed learning for joint object segmentation and categorization. In: BMVC (2013)
43.
Lee, T., Fidler, S., Dickinson, S.: Learning to combine mid-level cues for object proposal generation. In: CVPR, pp. 1680–1688 (2015)
44.
Wang, S., Fidler, S., Urtasun, R.: Lost shopping! monocular localization in large indoor spaces. In: ICCV (2015)
45.
Müller, A.C., Behnke, S.: PyStruct - learning structured prediction in python. JMLR 15, 2055–2060 (2014)MathSciNetMATH
46.
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE Trans. PAMI 28(10), 1568–1583 (2006)CrossRef
47.
Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In: CVPR, pp. 993–1000 (2006)
48.
Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: NIPS (2011)
Metadaten
Titel
Learning Diverse Models: The Coulomb Structured Support Vector Machine
verfasst von
Martin Schiegg
Ferran Diego
Fred A. Hamprecht
Copyright-Jahr
2016
Buch
Computer Vision – ECCV 2016

Print ISBN: 978-3-319-46486-2

Electronic ISBN: 978-3-319-46487-9

Copyright-Jahr: 2016

DOI
https://doi.org/10.1007/978-3-319-46487-9_36