Deconstructing Binary Classifiers in Computer Vision

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9005)

Abstract

This paper further develops the novel notion of deconstructive learning and proposes a practical model for deconstructing a broad class of binary classifiers commonly used in vision applications. Specifically, the problem studied in this paper is: Given an image-based binary classifier \({\mathbf {C}}\) as a black-box oracle, how much can we learn of its internal working by simply querying it? To formulate and answer this question computationally, we propose a novel framework that explicitly identifies and delineates the computer vision and machine learning components, and we propose an effective deconstruction algorithm for deconstructing binary classifiers with the typical two-component design that employ support vector machine or cascade of linear classifiers as their internal feature classifiers. The deconstruction algorithm simultaneously searches over a collection of candidate feature spaces by probing the spaces for the decision boundaries, using the labels provided by the given classifier. In particular, we demonstrate that it is possible to ascertain the type of kernel function used by the classifier and the number of support vectors (and the subspace spanned by the support vectors) using only image queries and ascertain the unknown feature space too. Furthermore, again using only simple image queries, we are able to completely deconstruct OpenCV’s pedestrian detector, ascertain the exact feature used, the type of classifier employed and recover the (almost) exact linear classifier.

Supplementary material

336663_1_En_31_MOESM1_ESM.zip (105 kb)
Supplementary material (zip 106 KB)

References

  1. 1.
    Ali, M., Rushdi, M., Ho, J.: Deconstructing kernel machines. In: Calders, T., Esposito, F., Hüllermeier, E., Meo, R. (eds.) ECML PKDD 2014, Part I. LNCS, vol. 8724, pp. 34–49. Springer, Heidelberg (2014) CrossRefGoogle Scholar
  2. 2.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  3. 3.
    Benenson, R., Mathias, M., Timofte, R., Van Gool, L.: Pedestrian detection at 100 frames per second. In: CVPR (2012)Google Scholar
  4. 4.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1, p. I-511. IEEE (2001)Google Scholar
  5. 5.
    Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2, pp. 524–531. IEEE (2005)Google Scholar
  6. 6.
    Bosch, A., Zisserman, A., Muñoz, X.: Scene classification via pLSA. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 517–530. Springer, Heidelberg (2006) CrossRefGoogle Scholar
  7. 7.
    Lowd, D., Meek, C.: Adversarial learning. In: Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, pp. 641–647. ACM (2005)Google Scholar
  8. 8.
    Dasgupta, S.: Analysis of a greedy active learning strategy. In: Advances in Neural Information Processing Systems (2004)Google Scholar
  9. 9.
    Balcan, M., Beygelzimer, A., Langford, J.: Agnostic active learning. In: Proceedings of the International Conference Machine Learning (ICML) (2006)Google Scholar
  10. 10.
    Balcan, M.-F., Broder, A., Zhang, T.: Margin based active learning. In: Bshouty, N.H., Gentile, C. (eds.) COLT. LNCS (LNAI), vol. 4539, pp. 35–50. Springer, Heidelberg (2007) CrossRefGoogle Scholar
  11. 11.
    Vondrick, C., Khosla, A., Malisiewicz, T., Torralba, A.: Hoggles: Visualizing object detection features. In: Proceedings of the International Conference on Computer Vision (2013)Google Scholar
  12. 12.
    Heath, M.: Scientific Computing. The McGraw-Hill Companies Inc., New York (2002) Google Scholar
  13. 13.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 886–893. IEEE (2005)Google Scholar
  14. 14.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: The Proceedings of the Seventh IEEE International Conference on Computer vision, vol. 2, pp. 1150–1157. IEEE (1999)Google Scholar
  15. 15.
    Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28, 594–611 (2006)CrossRefGoogle Scholar
  16. 16.
    Bradski, G.: The OpenCV library. Dr. Dobb’s J. Softw. Tools 25, 120–126 (2000)Google Scholar
  17. 17.
    Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 104. ACM (2004)Google Scholar
  18. 18.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Discriminative learned dictionaries for local image analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8. IEEE (2008)Google Scholar
  19. 19.
    Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, ECCV, vol. 1, pp. 1–2 (2004)Google Scholar
  20. 20.
    Bengio, Y.: Learning deep architectures for ai. Found. Trends\(\textregistered \) Mach. Learn. 2, 1–127 (2009)Google Scholar
  21. 21.
    Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)CrossRefMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Information Technology UniversityLahorePakistan
  2. 2.University of FloridaGainesvilleUSA

Personalised recommendations