Learning Structured Low-Rank Representations for Image Classification

Yangmuzi Zhang, Zhuolin Jiang, Larry S. Davis

CVPR 2013

doi:10.1109/CVPR.2013.93 /cvpr/2013/zhang2013cvpr-learning/

Abstract

An approach to learn a structured low-rank representation for image classification is presented. We use a supervised learning method to construct a discriminative and reconstructive dictionary. By introducing an ideal regularization term, we perform low-rank matrix recovery for contaminated training data from all categories simultaneously without losing structural information. A discriminative low-rank representation for images with respect to the constructed dictionary is obtained. With semantic structure information and strong identification capability, this representation is good for classification tasks even using a simple linear multi-classifier. Experimental results demonstrate the effectiveness of our approach.

PDF CVPR Semantic Scholar

Cite

Text

Zhang et al. "Learning Structured Low-Rank Representations for Image Classification." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.93

Markdown

[Zhang et al. "Learning Structured Low-Rank Representations for Image Classification." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/zhang2013cvpr-learning/) doi:10.1109/CVPR.2013.93

BibTeX

@inproceedings{zhang2013cvpr-learning,
  title     = {{Learning Structured Low-Rank Representations for Image Classification}},
  author    = {Zhang, Yangmuzi and Jiang, Zhuolin and Davis, Larry S.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.93},
  url       = {https://mlanthology.org/cvpr/2013/zhang2013cvpr-learning/}
}