Advertisement

Multi-instance Methods for Partially Supervised Image Segmentation

  • Andreas Müller
  • Sven Behnke
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7081)

Abstract

In this paper, we propose a new partially supervised multi-class image segmentation algorithm. We focus on the multi-class, single-label setup, where each image is assigned one of multiple classes. We formulate the problem of image segmentation as a multi-instance task on a given set of overlapping candidate segments. Using these candidate segments, we solve the multi-instance, multi-class problem using multi-instance kernels with an SVM. This computationally advantageous approach, which requires only convex optimization, yields encouraging results on the challenging problem of partially supervised image segmentation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning, pp. 577–584 (2003)Google Scholar
  2. 2.
    Carreira, J., Sminchisescu, C.: Constrained parametric min-cuts for automatic object segmentation. In: Conference on Computer Vision and Pattern Recognition, pp. 3241–3248 (2010)Google Scholar
  3. 3.
    Catanzaro, B., Su, B.Y., Sundaram, N., Lee, Y., Murphy, M., Keutzer, K.: Efficient, high-quality image contour detection. In: International Conference on Computer Vision, pp. 2381–2388 (2009)Google Scholar
  4. 4.
    Chen, Y., Bi, J., Wang, J.Z.: MILES: Multiple-instance learning via embedded instance selection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1931–1947 (2006)Google Scholar
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Converence on Computer Vision and Pattern Recognition, vol. 1, pp. 886–893 (2005)Google Scholar
  6. 6.
    Dietterich, T., Lathrop, R., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artificial Intelligence 89(1-2), 31–71 (1997)CrossRefzbMATHGoogle Scholar
  7. 7.
    Endres, I., Hoiem, D.: Category independent object proposals, pp. 575–588. Springer, Heidelberg (2010)Google Scholar
  8. 8.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal Visual Object Classes (VOC) Challenger. International Journal of Computer Vision 88(2), 303–338 (2010)CrossRefGoogle Scholar
  9. 9.
    Fulkerson, B., Vedaldi, A., Soatto, S.: Class segmentation and object localization with superpixel neighborhoods. In: International Conference on Computer Vision, pp. 670–677 (2009)Google Scholar
  10. 10.
    Gärtner, T., Flach, P., Kowalczyk, A., Smola, A.: Multi-instance kernels. In: International Conference on Machine Learning, pp. 179–186 (2002)Google Scholar
  11. 11.
    Gonfaus, J., Boix, X., van de Weijer, J., Bagdanov, A., Serrat, J., Gonzalez, J.: Harmony potentials for joint classification and segmentation. In: Conference on Computer Vision and Pattern Recognition (2010)Google Scholar
  12. 12.
    Hanbury, A.: How do superpixels affect image segmentation? In: Progress in Pattern Recognition, Image Analysis and Applications, pp. 178–186 (2008)Google Scholar
  13. 13.
    Jiang, J., Tu, Z.: Efficient scale space auto-context for image segmentation and labeling. In: Conference on Computer Vision and Pattern Recognition, pp. 1810–1817 (2009)Google Scholar
  14. 14.
    Ladicky, L., Russell, C., Kohli, P., Torr, P.: Associative hierarchical CRFs for object class image segmentation. In: International Conference on Computer Vision, pp. 739–746 (2009)Google Scholar
  15. 15.
    Leistner, C., Saffari, A., Bischof, H.: MIForests: Multiple-Instance Learning with Randomized Trees. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6316, pp. 29–42. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  16. 16.
    Li, F., Carreira, J., Sminchisescu, C.: Object recognition as ranking holistic figure-ground hypotheses. In: Conference on Computer Vision and Pattern Recognition, pp. 1712–1719 (2010)Google Scholar
  17. 17.
    Li, F., Sminchisescu, C.: Convex multiple-instance learning by estimating likelihood ratio. In: Advances in Neural Information Processing Systems. pp. 1360–1368 (2010)Google Scholar
  18. 18.
    Li, Y.F., Kwok, J., Tsang, I., Zhou, Z.H.: A convex method for locating regions of interest with multi-instance learning. Machine Learning and Knowledge Discovery in Databases, 15–30 (2009)Google Scholar
  19. 19.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  20. 20.
    Maire, M., Arbeláez, P., Fowlkes, C., Malik, J.: Using contours to detect and localize junctions in natural images. In: Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  21. 21.
    Mangasarian, O., Wild, E.W.: Multiple instance classification via successive linear programming. Journal of Optimization Theory and Applications 137(3), 555–568 (2008)CrossRefzbMATHMathSciNetGoogle Scholar
  22. 22.
    Nguyen, N.: A New SVM Approach to Multi-instance Multi-label Learning. In: International Conference on Data Mining, pp. 384–392 (2010)Google Scholar
  23. 23.
    Russell, B., Torralba, A., Murphy, K., Freeman, W.: LabelMe: A database and web-based tool for image annotation. International Journal of Computer Vision 77(1), 157–173 (2008)CrossRefGoogle Scholar
  24. 24.
    Schroff, F., Criminisi, A., Zisserman, A.: Object class segmentation using random forests. In: British Machine Vision Conference (2008)Google Scholar
  25. 25.
    Schulz, H., Behnke, S.: Object-class segmentation using deep convolutional neural networks. In: Hammer, B., Villmann, T. (eds.) Proceedings of the DAGM Workshop on New Challenges in Neural Computation 2011. Machine Learning Reports, vol. 5, pp. 58–61 (2011)Google Scholar
  26. 26.
    Van De Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. Transactions on Pattern Analysis and Machine Intelligence, 1582–1596 (2009)Google Scholar
  27. 27.
    Verbeek, J., Triggs, B.: Region classification with Markov field aspect models. In: Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar
  28. 28.
    Vezhnevets, A., Buhmann, J.: Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning. In: Computer Vision and Pattern Recognition, pp. 3249–3256 (2010)Google Scholar
  29. 29.
    Vezhnevets, A., Ferrari, V., Buhmann, J.M.: Weakly supervised semantic segmentation with a multi-image model. In: International Conference on Computer Vision (2011)Google Scholar
  30. 30.
    Wang, S., Siskind, J.: Image segmentation with Ratio Cut. IEEE Transactions on Pattern Analysis and Machine Intelligence, 675–690 (2003)Google Scholar
  31. 31.
    Zha, Z., Hua, X., Mei, T., Wang, J., Qi, G., Wang, Z.: Joint multi-label multi-instance learning for image classification. In: Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  32. 32.
    Zhang, M., Zhou, Z.: M3miml: A maximum margin method for multi-instance multi-label learning. In: International Conference on Data Mining, pp. 688–697 (2008)Google Scholar
  33. 33.
    Zhang, Q., Goldman, S.A.: Em-dd: An improved multiple-instance learning technique. In: Advances in Neural Information Processing Systems, vol. 2, pp. 1073–1080 (2002)Google Scholar
  34. 34.
    Zhou, Z., Sun, Y., Li, Y.: Multi-instance learning by treating instances as non-iid samples. In: International Conference on Machine Learning, pp. 1249–1256 (2009)Google Scholar
  35. 35.
    Zhou, Z., Zhang, M.: Multi-instance multi-label learning with application to scene classification. In: Advances in Neural Information Processing Systems, pp. 1609–1616 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Andreas Müller
    • 1
  • Sven Behnke
    • 1
  1. 1.Autonomous Intelligent Systems Department of Computer ScienceUniversity of BonnBonnGermany

Personalised recommendations