A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
arXiv:2605.11989 · doi:10.3390/make4010002
Abstract
Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages in achieving high performance while saving training time, memory, and effort in network design. In this paper, we investigate how to select the best pre-trained model that meets the target domain requirements for image classification tasks. In our study, we refined the output layers and general network parameters to apply the knowledge of eleven image processing models, pre-trained on ImageNet, to five different target domain datasets. We measured the accuracy, accuracy density, training time, and model size to evaluate the pre-trained models both in training sessions in one episode and with ten episodes.
Published by Machine Learning and Knowledge Extraction Journal
References in corpus (8)
- A Survey of the Recent Architectures of Deep Convolutional Neural Networks
- An overview of deep learning in medical imaging focusing on MRI
- Benchmark Analysis of Representative Deep Neural Network Architectures
- Label-Embedding for Image Classification
- Generalizing from a Few Examples: A Survey on Few-Shot Learning
- Transfer learning for time series classification
- Effect of Depth and Width on Local Minima in Deep Learning
- Transfer learning-based method for automated ewaste recycling in smart cities