Multiple-Instance Learning with Instance Selection via Dominant Sets

  • Aykut Erdem
  • Erkut Erdem
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7005)


Multiple-instance learning (MIL) deals with learning under ambiguity, in which patterns to be classified are described by bags of instances. There has been a growing interest in the design and use of MIL algorithms as it provides a natural framework to solve a wide variety of pattern recognition problems. In this paper, we address MIL from a view that transforms the problem into a standard supervised learning problem via instance selection. The novelty of the proposed approach comes from its selection strategy to identify the most representative examples in the positive and negative training bags, which is based on an effective pairwise clustering algorithm referred to as dominant sets. Experimental results on both standard benchmark data sets and on multi-class image classification problems show that the proposed approach is not only highly competitive with state-of-the-art MIL algorithms but also very robust to outliers and noise.


Negative Instance Instance Selection Multiple Instance Learning Label Noise Instance Prototype 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: NIPS, pp. 1073–1080 (2003)Google Scholar
  2. 2.
    Babenko, B., Yang, M.H., Belongie, S.: Visual tracking with online multiple instance learning. In: CVPR, pp. 983–990 (2009)Google Scholar
  3. 3.
    Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines (2001), software
  4. 4.
    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
  5. 5.
    Chen, Y., Wang, J.Z.: Image categorization by learning and reasoning with regions. J. Mach. Learn. Res. 5, 913–939 (2004)MathSciNetGoogle Scholar
  6. 6.
    Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: ECCV Int. Workshop Stat. Learning in Comp. Vis. (2004)Google Scholar
  7. 7.
    Dietterich, T.G., Lathrop, R.H., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89(1-2), 31–71 (1997)CrossRefzbMATHGoogle Scholar
  8. 8.
    Fu, Z., Robles-Kelly, A., Zhou, J.: MILIS: Multiple instance learning with instance selection. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 958–977 (2011)CrossRefGoogle Scholar
  9. 9.
    Gärtner, T., Flach, P.A., Kowalczyk, A., Smola, A.J.: Multi-instance kernels. In: ICML, pp. 179–186 (2002)Google Scholar
  10. 10.
    Leistner, C., Saffari, A., Bischof, H.: MIForests: Multiple-instance learning with randomized trees. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 29–42. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  11. 11.
    Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: ICCV, vol. 2, pp. 1482–1489 (2005)Google Scholar
  12. 12.
    Li, M., Kwok, J., Lu, B.L.: Online multiple instance learning with no regret. In: CVPR, pp. 1395–1401 (2010)Google Scholar
  13. 13.
    Li, W.J., Yeung, D.Y.: MILD: Multiple-instance learning via disambiguation. IEEE Trans. on Knowl. and Data Eng. 22, 76–89 (2010)CrossRefGoogle Scholar
  14. 14.
    Li, Y.F., Kwok, J.T., Tsang, I.W., Zhou, Z.H.: A convex method for locating regions of interest with multi-instance learning. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009, Part II. LNCS, vol. 5782, pp. 15–30. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  15. 15.
    Liu, H., Yan, S.: Common visual pattern discovery via spatially coherent correspondences. In: CVPR, pp. 1609–1616 (2010)Google Scholar
  16. 16.
    Maron, O., Lozano-Pérez, T.: A framework for multiple instance learning. In: NIPS, pp. 570–576 (1998)Google Scholar
  17. 17.
    Motzkin, T.S., Straus, E.G.: Maxima for graphs and a new proof of a theorem of Turán. Canad. J. Math. 17, 533–540 (1965)CrossRefzbMATHGoogle Scholar
  18. 18.
    Pavan, M., Pelillo, M.: Dominant sets and pairwise clustering. IEEE Trans. on Pattern Anal. and Mach. Intell. 29(1), 167–172 (2007)CrossRefGoogle Scholar
  19. 19.
    Rota Bulò, S., Bomze, I., Pelillo, M.: Fast population game dynamics for dominant sets and other quadratic optimization problems. In: Hancock, E.R., Wilson, R.C., Windeatt, T., Ulusoy, I., Escolano, F. (eds.) SSPR&SPR 2010. LNCS, vol. 6218, pp. 275–285. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  20. 20.
    Sarkar, S., Boyer, K.L.: Quantitative measures of change based on feature organization: Eigenvalues and eigenvectors. Comput. Vis. Image Understand. 71(1), 110–136 (1998)CrossRefGoogle Scholar
  21. 21.
    Viola, P., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. In: NIPS, pp. 1419–1426 (2006)Google Scholar
  22. 22.
    Wang, J., Zucker, J.-D.: Solving multiple-instance problem: A lazy learning approach. In: ICML (2000)Google Scholar
  23. 23.
    Zha, Z.J., Hua, X.S., Mei, T., Wang, J., Qi, G.J., Wang, Z.: Joint multi-label multi-instance learning for image classification. In: CVPR (2008)Google Scholar
  24. 24.
    Zhang, Q., Goldman, S.A.: EM-DD: An improved multi-instance learning technique. In: NIPS, pp. 561–568 (2002)Google Scholar
  25. 25.
    Zhang, Q., Goldman, S.A., Yu, W., Fritts, J.: Content-based image retrieval using multiple-instance learning. In: ICML, pp. 682–689 (2002)Google Scholar
  26. 26.
    Zhou, Z.H., Xu, J.M.: On the relation between multi-instance learning and semi-supervised learning. In: ICML, pp. 1167–1174 (2007)Google Scholar
  27. 27.
    Zhou, Z.H., Zhang, M.L.: Multi-instance multi-label learning with applications to scene classification. In: NIPS, pp. 1609–1616 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Aykut Erdem
    • 1
  • Erkut Erdem
    • 1
  1. 1.Hacettepe UniversityBeytepeTurkey

Personalised recommendations