SNR maximization hashing for learning compact binary codes

Honghai Yu; Pierre Moulin

ICASSP 2015accepted0 citations

SNR maximization hashing for learning compact binary codes

Abstract

In this paper, we propose a novel robust hashing algorithm based on signal-to-noise ratio (SNR) maximization to learn binary codes. We first motivate SNR maximization for robust hashing in a statistical model, under which maximizing SNR minimizes the robust hashing error probability. A globally optimal solution can be obtained by solving a generalized eigenvalue problem. The proposed algorithm is tested on both synthetic and real datasets, showing significant performance gain over existing hashing algorithms.

BibTeX

@inproceedings{icassp2015_snrmaximizationh,
  title = {SNR maximization hashing for learning compact binary codes},
  author = {Honghai Yu and Pierre Moulin},
  booktitle = {ICASSP 2015},
  year = {2015}
}