search for


Tutorial and applications of convolutional neural network models in image classification
Journal of the Korean Data & Information Science Society 2022;33:533-49
Published online May 31, 2022;
© 2022 Korean Data and Information Science Society.

Dong Gyu Lee1 · Yoonsuh Jung2

1,2Department of Statistics, Korea University
Correspondence to: Jung's work has been partially supported by National Research Foundation of Korea (NRF) grants funded by the Korean government (MIST) 2019R1F1A1040515 and 2021R1F1A1062347. This paper is based on Dong Gyu Lee's Master thesis.
1 Graduate Student, Department of Statistics, Korea University, Seoul 02841, Korea
2 Associate professor, Department of Statistics, Korea University, Seoul 02841, Korea. E-mail:
Received February 19, 2022; Revised March 28, 2022; Accepted March 29, 2022.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Image classification is a supervised learning problem in the machine learning area. We apply deep learning models to classify image data. In particular, we discuss the advantages of the various types of convolutional neural networks competed in the ImageNet large-scale visual recognition challenge (ILSVRC). First, we provide a review of the CNN models to be applied and explain the details of models to be employed. In general, we keep the core structure of the models in the same form proposed in ILSVRC. We investigate the models via four popular image data sets of various sizes. To compare the performance of the models, we adopt top-1 accuracy, top-5 accuracy, and f1-score as the measures of accuracy. We employ AdamW for an optimizer that is a fast algorithm and often yields precise learning. As a result, we show that the Inception-ResNet-v2 model has excellent performance, and the ResNet is robust to imbalanced data.
Keywords : AdamW, convolution neural network, deep learning, ILSVRC.