Home > Published Issues > 2024 > Volume 15, No. 1, 2024 >
JAIT 2024 Vol.15(1): 66-78
doi: 10.12720/jait.15.1.66-78

Exploratory Architectures Analysis of Various Pre-trained Image Classification Models for Deep Learning

S. Deepa 1, J. Loveline Zeema 1, and S. Gokila 2,*
1. Department of Computer Science, Christ University, Bangalore, India
2. Department of Computer Applications, Hindustan Institute of Technology and Science, Chennai, India
Email: sdeepa369@gmail.com (S.D.); j.lovelinezeema@gmail.com (J.L.Z.); sgokilas@gmail.com (S.G.)
*Corresponding author

Manuscript received May 8, 2023; revised July 11, 2023; accepted August 8, 2023; published January 18, 2024.

Abstract—The image classification is one of the significant applications in the area of Deep Learning (DL) with respective to various sectors. Different types of neural network architectures are available to perform the image classification and each of which produces the different accuracy. The dataset and the features used are influence the outcome of the model. The research community is working towards the generalized model at least to the domain specific. On this gesture the contemporary survey of various Deep Learning models is identified using knowledge information management methods to move further to provide optimal architecture and also to generalized Deep Learning model to classify images narrow down to the sector specific. The study systematically presents the different types of architecture, its variants, layers and parameters used for each version of Deep Learning model. Domain specific applications and limitations of the type of architecture are detailed. It helps the researchers to select appropriate Deep Learning architecture for specific sector.
Keywords—image classification, deep learning, neural network

Cite: S. Deepa, J. Loveline Zeema, and S. Gokila, "Exploratory Architectures Analysis of Various Pre-trained Image Classification Models for Deep Learning," Journal of Advances in Information Technology, Vol. 15, No. 1, pp. 66-78, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.