Abstract
At present, the rapid development of convolutional neural networks (CNNs or ConvNets) as a tool for image detection and classification encourages us to implement them more widely in CBIR systems. This paper compares the transfer learning architecture for selected pre-trained CNNs: AlexNet, GoogleNet, VGG16 and VGG19 with the simple ConvNet training from scratch. We have analysed three solvers (optimisation methods): the stochastic gradient descent with the momentum (SGDM) optimizer, the RMSProp optimizer and the ADAM optimization method for both models with and without transfer learning. We concentrated on (3 × 3), (7 × 7) and (9 × 9) sizes of convolutional filters, respectively for each of the above mentioned ConvNets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
Jaworska, T.: Spatial representation of object location for image matching in CBIR. In: Zgrzywa, A., Choroś, K., Siemiński, A. (eds.) New Research in Multimedia and Internet Systems, vol. 314, pp. 25–34. Springer, Wrocław (2014)
Rish, I.: An empirical study of the Naïve Bayes classifier. In: Proceedings of the IJCAI 2001 Workshop on Empirical Methods in AI, Brussels (2001)
Ishibuchi, H., Nojima, Y.: Toward quantitative definition of explanation ability of fuzzy rule-based classifiers. In: IEEE International Conference on Fuzzy Systems, Taipei, Taiwan, 27–39 June 2011
Jaworska, T.: Application of fuzzy rule-based classifier to CBIR in comparison with other classifiers. In: 11th International Conference on Fuzzy Systems and Knowledge Discovery, Xiamen, China, 19–21 August 2014
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems – NIPS 2012, Lake Tahoe, Nevada, USA, 3–6 December 2012
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations, San Diego, CA, 7–9 May 2015
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Huang, Z., Pan, Z., Lei, B.: Transfer learning with deep convolutional neural network for SAR target classification with limited labeled data. Remote Sens. 9(9), 907 (2017)
Chen, S., Zhang, C., Dong, M.: Coupled end-to-end transfer learning with generalized fisher information. In: The Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, June 2018
LeCun, Y., Bottou, L., Orr, G.B., Müller, K.R.: Efficient backprop. In: Orr, G.B., Müller, K.R. (eds.) Neural Networks: Tricks of the Trade, pp. 9–50. Springer, Heidelberg (1998)
Lin, M., Chen, Q., Yan, S.: Network in network, March 2014
Hinton, G., Srivastava, N., Swersky, K.: Neural Networks for Machine Learning, The momentum method, Toronto (2012)
Loos, S., Irving, G., Szegedy, C., Kaliszyk, C.: Deep network guided proof search. In: 21st International Conference on Logic for Programming, Artificial Intelligence and Reasoning, Maun, Botswana, 7–12 May 2017
Dauphin, Y., de Vries, H., Chung, J., Bengio, Y.: RMSProp and equilibrated adaptive learning rates for non-convex optimization. Neural Information Processing Systems, 15 February 2015
Kingma, D.P., Ba, J.L.: ADAM: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA, May 2015
Masters, D., Luschi, C.: Revisiting small batch training for deep neural networks, Bristol, UK. arXiv e-prints (2018)
Acknowledgement
We would like to thank the Project Office MTM Style
for the kind permission to use their visualisation of projects ‘Amadeusz’ and ‘Aksamit’, on which we tested our results.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Jaworska, T. (2021). Image Segment Classification Using CNN. In: Atanassov, K., et al. Uncertainty and Imprecision in Decision Making and Decision Support: New Challenges, Solutions and Perspectives. IWIFSGN 2018. Advances in Intelligent Systems and Computing, vol 1081. Springer, Cham. https://doi.org/10.1007/978-3-030-47024-1_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-47024-1_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-47023-4
Online ISBN: 978-3-030-47024-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)