Determining Top Fully Connected Layer's Hidden Neuron Count for Transfer Learning, Using Knowledge Distillation: a Case Study on Chest X-Ray Classification of Pneumonia and COVID-19.

Deep convolutional neural network (CNN)-assisted classification of images is one of the most discussed topics in recent years. Continuously innovation of neural network architectures is making it more correct and efficient every day. But training a neural network from scratch is very time-consuming...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Digital Imaging Vol. 34; no. 6; pp. 1349 - 1359
Autor principal: Ghosh, Ritwick
Formato: diagnostic images equations & formulas research tables/charts Journal Article
Publicado: Springer Nature Dec2021
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=154097224&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 154097224
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        08971889
        DOQ
      jtl: Journal of Digital Imaging
      issn: 08971889
      maglogo: N
    pubinfo:
      dt: Dec2021
      vid: 34
      iid: 6
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        154097224
        152702867
        154097224
        154097224
        10.1007/s10278-021-00518-2
        154097224
      ppf: 1349
      ppct: 10
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Determining Top Fully Connected Layer's Hidden Neuron Count for Transfer Learning, Using Knowledge Distillation: a Case Study on Chest X-Ray Classification of Pneumonia and COVID-19.
      aug:
        au: Ghosh, Ritwick
        affil: Department of Mining Engineering, Indian Institute of Engineering Science and Technology, P.O, Shibpur, 711103, Botanical Garden, Howrah, West Bengal, India
      sug:
        subj:
          Digital Imaging Classification
          Neural Networks (Computer) Methods
          Transfer (Psychology)
          Learning Methods
          Machine Learning Utilization
          Radiography, Thoracic Classification
          Pneumonia Radiography
          COVID-19 Radiography
          Neurons
          Human
          Knowledge
          Models, Educational
          Diagnostic Imaging
          Time Factors
      ab: Deep convolutional neural network (CNN)-assisted classification of images is one of the most discussed topics in recent years. Continuously innovation of neural network architectures is making it more correct and efficient every day. But training a neural network from scratch is very time-consuming and requires a lot of sophisticated computational equipment and power. So, using some pre-trained neural network as feature extractor for any image classification task or "transfer learning" is a very popular approach that saves time and computational power for practical use of CNNs. In this paper, an efficient way of building full model from any pre-trained model with high accuracy and low memory is proposed using knowledge distillation. Using the distilled knowledge of the last layer of pre-trained networks passes through fully connected layers with different hidden layers, followed by Softmax layer. The accuracies of student networks are mildly lesser than the whole models, but accuracy of student models clearly indicates the accuracy of the real network. In this way, the best number of hidden layers for dense layer for that pre-trained network with best accuracy and no-overfitting can be found with less time. Here, VGG16 and VGG19 (pre-trained upon "ImageNet" dataset) is tested upon chest X-rays (pneumonia and COVID-19). For finding the best total number of hidden layers, it saves nearly 44 min for VGG19 and 36 min and 37 s for VGG16 feature extractor.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        equations & formulas
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N