Evaluation of image classification for transfer learning in convolutional neural networks

Authors

  • M. S. Mamuta National Technical University of Ukraine "Ihor Sikorskyi Kyiv Polytechnic Institute"
  • I. V. Kravchenko National Technical University of Ukraine "Ihor Sikorskyi Kyiv Polytechnic Institute"
  • O. D. Mamuta Institute of Physics of the National Academy of Sciences of Ukraine
  • S. E. Tuzhansky Vinnytsia National Technical University

DOI:

https://doi.org/10.31649/1681-7893-2023-45-1-64-70

Keywords:

neural network, computer vision, deep learning, transfer learning

Abstract

 

Abstract. The article provides an overview of the main neural networks used for image classification tasks. Their main advantages and disadvantages are discussed. The peculiarities of transfer learning for classification are analyzed. The effectiveness of transfer learning when using the basic networks of the Keras library is examined

Author Biographies

M. S. Mamuta, National Technical University of Ukraine "Ihor Sikorskyi Kyiv Polytechnic Institute"

к.т.н., старший викладач кафедри комп’ютерно-інтегрованих оптичних та навігаційних систем

I. V. Kravchenko, National Technical University of Ukraine "Ihor Sikorskyi Kyiv Polytechnic Institute"

старший викладач кафедри комп’ютерно-інтегрованих оптичних та навігаційних систем

O. D. Mamuta, Institute of Physics of the National Academy of Sciences of Ukraine

к.т.н., науковий співробітник відділу когерентної та квантової оптики

S. E. Tuzhansky, Vinnytsia National Technical University

к.т.н., доцент кафедри біомедичної інженерії та оптико-електронних систем

References

Yu. Tomka, M. Talakh, V. Dvorzhak, O. Ushenko, "Implementation of a Convolutional Neural Network Using TensorFlow Machine Learning Platform", Optoelectronic Information-Power Technologies, vol. 44, №2, pp. 55-65, 2023. DOI: https://doi.org/10.31649/1681-7893-2022-44-2-55-65

A. Krizhecsky, I. Sutskever, and G. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks", [Electronic resource]. Available:

https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf

K. He, X. Zhang, S. Ren, J. Sun, "Deep Residual Learning for Image Recognition", [Electronic resource]. Available: https://arxiv.org/pdf/1512.03385.pdf.

Qiang Yang, Yu Zhang, Wenyuan Dai, Sinno Jialin Pan. "Transfer Learning", Cambridge University Press, 2020, p. 380. DOI: https://doi.org/10.1017/9781139061773

Nafiz Shahriar, "What is Convolutional Neural Network – CNN (Deep Learning)", [Electronic resource]. Available: https://nafizshahriar.medium.com/what-is-convolutional-neural-network-cnn-deep-learning-b3921bdd82d5

Ian Goodfellow, Yoshua Bengio, Aaron Courville. "Deep learning", MIT Press, 2017, p. 800

А. Момот, М. Мамута. "Інтелектуальні та інформаційні системи. Практикум", КПІ ім. Ігоря Сікорського, 2022, 221 с.

[Electronic resource]. Available: https://ela.kpi.ua/bitstream/123456789/47696/1/IIS.pdf

K. Simonyan, A. Zisserman, "Very deep convolutional networks for large-scale image recognition", [Electronic resource]. Available : https://arxiv.org/pdf/1409.1556.pdf

C. Szegedy. "Going Deeper with Convolutions", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, 2015, pp. 1-9. DOI: 10.1109/CVPR.2015.7298594

K. He, X. Zhang, S. Ren, J. Sun. "Deep Residual Learning for Image Recognition", [Electronic resource]. Available: https://arxiv.org/pdf/ 1512.03385.pdf.

Downloads

Abstract views: 91

Published

2023-09-28

How to Cite

[1]
M. S. Mamuta, I. V. Kravchenko, O. D. Mamuta, and S. E. Tuzhansky, “Evaluation of image classification for transfer learning in convolutional neural networks”, Опт-ел. інф-енерг. техн., vol. 45, no. 1, pp. 64–70, Sep. 2023.

Issue

Section

Systems Of Technical Vision And Artificial Intelligence, Image Processing And Pattern Recognition

Metrics

Downloads

Download data is not yet available.

Most read articles by the same author(s)