Ensemble Partitioning for Unsupervised Image Categorization

  • Dengxin Dai
  • Mukta Prasad
  • Christian Leistner
  • Luc Van Gool
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7574)

Abstract

While the quality of object recognition systems can strongly benefit from more data, human annotation and labeling can hardly keep pace. This motivates the usage of autonomous and unsupervised learning methods. In this paper, we present a simple, yet effective method for unsupervised image categorization, which relies on discriminative learners. Since automatically obtaining error-free labeled training data for the learners is infeasible, we propose the concept of weak training (WT) set. WT sets have various deficiencies, but still carry useful information. Training on a single WT set cannot result in good performance, thus we design a random walk sampling scheme to create a series of diverse WT sets. This naturally allows our categorization learning to leverage ensemble learning techniques. In particular, for each WT set, we train a max-margin classifier to further partition the whole dataset to be categorized. By doing so, each WT set leads to a base partitioning of the dataset and all the base partitionings are combined into an ensemble proximity matrix. The final categorization is completed by feeding this proximity matrix into a spectral clustering algorithm. Experiments on a variety of challenging datasets show that our method outperforms competing methods by a considerable margin.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)Google Scholar
  2. 2.
    Bosch, A., Zisserman, A., Muoz, X.: Image classification using random forests and ferns. In: ICCV (2007)Google Scholar
  3. 3.
    Boiman, O., Shechtman, E., Irani, M.: In defense of nearest-neighbor based image classification. In: CVPR (2008)Google Scholar
  4. 4.
    Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database large-scale scene recognition from abbey to zoo. In: CVPR (2010)Google Scholar
  5. 5.
    Fergus, R., Weiss, Y., Torralba, A.: Semi-supervised learning in gigantic image collections. In: NIPS (2009)Google Scholar
  6. 6.
    Deselaers, T., Alexe, B., Ferrari, V.: Localizing Objects While Learning Their Appearance. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 452–466. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Blaschko, M.B., Vedaldi, A., Zisserman, A.: Simultaneous object detection and ranking with weak supervision. In: NIPS (2010)Google Scholar
  8. 8.
    Dietterich, T.G.: Ensemble Methods in Machine Learning. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 1–15. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  9. 9.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR (2003)Google Scholar
  10. 10.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their location in images. In: ICCV (2005)Google Scholar
  11. 11.
    Sivic, J., Russell, B.C., Zisserman, A., Freeman, W.T., Efros, A.A.: Unsupervised discovery of visual object class hierarchies. In: CVPR (2008)Google Scholar
  12. 12.
    Dai, D., Wu, T., Zhu, S.C.: Discovering scene categories by information projection and cluster sampling. In: CVPR (2010)Google Scholar
  13. 13.
    Dueck, D., Frey, B.J.: Non-metric affinity propagation for unsupervised image categorization. In: ICCV (2007)Google Scholar
  14. 14.
    Frey, B.J., Dueck, D.: Clustering by passing messages between data points. Science 315, 972–976 (2007)MathSciNetMATHCrossRefGoogle Scholar
  15. 15.
    Grauman, K., Darrell, T.: Unsupervised learning of categories from sets of partially matching image features. In: CVPR (2006)Google Scholar
  16. 16.
    Tuytelaars, T., Lampert, C.H., Blaschko, M.B., Buntine, W.: Unsupervised object discovery: A comparison. IJCV 88, 284–302 (2009)CrossRefGoogle Scholar
  17. 17.
    Gomes, R., Krause, A., Perona, P.: Discriminative clustering by regularized information maximization. In: NIPS (2010)Google Scholar
  18. 18.
    Lee, Y.J., Grauman, K.: Learning the easy things first: Self-paced visual category discovery. In: CVPR (2011)Google Scholar
  19. 19.
    Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML (2009)Google Scholar
  20. 20.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive Logistic Regression: a Statistical View of Boosting. The Annals of Statistics 28, 337–407 (2000)MathSciNetMATHCrossRefGoogle Scholar
  21. 21.
    Breiman, L.: Bagging predictors. ML 24, 123–140 (1996)MathSciNetMATHGoogle Scholar
  22. 22.
    Breiman, L.: Random forest. ML 45, 5–32 (2001)MATHGoogle Scholar
  23. 23.
    Leisch, F.: Bagged clustering. Working Paper Series (1999)Google Scholar
  24. 24.
    Saffari, A., Bischof, H.: Clustering in a boosting framework. In: CVWW (2007)Google Scholar
  25. 25.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV 41, 145–175 (2001)CrossRefGoogle Scholar
  26. 26.
    Ojala, T., Pietikinen, M., Menp, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. PAMI 24, 971–987 (2002)CrossRefGoogle Scholar
  27. 27.
    Harel, D., Koren, Y.: On Clustering Using Random Walks. In: Hariharan, R., Mukund, M., Vinay, V. (eds.) FSTTCS 2001. LNCS, vol. 2245, pp. 18–41. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  28. 28.
    Malisiewicz, T., Gupta, A., Efros, A.A.: Ensemble of exemplar-svms for object detection and beyond. In: ICCV (2011)Google Scholar
  29. 29.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: WGMBV (2004)Google Scholar
  30. 30.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  31. 31.
    Zelnik-Manor, L., Perona, P.: Self-tuning spectral clustering. In: NIPS (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Dengxin Dai
    • 1
  • Mukta Prasad
    • 1
  • Christian Leistner
    • 1
  • Luc Van Gool
    • 1
  1. 1.Computer Vision Lab.ETH ZürichSwitzerland

Personalised recommendations