Skip to main navigation Skip to search Skip to main content

Deep Network Shrinkage Applied to Cross-Spectrum Face Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In recent years, deep learning has emerged as a dominant methodology in virtually all machine learning problems. While it has been shown to produce state-of-the-art results for a variety of applicatons (including face recognition and heterogeneous face recognition), one aspect of deep networks that has not been extensively researched is how to determine the optimal network structure. This problem is generally solved by ad hoc methods. In this work we address a subproblem of this task: determining the breadth (number of nodes) of each layer. We show how to use group-sparsity-inducing regularization to effectively replace these hyper-parameters with a single hyperparameter which can be determined by cross-validation. We demonstrate our method by using it to reduce the size of networks on two commonly used NIR face datasets.

Original languageEnglish (US)
Title of host publicationProceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages897-903
Number of pages7
ISBN (Electronic)9781509040230
DOIs
StatePublished - Jun 28 2017
Externally publishedYes
Event12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - Washington, United States
Duration: May 30 2017Jun 3 2017

Publication series

NameProceedings - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - 1st International Workshop on Adaptive Shot Learning for Gesture Understanding and Production, ASL4GUP 2017, Biometrics in the Wild, Bwild 2017, Heterogeneous Face Recognition, HFR 2017, Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation, DCER and HPE 2017 and 3rd Facial Expression Recognition and Analysis Challenge, FERA 2017

Conference

Conference12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017
Country/TerritoryUnited States
CityWashington
Period5/30/176/3/17

ASJC Scopus subject areas

  • Media Technology
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Deep Network Shrinkage Applied to Cross-Spectrum Face Recognition'. Together they form a unique fingerprint.

Cite this