Discriminative Decorrelation for Clustering and Classification

  • Bharath Hariharan
  • Jitendra Malik
  • Deva Ramanan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7575)

Abstract

Object detection has over the past few years converged on using linear SVMs over HOG features. Training linear SVMs however is quite expensive, and can become intractable as the number of categories increase. In this work we revisit a much older technique, viz. Linear Discriminant Analysis, and show that LDA models can be trained almost trivially, and with little or no loss in performance. The covariance matrices we estimate capture properties of natural images. Whitening HOG features with these covariances thus removes naturally occuring correlations between the HOG features. We show that these whitened features (which we call WHO) are considerably better than the original HOG features for computing similarities, and prove their usefulness in clustering. Finally, we use our findings to produce an object detection system that is competitive on PASCAL VOC 2007 while being considerably easier to train and test.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  2. 2.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32 (2010)Google Scholar
  3. 3.
    Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3D human pose annotations. In: ICCV (2009)Google Scholar
  4. 4.
    Malisiewicz, T., Gupta, A., Efros, A.A.: Ensemble of exemplar-svms for object detection and beyond. In: ICCV (2011)Google Scholar
  5. 5.
    Fisher, R.: The use of multiple measurements in taxonomic problems. Annals of Human Genetics (1936)Google Scholar
  6. 6.
    Hastie, T., Tibshirani, R., Friedman, J.J.H.: The elements of statistical learning. Springer (2009)Google Scholar
  7. 7.
    Duda, R., Hart, P.: Pattern recognition and scene analysis (1973)Google Scholar
  8. 8.
    Belhumeur, P., Hespanha, J., Kriegman, D.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. TPAMI 19 (1997)Google Scholar
  9. 9.
    Turk, M., Pentland, A.: Eigenfaces for recognition. Journal of Cognitive Neuroscience (1991)Google Scholar
  10. 10.
    Murase, H., Nayar, S.: Visual learning and recognition of 3-D objects from appearance. IJCV 14 (1995)Google Scholar
  11. 11.
    Ke, Y., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: CVPR (2004)Google Scholar
  12. 12.
    Schwartz, W., Kembhavi, A., Harwood, D., Davis, L.: Human detection using partial least squares analysis. In: ICCV (2009)Google Scholar
  13. 13.
    Hyvärinen, A., Hurri, J., Hoyer, P.: Natural Image Statistics: A probabilistic approach to early computational vision (2009)Google Scholar
  14. 14.
    Rue, H., Held, L.: Gaussian Markov random fields: theory and applications (2005)Google Scholar
  15. 15.
    Marlin, B., Schmidt, M., Murphy, K.: Group sparse priors for covariance estimation. In: UAI (2009)Google Scholar
  16. 16.
    Vedaldi, A., Zisserman, A.: Structured output regression for detection with partial truncation. In: NIPS (2009)Google Scholar
  17. 17.
    Gao, T., Packer, B., Koller, D.: A segmentation-aware object detection model with occlusion handling. In: CVPR (2011)Google Scholar
  18. 18.
    Dalal, N.: Finding people in Images and Videos. PhD thesis, INRIA (2006)Google Scholar
  19. 19.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results, http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html
  20. 20.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI 22 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Bharath Hariharan
    • 1
  • Jitendra Malik
    • 1
  • Deva Ramanan
    • 2
  1. 1.Univerisity of California at BerkeleyBerkeleyUSA
  2. 2.University of California at IrvineIrvineUSA

Personalised recommendations