Advertisement

Weakly Supervised Object Localization with Stable Segmentations

  • Carolina Galleguillos
  • Boris Babenko
  • Andrew Rabinovich
  • Serge Belongie
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5302)

Abstract

Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learning object classifiers from weakly labeled image data, where only the presence of an object in an image is known, but not its location. Some recent work has explored the application of MIL algorithms to the tasks of image categorization and natural scene classification. In this paper we extend these ideas in a framework that uses MIL to recognize and localize objects in images. To achieve this we employ state of the art image descriptors and multiple stable segmentations. These components, combined with a powerful MIL algorithm, form our object recognition system called MILSS. We show highly competitive object categorization results on the Caltech dataset. To evaluate the performance of our algorithm further, we introduce the challenging Landmarks-18 dataset, a collection of photographs of famous landmarks from around the world. The results on this new dataset show the great potential of our proposed algorithm.

Keywords

Image Categorization Object Categorization Salient Region Average Categorization Accuracy Multiple Instance Learn 
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.
Download to read the full conference paper text

References

  1. 1.
    Fergus, R., Perona, P., Zisserman, A.: Weakly supervised scale-invariant learning of models for visual recognition. IJCV 71(3), 273–303 (2007)CrossRefGoogle Scholar
  2. 2.
    Opelt, A., Fussenegger, M., Auer, P.: Generic object recognition with boosting. PAMI 28(3), 416–431 (2006)CrossRefzbMATHGoogle Scholar
  3. 3.
    Russell, B., Efros, A., Sivic, J., Freeman, W., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR (2006)Google Scholar
  4. 4.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering object categories in image collections. In: CVPR (2005)Google Scholar
  5. 5.
    Todorovic, S., Ahuja, N.: Extracting subimages of an unknown category from a set of images. In: CVPR (2006)Google Scholar
  6. 6.
    Bar-Hillel, A., Hertz, T., Weinshall, D.: Object class recognition by boosting a part-based model. In: CVPR (2005)Google Scholar
  7. 7.
    Crandall, D., Huttenlocher, D.: Weakly supervised learning of part-based spatial models for visual object recognition. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 16–29. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Wang, G., Zhang, Y., Fei-Fei, L.: Using dependent regions for object categorization in a generative framework. In: CVPR (2006)Google Scholar
  9. 9.
    Chen, Y., Bi, J., Wang, J.: MILES: Multiple-instance learning via embedded instance selection. PAMI 28(12), 1931–1947 (2006)CrossRefGoogle Scholar
  10. 10.
    Qi, G., Hua, X., Rui, Y., Mei, T., Tang, J., Zhang, H.: Concurrent multiple instance learning for image categorization. In: CVPR (2007)Google Scholar
  11. 11.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR (2003)Google Scholar
  12. 12.
    Dietterich, T.G., Lathrop, R.H., Perez, L.T.: Solving the multiple-instance problem with axis parallel rectangles. AAAI, Menlo Park (1997)zbMATHGoogle Scholar
  13. 13.
    Andrews, S., Hofmann, T., Tsochantaridis, I.: Multiple instance learning with generalized support vector machines. AAAI, Menlo Park (2002)zbMATHGoogle Scholar
  14. 14.
    Viola, P., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. In: NIPS, vol. 18 (2006)Google Scholar
  15. 15.
    Maron, O., Ratan, A.: Multiple-instance learning for natural scene classification. In: ICML (1998)Google Scholar
  16. 16.
    Zhou, Z., Zhang, M.: Multi-instance multi-label learning with application to scene classification. In: NIPS, vol. 19 (2007)Google Scholar
  17. 17.
    Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: NIPS, vol. 15 (2002)Google Scholar
  18. 18.
    Yang, C., Dong, M., Hua, J.: Region-based image annotation using asymmetrical support vector machine-based multi-instance learning. In: CVPR (2006)Google Scholar
  19. 19.
    Chen, Y., Wang, J.: Image categorization by learning and reasoning with regions. JMLR 5, 913–939 (2004)MathSciNetGoogle Scholar
  20. 20.
    Bi, J., Chen, Y., Wang, J.: A sparse support vector machine approach to region-based image categorization. In: CVPR (2005)Google Scholar
  21. 21.
    Friedman, J.H.: Greedy function approximation: A gradient boosting machine. The Annals of Statistics 29(5), 1189–1232 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. JCSS 55, 119–139 (1997)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)Google Scholar
  24. 24.
    Kadir, T., Brady, M.: Saliency, scale and image description. IJCV 45 (2001)Google Scholar
  25. 25.
    Carson, C., Belongie, S., Greenspan, H., Malik, J.: Blobworld: image segmentation using expectation-maximization and its application to image querying. PAMI 24(8), 1026–1038 (2002)CrossRefGoogle Scholar
  26. 26.
    Deng, Y., Manjunath, B.: Unsupervised segmentation of color-texture regions in images and video. PAMI 23(8), 800–810 (2001)CrossRefGoogle Scholar
  27. 27.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. PAMI 22(8), 888–905 (2000)CrossRefGoogle Scholar
  28. 28.
    Rabinovich, A., Lange, T., Buhmann, J., Belongie, S.: Model order selection and cue combination for image segmentation. In: CVPR (2006)Google Scholar
  29. 29.
    Rabinovich, A., Vedaldi, A., Belongie, S.: Does image segmentation improve object categorization? UCSD Technical Report CSE CS2007-0908 (2007)Google Scholar
  30. 30.
    Malisiewicz, T., Efros, A.: Improving spatial support for objects via multiple segmentations. BMVC (2007)Google Scholar
  31. 31.
    Roth, V., Ommer, B.: Exploiting low-level image segmentation for object recognition. In: Franke, K., Müller, K.-R., Nickolay, B., Schäfer, R. (eds.) DAGM 2006. LNCS, vol. 4174, pp. 11–20. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  32. 32.
    Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewora, E., Belongie, S.: Objects in context. In: ICCV (2007)Google Scholar
  33. 33.
    Malik, J., Belongie, S., Shi, J., Leung, T.: Textons, contours and regions: Cue integration in image segmentation. In: ICCV (1999)Google Scholar
  34. 34.
    Lowe, D.: Object recognition from local scale-invariant features. In: ICCV (1999)Google Scholar
  35. 35.
    Cour, T., Benezit, F., Shi, J.: Spectral segmentation with multiscale graph decomposition. In: CVPR (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Carolina Galleguillos
    • 1
  • Boris Babenko
    • 1
  • Andrew Rabinovich
    • 1
  • Serge Belongie
    • 1
    • 2
  1. 1.Computer Science and EngineeringUniversity of CaliforniaSan DiegoUSA
  2. 2.Electrical Engineering, California Institute of TechnologyUSA

Personalised recommendations

Cite paper