Help for this page

Journal of Basic and Applied Sciences Volume 1 (2026) · Issue 1

Original Research

A Study of the Performance and Efficiency of Transfer Learning for Image Classification.

Rotimi-Williams Bello*, Roseline Oluwaseun Ogundokun, Celestine Uche Agwi

  1. * Corresponding author

Read PDFDownload PDF (518 KB)

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

Bello, R., Ogundokun, R. O., & Agwi, C. U. (2026). A Study of the Performance and Efficiency of Transfer Learning for Image Classification. Journal of Basic and Applied Sciences, 1(1), Article JBAS-2026-0702-044AF5. https://journals.uat.edu.ng/pub/0000000043
Bello, Rotimi-Williams, et al. "A Study of the Performance and Efficiency of Transfer Learning for Image Classification." Journal of Basic and Applied Sciences, vol. 1, no. 1, 2026, article JBAS-2026-0702-044AF5, https://journals.uat.edu.ng/pub/0000000043.
Bello, Rotimi-Williams, Roseline Oluwaseun Ogundokun, and Celestine Uche Agwi. 2026. "A Study of the Performance and Efficiency of Transfer Learning for Image Classification." Journal of Basic and Applied Sciences 1 (1): JBAS-2026-0702-044AF5. https://journals.uat.edu.ng/pub/0000000043.
Bello, R., Ogundokun, R. O. and Agwi, C. U. (2026) 'A Study of the Performance and Efficiency of Transfer Learning for Image Classification', Journal of Basic and Applied Sciences, 1(1), Article JBAS-2026-0702-044AF5. Available at: https://journals.uat.edu.ng/pub/0000000043 (Accessed: 20 November 2026).
R. Bello, R. O. Ogundokun, and C. U. Agwi, "A Study of the Performance and Efficiency of Transfer Learning for Image Classification," Journal of Basic and Applied Sciences, vol. 1, no. 1, Art. no. JBAS-2026-0702-044AF5, 2026. [Online]. Available: https://journals.uat.edu.ng/pub/0000000043
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}
}

Download .bib

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  - 

Download .ris