Advertisement

Performance Analysis of Convolutional Neural Network When Augmented with New Classes in Classification

  • K. Teja SreenivasEmail author
  • K. Venkata Raju
  • M. Bhavya Spandana
  • D. Sri Harshavardhan Reddy
  • V. Bhavani
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1057)

Abstract

Classification of images is one of the important goals of artificial neural networks. Due to increasing efficiency and accuracy of neural networks today, neural networks have been doing more than image classification, and they are used for image captioning, text detection, and recognition. Deep learning models such as convolutional neural network, recurrent neural network, autoencoders, restricted Boltzman machines, modular neural network, and deep belief networks are widely used across the various domain of problems. The convolutional neural network has been proved successful in computer vision tasks such as object recognition and classification. This paper analyzes how the accuracy and performance of the convolutional neural network are affected while increasing number of classification classes, by augmenting with a new dataset. Through the analysis, it is propounded that the augmentation resulted in an increase in the accuracy and performance of convolutional neural network. In our experimental study, MNIST is used as the primary dataset and Fashion-MNIST is used as the augmented dataset. In our analysis, we observed five times faster convergence time for the MNIST dataset.

Keywords

Convolutional neural network MNIST Fashion-MNIST Data augmentation 

References

  1. 1.
    Alom, M.Z., Taha, T.M., Yakopcic, C., Westberg, S., Hasan, M., Esesn, B.C.V., Awwal, A.A.S., Asari, V.K.: The history began from alexnet: a comprehensive survey on deep learning approaches. CoRR. abs/1803.01164 (2018)Google Scholar
  2. 2.
    Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193–202 (1980)CrossRefGoogle Scholar
  3. 3.
    Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: AISTATS (2011)Google Scholar
  4. 4.
    Gong, Y., Wang, L., Guo, R., Lazebnik, S.: Multi-scale orderless pooling of deep convolutional activation features. In: ECCV (2014)Google Scholar
  5. 5.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
  6. 6.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)Google Scholar
  7. 7.
    Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195(1), 215–43 (1968)CrossRefGoogle Scholar
  8. 8.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  9. 9.
    LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: NIPS (1989)Google Scholar
  10. 10.
    Lee, D.H.: Pseudo-Label : The Simple and Efficient Semi-supervised Learning Method for Deep Neural Networks (2013)Google Scholar
  11. 11.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: ICML (2010)Google Scholar
  12. 12.
    Nguyen, A.M., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 427–436 (2015)Google Scholar
  13. 13.
    O’Shea, K., Nash, R.: An introduction to convolutional neural networks. CoRR. abs/1511.08458 (2015)Google Scholar
  14. 14.
    Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. CoRR. abs/1712.04621 (2017)Google Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR. abs/1409.1556 (2014)Google Scholar
  16. 16.
    Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.A.: Striving for simplicity: The all convolutional net. CoRR. abs/1412.6806 (2014)Google Scholar
  17. 17.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  18. 18.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015)Google Scholar
  19. 19.
    Wan, L., Zeiler, M.D., Zhang, S., LeCun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: ICML (2013)Google Scholar
  20. 20.
    Zamir, A.R., Sax, A., Shen, W.B., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. CoRR. abs/1804.08328 (2018)Google Scholar
  21. 21.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: ECCV (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • K. Teja Sreenivas
    • 1
    Email author
  • K. Venkata Raju
    • 1
  • M. Bhavya Spandana
    • 1
  • D. Sri Harshavardhan Reddy
    • 1
  • V. Bhavani
    • 1
  1. 1.Koneru Lakshmaiah Education FoundationGunturIndia

Personalised recommendations