Title: Quantitative analysis of transfer and incremental learning for image classification

Authors: Mohammed Ehsan Ur Rahman; Imran Shafiq Ahmad

Addresses: School of Computer Science, University of Windsor, Windsor, Canada ' School of Computer Science, University of Windsor, Windsor, Canada

Abstract: Incremental and transfer learning are becoming increasingly popular and important because of its advantageous nature in data scarcity scenarios. This work entails a quantitative analysis of the incremental learning approach along with various transfer learning methods using the task of image classification. A detailed analysis of the assumptions under which incremental learning should be applied is presented. The degree to which these assumptions hold in most real-world scenarios is also presented. For experiments, MNIST and CIFAR-100 were used. The extensive coverage of incremental and transfer learning techniques on these two datasets showed that a performance improvement is achieved when these techniques are used in data-scarce situations.

Keywords: transfer learning; incremental learning; deep learning; image classification; image generation; neural networks; artificial intelligence; machine learning; MNIST; CIFAR-10; digit recognition.

DOI: 10.1504/IJCVR.2024.136996

International Journal of Computational Vision and Robotics, 2024 Vol.14 No.2, pp.202 - 212

Received: 03 Dec 2021
Accepted: 25 Jul 2022
Published online: 01 Mar 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article