Learning Attribute Relation in Attribute-Based Zero-Shot Classification

  • Mingxia Liu
  • Songcan Chen
  • Daoqiang Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7751)

Abstract

Recently, zero-shot learning has attracted increasing attention in computer vision community. One way of realizing zero-shot learning is by resorting to knowledge about attributes and object categories. Most existing attribute-centric approaches focus on attribute-class relation artificially derived by linguistic knowledge base or mutual information. In this paper, we aim to learn the attribute-attribute relation automatically and explicitly. Specifically, we propose to incorporate the attribute relation learning into attribute classifier design in a unified framework. Furthermore, we develop a new scheme for attribute-based zero-shot object classification, such that the learned attribute relation can be reused to boost the traditional attribute classifiers. Extensive experimental results demonstrate that our proposed method can enhance the performance of attribute prediction and zero-shot learning.

Keywords

attribute relation attribute-based classification zero-shot learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Farhadi, A., et al.: Describing Objects by Their Attributes. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  2. 2.
    Rohrbach, M., et al.: What Helps Where - and Why? Semantic Relatedness for Knowledge transfer. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2010)Google Scholar
  3. 3.
    Lang, H., Ling, H.: Classifying Covert Photographs. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2012)Google Scholar
  4. 4.
    Wang, Y., Mori, G.: A Discriminative Latent Model of Object Classes and Attributes. Perspectives in Neural Computing, 155–168 (2010)Google Scholar
  5. 5.
    Siddiquie, B., et al.: Image Ranking and Retrieval based on Multi-attribute Queries. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2011)Google Scholar
  6. 6.
    Rohrbach, M., et al.: Evaluating Knowledge Transfer and Zero-Shot Learning in a Large-Scale Setting. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2011)Google Scholar
  7. 7.
    Larochelle, H., et al.: Zero-data Learning of New Tasks. In: Proceedings of the 23rd AAAI Conference on Artificial Intelligence (2008)Google Scholar
  8. 8.
    Mitchell, T.M., et al.: Predicting Human Brain Activity Associated with the Meanings of Nouns. Science 320, 1191–1195 (2008)CrossRefGoogle Scholar
  9. 9.
    Palatucci, M., et al.: Zero-Shot Learning with Semantic Output Codes. In: Advances in Neural Information Processing Systems (2009)Google Scholar
  10. 10.
    Lampert, C.H., et al.: Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  11. 11.
    Farhadi, A., et al.: Attribute-centric Recognition for Cross-category Generalization. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2010)Google Scholar
  12. 12.
    Parikh, D., Grauman, K.: Interactively Building a Discriminative Vocabulary of Nameable Attributes. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2011)Google Scholar
  13. 13.
    Kovashka, A., et al.: Actively Selecting Annotations among Objects and Attributes. In: IEEE International Conference on Computer Vision (2011)Google Scholar
  14. 14.
    Argyriou, A., et al.: Convex Multi-task Feature Learning. Machine Learning 73, 243–272 (2008)CrossRefGoogle Scholar
  15. 15.
    Bonilla, E., et al.: Multi-task Gaussian Process Prediction. In: Proceedings of NIPS (2007)Google Scholar
  16. 16.
    Zhang, Y., Yeung, D.-Y.: A Convex Formulation for Learning Task Relationships in Multi-Task Learning. In: Proceedings of UAI, pp. 733–742 (2010)Google Scholar
  17. 17.
    Rukhin, A.L.: Matrix Variate Distributions. Journal of the American Statistical Association 98, 462, 495–496 (2003)Google Scholar
  18. 18.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)MATHGoogle Scholar
  19. 19.
    Van Gestel, T., et al.: Benchmarking Least Squares Support Vector Machine Classifiers. Machine Learning 54, 5–32 (2004)MATHCrossRefGoogle Scholar
  20. 20.
    Keerthi, S.S., Shevade, S.K.: SMO Algorithm for Least-squares SVM Formulation. Neural Computation 15, 487–507 (2003)MATHCrossRefGoogle Scholar
  21. 21.
    Teytaud, O., Jalam, R.: Kernel-based Text Categorization. In: International Joint Conference on Neural Networks, vol. 3, pp. 1891–1896 (2001)Google Scholar
  22. 22.
    Platt, J.C.: Probabilistic Outputs for Support Vector Machines and Comparison to Regularized Likelihood Methods. In: Smola, A.J., Bartlett, P., Schölkopf, B., Schuurmans, D. (eds.) Advances in Large Margin Classifiers, pp. 61–74 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Mingxia Liu
    • 1
    • 2
  • Songcan Chen
    • 1
  • Daoqiang Zhang
    • 1
  1. 1.School of Computer Science and EngineeringNanjing University of Aeronautics & AstronauticsNanjingP.R. China
  2. 2.School of Information Science and TechnologyTaishan UniversityTaianP.R. China

Personalised recommendations