Journal of Basic and Applied Sciences Volume 1 (2026) · Issue 1
Original ResearchA Study of the Performance and Efficiency of Transfer Learning for Image Classification.
- * Corresponding author
Abstract
Computer vision (CV) is a field with different tasks, including image classification. Applications of image classification range from agriculture, healthcare, and remote sensing to intelligent systems. Although a remarkable performance has been achieved by deep learning (DL) models, their achievement is usually determined by availability of large-scale annotated datasets and extensive computational resources. These challenges are addressed by the emergence of transfer learning (TL) as an effective solution that leverages knowledge from pre-trained models. A comprehensive study is presented in this paper on TL for classification of images with evaluation of its performance and efficiency across multiple Convolutional Neural Network (CNN) architectures. Feature extraction and fine-tuning were analyzed as two main TL strategies using pre-trained models. Their performance was compared in terms of computational efficiency, convergence speed, and accuracy. As demonstrated by experimental results, TL does not only significantly improve classification performance but also reduces training time and data requirements, demonstrating suitability for resource-constrained and real-world applications.
Keywords
How to cite
BibTeX and RIS
BibTeX
@article{bello2026study,
author = {Bello, Rotimi-Williams and Ogundokun, Roseline Oluwaseun and Agwi, Celestine Uche},
title = {{A Study of the Performance and Efficiency of Transfer Learning for Image Classification.}},
journal = {Journal of Basic and Applied Sciences},
year = {2026},
volume = {1},
number = {1},
note = {Article JBAS-2026-0702-044AF5},
publisher = {University of Africa, Toru-Orua},
url = {https://journals.uat.edu.ng/pub/0000000043},
keywords = {Convolutional Neural Networks, Image Classification, Transfer Learning, Deep Learning, Computer Vision}
}
RIS
TY - JOUR AU - Bello, Rotimi-Williams AU - Ogundokun, Roseline Oluwaseun AU - Agwi, Celestine Uche TI - A Study of the Performance and Efficiency of Transfer Learning for Image Classification. JO - Journal of Basic and Applied Sciences PY - 2026 DA - 2026/07/02 VL - 1 IS - 1 C7 - JBAS-2026-0702-044AF5 PB - University of Africa, Toru-Orua AB - Computer vision (CV) is a field with different tasks, including image classification. Applications of image classification range from agriculture, healthcare, and remote sensing to intelligent systems. Although a remarkable performance has been achieved by deep learning (DL) models, their achievement is usually determined by availability of large-scale annotated datasets and extensive computational resources. These challenges are addressed by the emergence of transfer learning (TL) as an effective solution that leverages knowledge from pre-trained models. A comprehensive study is presented in this paper on TL for classification of images with evaluation of its performance and efficiency across multiple Convolutional Neural Network (CNN) architectures. Feature extraction and fine-tuning were analyzed as two main TL strategies using pre-trained models. Their performance was compared in terms of computational efficiency, convergence speed, and accuracy. As demonstrated by experimental results, TL does not only significantly improve classification performance but also reduces training time and data requirements, demonstrating suitability for resource-constrained and real-world applications. KW - Convolutional Neural Networks KW - Image Classification KW - Transfer Learning KW - Deep Learning KW - Computer Vision UR - https://journals.uat.edu.ng/pub/0000000043 ER -