Logo PTI
Polish Information Processing Society
Logo FedCSIS

Annals of Computer Science and Information Systems, Volume 12

Position Papers of the 2017 Federated Conference on Computer Science and Information Systems

How effective is Transfer Learning method for image classification


DOI: http://dx.doi.org/10.15439/2017F526

Citation: Position Papers of the 2017 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 12, pages 39 ()

Full text

Abstract. This paper deals with re-training neural network-based image classification model, using so-called Transfer Learning approach. This method allows for creating a new image classifier, reusing pre-trained weights from a publicly available model. Our study gives some insight on accuracy of re-trained models and provides guidelines concerning required number of training examples. Presented results may be useful for computer vision practitioners, who would like to adapt results of state-of-the-art research on neural networks for their own customized image recognition models.


  1. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, “Deep Learning”, Book in preparation for MIT Press, 2016, on-line version available at:http://www.deeplearningbook.org
  2. Michael A.Nielsen, “Neural Networks and Deep Learning”, Determination Press, 2015, on-line version of the book available at: http://neuralnetworksanddeeplearning.com/index.html
  3. LeCun, Y., Jackel, L. D., Boser, B., Denker, J. S., Graf, H. P., Guyon, I., Henderson, D.,Howard, R. E., and Hubbard, W.. Handwritten digit recognition: Applications of neural network chips and automatic learning. IEEE Communications Magazine, 27(11), 1989
  4. A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS 2012, Neural Information Processing Systems, Nevada, 2012
  5. ImageNet database of computer images: http://image-net.org/
  6. Li Fei-Fei et al. ImageNet Large Scale Visual Recognition Challenge, International Journal of Computer Vision, 2015.
  7. Ch.Szegedy et al, “Going deeper with convolutions”, http://arxiv.org/abs/1409.4842
  8. Ch.Szegedy et al, Rethinking the Inception Architecture for Computer Vision, https://arxiv.org/abs/1512.00567
  9. Ch.Szegedy et al, Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, https://arxiv.org/abs/1602.07261
  10. M.Abadi et al, TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Software available from tensorflow.org.
  11. Publicly available pre-trained GoogleNet model: https://github.com/tensorflow/models/tree/master/inception
  12. Yosinski J, Clune J, Bengio Y, and Lipson H. How transferable are features in deep neural networks? In Advances in Neural Information Processing Systems 27 (NIPS ’14), NIPS Foundation, 2014
  13. M. Dąbrowski, J. Gromada, T. Michalik, A practical study of neural network-based image classification model trained with transfer learning method, Position Paper of FedCSIS AIMaViG 2016, Gdańsk, September 2016, http://dx.doi.org/http://dx.doi.org/10.15439/2016F211