Channel-level acceleration of deep face representations

Adam Polyak, Lior Wolf*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

122 Scopus citations

Abstract

A major challenge in biometrics is performing the test at the client side, where hardware resources are often limited. Deep learning approaches pose a unique challenge: while such architectures dominate the field of face recognition with regard to accuracy, they require elaborate, multi-stage computations. Recently, there has been some work on compressing networks for the purpose of reducing run time and network size. However, it is not clear that these compression methods would work in deep face nets, which are, generally speaking, less redundant than the object recognition networks, i.e., they are already relatively lean. We propose two novel methods for compression: one based on eliminating lowly active channels and the other on coupling pruning with repeated use of already computed elements. Pruning of entire channels is an appealing idea, since it leads to direct saving in run time in almost every reasonable architecture.

Original languageEnglish
Article number7303876
Pages (from-to)2163-2175
Number of pages13
JournalIEEE Access
Volume3
DOIs
StatePublished - 26 Oct 2015

Keywords

  • Face recognition
  • Neural network compression

Fingerprint

Dive into the research topics of 'Channel-level acceleration of deep face representations'. Together they form a unique fingerprint.

Cite this