Are Sparse Representations Really Relevant for Image Classification?

Recent years have seen an increasing interest in sparse representations for image classification and object recognition, probably motivated by evidence from the analysis of the primate visual cortex. It is still unclear, however, whether or not sparsity helps classification. In this paper we evaluate its impact on the recognition rate using a shallow modular architecture, adopting both standard filter banks and filter banks learned in an unsupervised way. In our experiments on the CIFAR-10 and on the Caltech-101 datasets, enforcing sparsity constraints actually does not improve recognition performance. This has an important practical impact in image descriptor design, as enforcing these constraints can have a heavy computational cost.


Published in:
Proc. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2011), 1545 - 1552
Presented at:
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2011), Colorado Springs
Year:
2011
Publisher:
Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa
Keywords:
Laboratories:




 Record created 2011-06-29, last modified 2018-03-18

n/a:
rigamonti_cvpr2011 - Download fulltextPDF
suppl_rigamonti_cvpr2011 - Download fulltextPDF
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)