Realization of a Hybrid Locally Connected Extreme Learning Machine with DeepID for Face Verification

Shen Yuong Wong, Keem Siah Yap, Qingwei Zhai, Xiaochao Li

Research output: Contribution to journalArticle

Abstract

Most existing state-of-the-art deep learning algorithms discover sophisticated representations in huge datasets using convolutional neural networks (CNNs) that mainly adopt backpropagation (BP) algorithm as the backbone for training the face recognition problems. However, since decades ago, BP has been debated for causing trivial issues such as iterative gradient-descent operation, slow convergence rate, local minima, intensive human intervention, exhaustive computation, time-consuming, and so on. On the other hand, a competitive machine learning algorithm called extreme learning machine (ELM) emerged with extreme fast implementation and simple in theory has overcome the challenges faced by BP. The ELM advocates the convergence of machine learning and biological learning for pervasive learning and intelligence and has been extensively researched in widespread applications. Nonetheless, till date, none of the work of ELM has proved its competency in tackling face verification problem. Hence, in this paper, we are going to probe for the first time the feasibility of ELM-based network in handling the face verification task. We devise and propose a novel and distinguished hybrid local receptive field-based extreme learning machine with DeepID (hereinafter denoted as H-ELM-LRF-DeepID), to discriminate face pairs. The experimental results on the YouTube face database, labeled faces in the wild (LFW), and CelebFaces datasets have shed light upon the feasibility and usefulness of the H-ELM-LRF-DeepID in the face verification task.

Original languageEnglish
Article number8725548
Pages (from-to)70447-70460
Number of pages14
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 01 Jan 2019

Fingerprint

Learning systems
Backpropagation
Learning algorithms
Backpropagation algorithms
Face recognition
Neural networks

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Wong, Shen Yuong ; Yap, Keem Siah ; Zhai, Qingwei ; Li, Xiaochao. / Realization of a Hybrid Locally Connected Extreme Learning Machine with DeepID for Face Verification. In: IEEE Access. 2019 ; Vol. 7. pp. 70447-70460.
@article{8389f2ad08f84db6a8ed5639b34f8bf9,
title = "Realization of a Hybrid Locally Connected Extreme Learning Machine with DeepID for Face Verification",
abstract = "Most existing state-of-the-art deep learning algorithms discover sophisticated representations in huge datasets using convolutional neural networks (CNNs) that mainly adopt backpropagation (BP) algorithm as the backbone for training the face recognition problems. However, since decades ago, BP has been debated for causing trivial issues such as iterative gradient-descent operation, slow convergence rate, local minima, intensive human intervention, exhaustive computation, time-consuming, and so on. On the other hand, a competitive machine learning algorithm called extreme learning machine (ELM) emerged with extreme fast implementation and simple in theory has overcome the challenges faced by BP. The ELM advocates the convergence of machine learning and biological learning for pervasive learning and intelligence and has been extensively researched in widespread applications. Nonetheless, till date, none of the work of ELM has proved its competency in tackling face verification problem. Hence, in this paper, we are going to probe for the first time the feasibility of ELM-based network in handling the face verification task. We devise and propose a novel and distinguished hybrid local receptive field-based extreme learning machine with DeepID (hereinafter denoted as H-ELM-LRF-DeepID), to discriminate face pairs. The experimental results on the YouTube face database, labeled faces in the wild (LFW), and CelebFaces datasets have shed light upon the feasibility and usefulness of the H-ELM-LRF-DeepID in the face verification task.",
author = "Wong, {Shen Yuong} and Yap, {Keem Siah} and Qingwei Zhai and Xiaochao Li",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2919806",
language = "English",
volume = "7",
pages = "70447--70460",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Realization of a Hybrid Locally Connected Extreme Learning Machine with DeepID for Face Verification. / Wong, Shen Yuong; Yap, Keem Siah; Zhai, Qingwei; Li, Xiaochao.

In: IEEE Access, Vol. 7, 8725548, 01.01.2019, p. 70447-70460.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Realization of a Hybrid Locally Connected Extreme Learning Machine with DeepID for Face Verification

AU - Wong, Shen Yuong

AU - Yap, Keem Siah

AU - Zhai, Qingwei

AU - Li, Xiaochao

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Most existing state-of-the-art deep learning algorithms discover sophisticated representations in huge datasets using convolutional neural networks (CNNs) that mainly adopt backpropagation (BP) algorithm as the backbone for training the face recognition problems. However, since decades ago, BP has been debated for causing trivial issues such as iterative gradient-descent operation, slow convergence rate, local minima, intensive human intervention, exhaustive computation, time-consuming, and so on. On the other hand, a competitive machine learning algorithm called extreme learning machine (ELM) emerged with extreme fast implementation and simple in theory has overcome the challenges faced by BP. The ELM advocates the convergence of machine learning and biological learning for pervasive learning and intelligence and has been extensively researched in widespread applications. Nonetheless, till date, none of the work of ELM has proved its competency in tackling face verification problem. Hence, in this paper, we are going to probe for the first time the feasibility of ELM-based network in handling the face verification task. We devise and propose a novel and distinguished hybrid local receptive field-based extreme learning machine with DeepID (hereinafter denoted as H-ELM-LRF-DeepID), to discriminate face pairs. The experimental results on the YouTube face database, labeled faces in the wild (LFW), and CelebFaces datasets have shed light upon the feasibility and usefulness of the H-ELM-LRF-DeepID in the face verification task.

AB - Most existing state-of-the-art deep learning algorithms discover sophisticated representations in huge datasets using convolutional neural networks (CNNs) that mainly adopt backpropagation (BP) algorithm as the backbone for training the face recognition problems. However, since decades ago, BP has been debated for causing trivial issues such as iterative gradient-descent operation, slow convergence rate, local minima, intensive human intervention, exhaustive computation, time-consuming, and so on. On the other hand, a competitive machine learning algorithm called extreme learning machine (ELM) emerged with extreme fast implementation and simple in theory has overcome the challenges faced by BP. The ELM advocates the convergence of machine learning and biological learning for pervasive learning and intelligence and has been extensively researched in widespread applications. Nonetheless, till date, none of the work of ELM has proved its competency in tackling face verification problem. Hence, in this paper, we are going to probe for the first time the feasibility of ELM-based network in handling the face verification task. We devise and propose a novel and distinguished hybrid local receptive field-based extreme learning machine with DeepID (hereinafter denoted as H-ELM-LRF-DeepID), to discriminate face pairs. The experimental results on the YouTube face database, labeled faces in the wild (LFW), and CelebFaces datasets have shed light upon the feasibility and usefulness of the H-ELM-LRF-DeepID in the face verification task.

UR - http://www.scopus.com/inward/record.url?scp=85067406650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067406650&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2919806

DO - 10.1109/ACCESS.2019.2919806

M3 - Article

VL - 7

SP - 70447

EP - 70460

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8725548

ER -