European Conference on Computer Vision

ECCV 2014: Computer Vision – ECCV 2014 pp 600-616

Self-explanatory Sparse Representation for Image Classification

  • Bao-Di Liu
  • Yu-Xiong Wang
  • Bin Shen
  • Yu-Jin Zhang
  • Martial Hebert
Conference paper

DOI: 10.1007/978-3-319-10605-2_39

Volume 8690 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Liu BD., Wang YX., Shen B., Zhang YJ., Hebert M. (2014) Self-explanatory Sparse Representation for Image Classification. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8690. Springer, Cham

Abstract

Traditional sparse representation algorithms usually operate in a single Euclidean space. This paper leverages a self-explanatory reformulation of sparse representation, i.e., linking the learned dictionary atoms with the original feature spaces explicitly, to extend simultaneous dictionary learning and sparse coding into reproducing kernel Hilbert spaces (RKHS). The resulting single-view self-explanatory sparse representation (SSSR) is applicable to an arbitrary kernel space and has the nice property that the derivatives with respect to parameters of the coding are independent of the chosen kernel. With SSSR, multiple-view self-explanatory sparse representation (MSSR) is proposed to capture and combine various salient regions and structures from different kernel spaces. This is equivalent to learning a nonlinear structured dictionary, whose complexity is reduced by learning a set of smaller dictionary blocks via SSSR. SSSR and MSSR are then incorporated into a spatial pyramid matching framework and developed for image classification. Extensive experimental results on four benchmark datasets, including UIUC-Sports, Scene 15, Caltech-101, and Caltech-256, demonstrate the effectiveness of our proposed algorithm.

Keywords

Reproducing Kernel Hilbert Spaces Sparse Representation Multiple View Image Classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Bao-Di Liu
    • 1
  • Yu-Xiong Wang
    • 2
  • Bin Shen
    • 3
  • Yu-Jin Zhang
    • 4
  • Martial Hebert
    • 2
  1. 1.Col. of Information and Control EngineeringChina University of PetroleumQingdaoChina
  2. 2.Robotics InstituteCarnegie Mellon UniversityPittsburghUSA
  3. 3.Dept. of Computer SciencePurdue UniversityWest LafayetteUSA
  4. 4.Dept. of Electronic EngineeringTsinghua UniversityBeijingChina