Advertisement

One-Shot Learning of Object Categories Using Dependent Gaussian Processes

  • Erik Rodner
  • Joachim Denzler
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6376)

Abstract

Knowledge transfer from related object categories is a key concept to allow learning with few training examples. We present how to use dependent Gaussian processes for transferring knowledge from a related category in a non-parametric Bayesian way. Our method is able to select this category automatically using efficient model selection techniques. We show how to optionally incorporate semantic similarities obtained from the hierarchical lexical database WordNet [1] into the selection process. The framework is applied to image categorization tasks using state-of-the-art image-based kernel functions. A large scale evaluation shows the benefits of our approach compared to independent learning and a SVM based approach.

Keywords

Gaussian Process Knowledge Transfer Training Image Semantic Similarity Average Precision 
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.
    Pedersen, T., Patwardhan, S., Michelizzi, J.: Wordnet: Similarity - measuring the relatedness of concepts. In: Fifth Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL 2004), pp. 38–41 (2004)Google Scholar
  2. 2.
    Ahn, W., Brewer, W.F., Mooney, R.J.: Schema acquisition from a single example. J. of Experim. Psychology: Learning, Memory, and Cognition 18, 391–412 (1992)CrossRefGoogle Scholar
  3. 3.
    Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. PAMI 28(4), 594–611 (2006)Google Scholar
  4. 4.
    Tommasi, T., Caputo, B.: The more you know, the less you learn: from knowledge transfer to one-shot learning of object categories. In: BMVC (2009)Google Scholar
  5. 5.
    Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. Adaptive Computation and Machine Learning. The MIT Press, Cambridge (2005)Google Scholar
  6. 6.
    Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Gaussian processes for object categorization. IJCV 88(2), 169–188 (2009)CrossRefGoogle Scholar
  7. 7.
    Lawrence, N.D., Platt, J.C., Jordan, M.I.: Extensions of the informative vector machine. In: Deterministic and Statist. Methods in Machine Learn., pp. 56–87 (2004)Google Scholar
  8. 8.
    Urtasun, R., Quattoni, A., Lawrence, N.D., Darrell, T.: Transfering nonlinear representations using gaussian processes with a shared latent space. In: Proceedings of the Learning Workshop (Snowbird) (2008), MIT-CSAIL-TR-2008-020Google Scholar
  9. 9.
    Chai, K.M.: Generalization errors and learning curves for regression with multi-task gaussian processes. In: NIPS, pp. 279–287 (2009)Google Scholar
  10. 10.
    Bonilla, E., Chai, K.M., Williams, C.: Multi-task gaussian process prediction. In: NIPS, pp. 153–160. MIT Press, Cambridge (2008)Google Scholar
  11. 11.
    Cao, B., Pan, S.J., Zhang, Y., Yeung, D.Y., Yang, Q.: Adaptive transfer learning. In: Proceedings of the 24th AAAI Conference on Artificial Intelligence (2010)Google Scholar
  12. 12.
    Nickisch, H., Rasmussen, C.E.: Approximations for binary gaussian process classification. Journal of Machine Learning Research 9, 2035–2078 (2008)MathSciNetGoogle Scholar
  13. 13.
    Pillonetto, G., Dinuzzo, F., Nicolao, G.D.: Bayesian online multitask learning of gaussian processes. PAMI 2, 193–205 (2010)Google Scholar
  14. 14.
    Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing visual features for multiclass and multiview object detection. PAMI 29(5), 854–869 (2007)Google Scholar
  15. 15.
    van de Sande, K.E.A., Gevers, T., Snoek, C.G.M.: Evaluating color descriptors for object and scene recognition. PAMI (2010) (in press)Google Scholar
  16. 16.
    Kiefer, J.: Sequential minimax search for a maximum. Proceedings of the American Mathematical Society 4(3), 502–506 (1953)zbMATHMathSciNetGoogle Scholar
  17. 17.
    Rohrbach, M., Stark, M., Szarvas, G., Schiele, B., Gurevych, I.: What helps where - and why? semantic relatedness for knowledge transfer. In: CVPR (2010)Google Scholar
  18. 18.
    Marszalek, M., Schmid, C.: Semantic hierarchies for visual object recognition. In: CVPR, pp. 1–7 (2007)Google Scholar
  19. 19.
    Moosmann, F., Triggs, B., Jurie, F.: Fast discriminative visual codebooks using randomized clustering forests. In: NIPS, pp. 985–992 (2006)Google Scholar
  20. 20.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR, pp. 2169–2178 (2006)Google Scholar
  21. 21.
    Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: CIVR: Conference on Image and Video Retrieval, pp. 401–408 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Erik Rodner
    • 1
  • Joachim Denzler
    • 1
  1. 1.Chair for Computer VisionFriedrich Schiller University of Jena 

Personalised recommendations