The Optimization of the Convolutional Neural Network Transfer Learning Model for CIFAR-10 Image Classification

Optimasi Model Transfer Learning Convolutional Neural Network Untuk Klasifikasi Citra CIFAR-10

  • Rastri Prathivi Universitas Semarang
Keywords: CNN, convolutional neural network, CIFAR-10, image classification


The low accuracy when performing the image classification process is a problem that often occurs. The image classification process requires the completeness of the features of the image which form an informative image pattern so that information from the image can be displayed. The purpose of this study is to classify images in the CIFAR-10 image dataset using the CNN method. Initially the CNN method gave an accuracy of 79.4% but had a long computation time of 12 hours with 10,000 iterations. The optimization process for the CNN method is carried out by combining the CNN method, the PCA algorithm and the t-SNE algorithm. The algorithm is used to reduce the length of the image matrix in the initial transfer of learning without reducing the information in the image so that the classification process can be done correctly. The final result obtained from the optimization has an accuracy of 90.5%. With an optimization rate of 11%. The resulting time is more efficient, namely 3 hours for the feature transfer-value process and 6 minutes for the testing process with 10,000 iterations.


Download data is not yet available.


Zhong, Z., Li, J., Ma, L., Jiang, H. and Zhao, H.. 2017, July. Deep residual networks for hyperspectral image classification. In 2017 IEEE international geoscience and remote sensing symposium (IGARSS) (pp. 1824-1827). IEEE.

Ma, J. and Yuan, Y. 2019. Dimension reduction of image deep feature using PCA. Journal of Visual Communication and Image Representation, 63, p.102578.

Gao, L., Gu, D., Zhuang, L., Ren, J., Yang, D. and Zhang, B. 2019. Combining t-Distributed Stochastic Neighbor Embedding With Convolutional Neural Networks for Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters.

Kobak, D. and Berens, P. 2019. The art of using t-SNE for single-cell transcriptomics. Nature communications, 10(1), pp.1-14.

Husnain, M., Missen, M.M.S., Mumtaz, S., Luqman, M.M., Coustaty, M. and Ogier, J.M., 2019. Visualization of High-

Dimensional data by pairwise fusion matrices using t-SNE. Symmetry, 11(1), p.107.

Giuste, F.O. and Vizcarra, J.C. 2020. CIFAR-10 Image Classification Using Feature Ensembles. arXiv preprint arXiv:2002.03846.

Basha, S.S., Dubey, S.R., Pulabaigari, V. and Mukherjee, S. 2020. Impact of fully connected layers on performance of convolutional neural networks for image classification. Neurocomputing, 378, pp.112-119.

Krizhevsky, A., Sutskever, I. and Hinton, G.E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097- 1105)

Hussain, M., Bird, J.J. and Faria, D.R. 2018, September. A study on cnn transfer learning for image classification. In UK Workshop on Computational Intelligence (pp. 191-202). Springer, Cham.

Mohamed, S.S.N. and Srinivasan, K., 2019, September. Comparative Analysis of Deep Neural Networks for Crack Image Classification. In International Conference on Intelligent Data Communication Technologies and Internet of Things (pp. 434-443). Springer, Cham.

How to Cite
Rastri Prathivi. (2020). The Optimization of the Convolutional Neural Network Transfer Learning Model for CIFAR-10 Image Classification. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 4(4), 717 - 722.
Artikel Teknologi Informasi