High Order Tensor Formulation for Convolutional Sparse Coding

Type
Conference Paper

Authors
Bibi, Adel
Ghanem, Bernard

KAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
Visual Computing Center (VCC)

Online Publication Date
2017-12-25

Print Publication Date
2017-10

Date
2017-12-25

Abstract
Convolutional sparse coding (CSC) has gained attention for its successful role as a reconstruction and a classification tool in the computer vision and machine learning community. Current CSC methods can only reconstruct singlefeature 2D images independently. However, learning multidimensional dictionaries and sparse codes for the reconstruction of multi-dimensional data is very important, as it examines correlations among all the data jointly. This provides more capacity for the learned dictionaries to better reconstruct data. In this paper, we propose a generic and novel formulation for the CSC problem that can handle an arbitrary order tensor of data. Backed with experimental results, our proposed formulation can not only tackle applications that are not possible with standard CSC solvers, including colored video reconstruction (5D- tensors), but it also performs favorably in reconstruction with much fewer parameters as compared to naive extensions of standard CSC to multiple features/channels.

Citation
Bibi A, Ghanem B (2017) High Order Tensor Formulation for Convolutional Sparse Coding. 2017 IEEE International Conference on Computer Vision (ICCV). Available: http://dx.doi.org/10.1109/ICCV.2017.197.

Acknowledgements
This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.

Publisher
Institute of Electrical and Electronics Engineers (IEEE)

Journal
2017 IEEE International Conference on Computer Vision (ICCV)

Conference/Event Name
16th IEEE International Conference on Computer Vision, ICCV 2017

DOI
10.1109/ICCV.2017.197

Additional Links
http://ieeexplore.ieee.org/document/8237459/

Permanent link to this record