A Method of Choosing a Pre-trained Convolutional Neural Network for Transfer Learning in Image Classification Problems

被引：0
|
作者：
Trofimov, Alexander G. [1 ]
Bogatyreva, Anastasia A. [1 ]
机构：
[1] Natl Res Nucl Univ MEPhI, Moscow Engn Phys Inst, Kashirskoye Hwy 31, Moscow 115409, Russia
来源：
ADVANCES IN NEURAL COMPUTATION, MACHINE LEARNING, AND COGNITIVE RESEARCH III | 2020年 / 856卷
关键词：
Image classification; Convolutional neural network; ImageNet; Transfer learning;
D O I：
10.1007/978-3-030-30425-6_31
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A method of choosing a pre-trained convolutional neural network (CNN) for transfer learning on the new image classification problem is proposed. The method can be used for quick estimation of which of the CNNs trained on the ImageNet dataset images (AlexNet, VGG16, VGG19, GoogLeNet, etc.) will be the most accurate after its fine tuning on the new sample of images. It is shown that there is high correlation (rho approximate to 0.74, p < 0.01) between the characteristics of the features obtained at the output of the pre-trained CNN's convolutional part and its accuracy on the test sample after fine tuning. The proposed method can be used to make recommendations for researchers who want to apply the pre-trained CNN and transfer learning approach to solve their own classification problems and don't have sufficient computational resources and time for multiple fine tunings of available free CNNs with consequent choosing the best one.
引用
收藏
页码：263 / 270
页数：8
相关论文
共 50 条
  • [1] Transfer Learning for Mammogram Classification Using Pre-Trained Convolutional Neural Network
    Yasuda, K.
    Tsuru, H.
    Ohki, M.
    [J]. MEDICAL PHYSICS, 2017, 44 (06) : 3102 - 3102
  • [2] Pre-Trained Convolutional Neural Network for Classification of Tanning Leather Image
    Winiarti, Sri
    Prahara, Adhi
    Murinto
    Ismi, Dewi Pramudi
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2018, 9 (01) : 212 - 217
  • [3] Painting Classification Using a Pre-trained Convolutional Neural Network
    Banerji, Sugata
    Sinha, Atreyee
    [J]. COMPUTER VISION, GRAPHICS, AND IMAGE PROCESSING, ICVGIP 2016, 2017, 10481 : 168 - 179
  • [4] Transfer learning with pre-trained deep convolutional neural networks for serous cell classification
    Baykal, Elif
    Dogan, Hulya
    Ercin, Mustafa Emre
    Ersoz, Safak
    Ekinci, Murat
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (21-22) : 15593 - 15611
  • [5] Transfer learning with pre-trained deep convolutional neural networks for serous cell classification
    Elif Baykal
    Hulya Dogan
    Mustafa Emre Ercin
    Safak Ersoz
    Murat Ekinci
    [J]. Multimedia Tools and Applications, 2020, 79 : 15593 - 15611
  • [6] Classification of Atrial Fibrillation with Pre-Trained Convolutional Neural Network Models
    Qayyum, Abdul
    Meriaudeau, Fabrice
    Chan, Genevieve C. Y.
    [J]. 2018 IEEE-EMBS CONFERENCE ON BIOMEDICAL ENGINEERING AND SCIENCES (IECBES), 2018, : 594 - 599
  • [7] Lithography Hotspot Detection Method Based on Transfer Learning Using Pre-Trained Deep Convolutional Neural Network
    Liao, Lufeng
    Li, Sikun
    Che, Yongqiang
    Shi, Weijie
    Wang, Xiangzhao
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (04):
  • [8] Development of a deep learning network using a pre-trained convolutional neural network
    Rooney, M.
    Mitchell, J.
    McLaren, D. B.
    Nailon, W. H.
    [J]. RADIOTHERAPY AND ONCOLOGY, 2019, 133 : S1051 - S1052
  • [9] The Impact of Padding on Image Classification by Using Pre-trained Convolutional Neural Networks
    Tang, Hongxiang
    Ortis, Alessandro
    Battiato, Sebastiano
    [J]. IMAGE ANALYSIS AND PROCESSING - ICIAP 2019, PT II, 2019, 11752 : 337 - 344
  • [10] Red Green Blue Depth Image Classification Using Pre-Trained Deep Convolutional Neural Network
    Kumar, N.
    Kaur, N.
    Gupta, D.
    [J]. PATTERN RECOGNITION AND IMAGE ANALYSIS, 2020, 30 (03) : 382 - 390
12345