DMCA
Blessing of Dimensionality: High-dimensional Feature and Its Efficient Compression for Face Verification
Cached
Download Links
| Citations: | 48 - 2 self |
BibTeX
@MISC{Chen_blessingof,
author = {Dong Chen and Xudong Cao and Fang Wen and Jian Sun},
title = {Blessing of Dimensionality: High-dimensional Feature and Its Efficient Compression for Face Verification},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
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. 1.
Keyphrases
high-dimensional feature face verification efficient compression highdimensional feature single-type local binary pattern face recognition significant improvement sparse projection method consequent training good idea rotated sparse regression high performance model storage high dimensionality accuracy quality low-dimensional version 100k-dim feature
