Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification

Dong Chen, Xudong Cao, Fang Wen, Jian Sun

CVPR 2013

doi:10.1109/CVPR.2013.389 /cvpr/2013/chen2013cvpr-blessing/

Abstract

Making a high-dimensional (e.g., 100K-dim) feature for face recognition seems not a good idea because it will bring difficulties on consequent training, computation, and storage. This prevents further exploration of the use of a highdimensional feature. In this paper, we study the performance of a highdimensional feature. We first empirically show that high dimensionality is critical to high performance. A 100K-dim feature, based on a single-type Local Binary Pattern (LBP) descriptor, can achieve significant improvements over both its low-dimensional version and the state-of-the-art. We also make the high-dimensional feature practical. With our proposed sparse projection method, named rotated sparse regression, both computation and model storage can be reduced by over 100 times without sacrificing accuracy quality.

PDF CVPR Semantic Scholar

Cite

Text

Chen et al. "Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.389

Markdown

[Chen et al. "Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/chen2013cvpr-blessing/) doi:10.1109/CVPR.2013.389

BibTeX

@inproceedings{chen2013cvpr-blessing,
  title     = {{Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification}},
  author    = {Chen, Dong and Cao, Xudong and Wen, Fang and Sun, Jian},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.389},
  url       = {https://mlanthology.org/cvpr/2013/chen2013cvpr-blessing/}
}