Advertisement

ClassCut for Unsupervised Class Segmentation

  • Bogdan Alexe
  • Thomas Deselaers
  • Vittorio Ferrari
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)

Abstract

We propose a novel method for unsupervised class segmentation on a set of images. It alternates between segmenting object instances and learning a class model. The method is based on a segmentation energy defined over all images at the same time, which can be optimized efficiently by techniques used before in interactive segmentation. Over iterations, our method progressively learns a class model by integrating observations over all images. In addition to appearance, this model captures the location and shape of the class with respect to an automatically determined coordinate frame common across images. This frame allows us to build stronger shape and location models, similar to those used in object class detection. Our method is inspired by interactive segmentation methods [1], but it is fully automatic and learns models characteristic for the object class rather than specific to one particular object/image. We experimentally demonstrate on the Caltech4, Caltech101, and Weizmann horses datasets that our method (a) transfers class knowledge across images and this improves results compared to segmenting every image independently; (b) outperforms Grabcut [1] for the task of unsupervised segmentation; (c) offers competitive performance compared to the state-of-the-art in unsupervised segmentation and in particular it outperforms the topic model [2].

Keywords

Reference Frame Location Model Object Class Shape Model Appearance Model 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rother, C., Kolmogorov, V., Blake, A.: GrabCut: interactive foreground extraction using iterated graph cuts. SIGGRAPH 23, 309–314 (2004)CrossRefGoogle Scholar
  2. 2.
    Cao, L., Li, F.F.: Spatially coherent latent topic model for concurrent segmentation and classification of objects and scene. In: ICCV (2007)Google Scholar
  3. 3.
    Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: ICCV (2001)Google Scholar
  4. 4.
    Lempitsky, V., Kohli, P., Rother, C., Sharp, T.: Image segmentation with a bounding box prior. In: ICCV (2009)Google Scholar
  5. 5.
    Schroff, F., Criminisi, A., Zisserman, A.: Object class segmentation using random forests. In: Proceedings of the British Machine Vision Conference (2008)Google Scholar
  6. 6.
    Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling appearance, shape and context. IJCV 81, 2–23 (2009)CrossRefGoogle Scholar
  7. 7.
    Kumar, M.P., Torr, P.H.S., Zisserman, A.: OBJ CUT. In: CVPR (2005)Google Scholar
  8. 8.
    Borenstein, E., Ullman, S.: Learning to segment. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 315–328. Springer, Heidelberg (2004)Google Scholar
  9. 9.
    Arora, H., Loeff, N., Forsyth, D., Ahuja, N.: Unsupervised segmentation of objects using efficient learning. In: CVPR (2007)Google Scholar
  10. 10.
    Winn, J., Jojic, N.: LOCUS: learning object classes with unsupervised segmentation. In: ICCV (2005)Google Scholar
  11. 11.
    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
  12. 12.
    Todorovic, S., Ahuja, N.: Extracting subimages of an unknown category from a set of images. In: CVPR (2006)Google Scholar
  13. 13.
    Galleguillos, C., Babenko, B., Rabinovich, A., Belongie, S.: Weakly supervised object localization with stable segmentations. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 193–207. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  14. 14.
    Kolmogorov, V., Rother, C.: Minimizing nonsubmodular functions with graph cuts – a review. PAMI 29, 1274–1279 (2007)Google Scholar
  15. 15.
    Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. PAMI 28, 1568–1583 (2006)Google Scholar
  16. 16.
    Dalal, N., Triggs, B.: Histogram of Oriented Gradients for Human Detection. In: CVPR (2005)Google Scholar
  17. 17.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI (2009) (in press)Google Scholar
  18. 18.
    Alexe, B., Deselaers, T., Ferrari, V.: What is an object?. In: CVPR (2010)Google Scholar
  19. 19.
    Fulkerson, B., Vedaldi, A., Soatto, S.: Localizing objects with smart dictionaries. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 179–192. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  20. 20.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, vol. 2, pp. 264–271 (2003)Google Scholar
  21. 21.
    Rother, C., Kolmogorov, V., Minka, T., Blake, A.: Cosegmentation of image pairs by histogram matching - incorporating a global constraint into MRFs. In: CVPR (2006)Google Scholar
  22. 22.
    Rother, C., Kolmogorov, V., Lempitsky, V., Szummer, M.: Optimizing binary MRFs via extended roof duality. In: CVPR (2007)Google Scholar
  23. 23.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: ECCV Workshop on Stat. Learn. in: Comp. Vis. (2004)Google Scholar
  24. 24.
    Bay, H., Ess, A., Tuytelaars, T., van Gool, L.: SURF: Speeded up robust features. CVIU 110, 346–359 (2008)Google Scholar
  25. 25.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59, 167–181 (2004)CrossRefGoogle Scholar
  26. 26.
    Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color and texture cues. PAMI 26, 530–549 (2003)Google Scholar
  27. 27.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR (2003)Google Scholar
  28. 28.
    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: IEEE CVPR Workshop of Generative Model Based Vision (2004)Google Scholar
  29. 29.
    Lee, Y.J., Grauman, K.: Collect-cut: Segmentation with top-down cues discovered in multi-object images. In: CVPR (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Bogdan Alexe
    • 1
  • Thomas Deselaers
    • 1
  • Vittorio Ferrari
    • 1
  1. 1.Computer Vision LaboratoryETH ZurichZurichSwitzerland

Personalised recommendations