Using Neural Network Formalism to Solve Multiple-Instance Problems

  • Tomáš Pevný
  • Petr Somol
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10261)


Many objects in the real world are difficult to describe by means of a single numerical vector of a fixed length, whereas describing them by means of a set of vectors is more natural. Therefore, Multiple instance learning (MIL) techniques have been constantly gaining in importance throughout the last years. MIL formalism assumes that each object (sample) is represented by a set (bag) of feature vectors (instances) of fixed length, where knowledge about objects (e.g., class label) is available on bag level but not necessarily on instance level. Many standard tools including supervised classifiers have been already adapted to MIL setting since the problem got formalized in the late nineties. In this work we propose a neural network (NN) based formalism that intuitively bridges the gap between MIL problem definition and the vast existing knowledge-base of standard models and classifiers. We show that the proposed NN formalism is effectively optimizable by a back-propagation algorithm and can reveal unknown patterns inside bags. Comparison to 14 types of classifiers from the prior art on a set of 20 publicly available benchmark datasets confirms the advantages and accuracy of the proposed solution.


Equal Error Rate Multiple Instance Learning Ground Truth Information Hinge Loss Function Neural Network Formalism 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work has been partially supported by Czech Science Foundation project 15-08916S.


  1. 1.
    Amores, J.: Multiple instance classification: review, taxonomy and comparative study. Artif. Intell. 201, 81–105 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: Becker, S., Thrun, S., Obermayer, K. (eds.) Advances in Neural Information Processing Systems 15, pp. 577–584. MIT Press (2003)Google Scholar
  3. 3.
    Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. arXiv preprint arXiv:1206.5538v2 (2012)
  4. 4.
    Carbonneau, M.-A., Cheplygina, V., Granger, E., Gagnon, G.: Multiple instance learning: a survey of problem characteristics and applications. arXiv preprint arXiv:1612.03365 (2016)
  5. 5.
    Chen, Y., Bi, J., Wang, J.Z.: Miles: multiple-instance learning via embedded instance selection. IEEE Trans. Pattern Anal. Mach. Intell. 28(12), 1931–1947 (2006)CrossRefGoogle Scholar
  6. 6.
    Cheplygina, V., Tax, D.M., Loog, M.: Multiple instance learning with bag dissimilarities. Pattern Recogn. 48(1), 264–275 (2015)CrossRefGoogle Scholar
  7. 7.
    Cheplygina, V., Tax, D.M.J.: Characterizing multiple instance datasets. In: Feragen, A., Pelillo, M., Loog, M. (eds.) SIMBAD 2015. LNCS, vol. 9370, pp. 15–27. Springer, Cham (2015). doi: 10.1007/978-3-319-24261-3_2 CrossRefGoogle Scholar
  8. 8.
    Cheplygina, V., Tax, D.M.J., Loog, M.: Supplemental documents to characterizing multiple instance datasetsGoogle Scholar
  9. 9.
    Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7(Jan), 1–30 (2006)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Dietterich, T.G., Lathrop, R.H., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89(1), 31–71 (1997)CrossRefzbMATHGoogle Scholar
  11. 11.
    Foulds, J., Frank, E.: A review of multi-instance learning assumptions. Knowl. Eng. Rev. 25(01), 1–25 (2010)CrossRefGoogle Scholar
  12. 12.
    Gärtner, T., Flach, P.A., Kowalczyk, A., Smola, A.J.: Multi-instance kernels. In: ICML, vol. 2, pp. 179–186 (2002)Google Scholar
  13. 13.
    Haussler, D.: Convolution kernels on discrete structures, Raport instytutowy, Universityof California at Santa Cruz (1999)Google Scholar
  14. 14.
    Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2146–2153, September 2009Google Scholar
  15. 15.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  16. 16.
    Maron, O., Lozano-Pérez, T.: A framework for multiple-instance learning. In: Jordan, M.I., Kearns, M.J., Solla, S.A. (eds.) Advances in Neural Information Processing Systems 10, pp. 570–576. MIT Press (1998)Google Scholar
  17. 17.
    Muandet, K., Fukumizu, K., Dinuzzo, F., Schölkopf, B.: Learning from distributions via support measure machines. In: Advances in Neural Information Processing Systems, pp. 10–18 (2012)Google Scholar
  18. 18.
    Ramon, J., De Raedt, L.: Multi instance neural networks (2000)Google Scholar
  19. 19.
    Tax, D.M.J., Cheplygina, V.: MIL, A Matlab Toolbox for Multiple Instance Learning, version 1.2.1, June 2016.
  20. 20.
    Wang, J., Zucker, J.-D.: Solving the multiple-instance problem: a lazy learning approach. In: Proceedings of the Seventeenth International Conference on Machine Learning, ICML 2000, pp. 1119–1126. Morgan Kaufmann Publishers Inc., San Francisco (2000)Google Scholar
  21. 21.
    Zhang, C., Platt, J.C., Viola, P.A.: Multiple instance boosting for object detection. In: Weiss, Y., Schölkopf, B., Platt, J.C. (eds.) Advances in Neural Information Processing Systems 18, pp. 1417–1424. MIT Press (2006)Google Scholar
  22. 22.
    Zhang, Q., Goldman, S.A.: EM-DD: an improved multiple-instance learning technique. In: Dietterich, T.G., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems 14, pp. 1073–1080. MIT Press (2002)Google Scholar
  23. 23.
    Zhou, Z.-H., Zhang, M.-L.: Neural networks for multi-instance learning. In: Proceedings of the International Conference on Intelligent Information Technology, vol. 182. Citeseer (2002)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Cisco SystemsPragueCzech Republic
  2. 2.Faculty of Electrical EngineeringCzech Technical UniversityPragueCzech Republic
  3. 3.UTIA, Czech Academy of SciencesPragueCzech Republic

Personalised recommendations