Can Computer Vision Problems Benefit from Structured Hierarchical Classification?

  • Thomas Hoyoux
  • Antonio J. Rodríguez-Sánchez
  • Justus H. Piater
  • Sandor Szedmak
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9257)


While most current research in the classification domain still focuses on standard “flat” classification, there is an increasing interest in a particular type of structured classification called hierarchical classification. Incorporating knowledge about class hierarchy should be beneficial to computer vision systems as suggested by the fact that humans seem to organize objects into hierarchical structures based on visual geometrical similarities. In this paper, we analyze whether hierarchical classification provides better performance than flat classification by comparing three structured classification methods – Structured K-Nearest Neighbors, Structured Support Vector Machines and Maximum Margin Regression – with their flat counterparts on two very different computer vision tasks: facial expression recognition, for which we emphasize the underlying hierarchical structure, and 3D shape classification. The obtained results show no or only marginal improvement, which questions the way the data should be exploited for hierarchical classification in computer vision.


Hierarchical classification Flat classification Structured K-Nearest Neighbors  Structured Support Vector Machines Maximum Margin Regression 3D shape classification  expression recognition 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Astikainen, K., Holm, L., Pitkänen, E., Szedmak, S., Rousu, J.: Towards structured output prediction of enzyme function. BioMed. Central (2008)Google Scholar
  2. 2.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE PAMI 24(24), 509–522 (2002)CrossRefGoogle Scholar
  3. 3.
    Crammer, K., Singer, Y.: On the algorithmic implementation of multiclass kernel-based vector machines. JMLR 2, 265–292 (2001)Google Scholar
  4. 4.
    Ekman, P., Rosenberg, E.L.: What the face reveals: Basic and applied studies of spontaneous expression using the Facial Action Coding System (FACS). Oxford University Press (1997)Google Scholar
  5. 5.
    Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE PAMI 28(4), 594–611 (2006)CrossRefGoogle Scholar
  6. 6.
    Kiritchenko, S., Matwin, S., Famili, A.F.: Functional annotation of genes using hierarchical text categorization. In: BioLINK SIG: LLIKB (2005)Google Scholar
  7. 7.
    Lampert, C., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot learning of object categories. IEEE PAMI (2013)Google Scholar
  8. 8.
    Lucey, P., Cohn, J.F., Kanade, T., Saragih, J., Ambadar, Z., Matthews, I.: The extended cohn-kanade dataset (ck+): A complete dataset for action unit and emotion-specified expression. In: CVPRW, pp. 94–101 (2010)Google Scholar
  9. 9.
    Rodríguez-Sánchez, A., Tsotsos, J.: The roles of endstopped and curvature tuned computations in a hierarchical representation of 2D shape. PLOS ONE 7(8), 1–13 (2012)CrossRefGoogle Scholar
  10. 10.
    Rusu, R.B., Cousins, S.: 3D is here: Point cloud library (PCL). In: IEEE ICRA, pp. 1–4 (2011)Google Scholar
  11. 11.
    Rusu, R., Bradski, G., Thibaux, R., Hsu, J.: Fast 3D recognition and pose using the viewpoint feature histogram. In: IROS, pp. 2155–2162 (2010)Google Scholar
  12. 12.
    Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M.: Robust object recognition with cortex-like mechanisms. IEEE PAMI 29(3), 411–426 (2007)CrossRefGoogle Scholar
  13. 13.
    Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The princeton shape benchmark. In: Shape Modeling Applications, pp. 167–178 (2004)Google Scholar
  14. 14.
    Silla Jr., C.N., Freitas, A.A.: A survey of hierarchical classification across different application domains. DMKD 22(1–2), 31–72 (2011)zbMATHMathSciNetGoogle Scholar
  15. 15.
    Tombari, F., Salti, S., Di Stefano, L.: Unique shape context for 3D data description. In: Workshop on 3D Object Retrieval, pp. 57–62. ACM (2010)Google Scholar
  16. 16.
    Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: ICML, p. 104. ACM (2004)Google Scholar
  17. 17.
    Wang, X., Liu, Y., Zha, H.: Intrinsic spin images: A subspace decomposition approach to understanding 3D deformable shapes. In: 3DPVT, vol. 10, pp. 17–20 (2010)Google Scholar
  18. 18.
    Weidenbacher, U., Neumann, H.: Extraction of surface-related features in a recurrent model of V1–V2 interactions. PLOS ONE 4(6), e5909 (2009)Google Scholar
  19. 19.
    Wohlkinger, W., Vincze, M.: Ensemble of shape functions for 3D object classification. In: IEEE ROBIO, pp. 2987–2992 (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Thomas Hoyoux
    • 1
  • Antonio J. Rodríguez-Sánchez
    • 2
  • Justus H. Piater
    • 2
  • Sandor Szedmak
    • 2
  1. 1.INTELSIG, Montefiore InstituteUniversity of LiègeLiègeBelgium
  2. 2.Intelligent and Interactive Systems, Institute of Computer ScienceUniversity of InnsbruckInnsbruckAustria

Personalised recommendations