Transfer learning based performance comparison of the pre-trained deep neural networks
Deep learning has grown tremendously in recent years, having a substantial impact on practically every discipline. Transfer learning allows us to transfer the knowledge of a model that has been formerly trained for a particular task to a new model that is attempting to solve a related but not identi...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Science and Information Organization
2022
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/100857/1/JayapalanSenthilKumar2022_TransferLearningbasedPerformanceComparison.pdf http://eprints.utm.my/id/eprint/100857/ http://dx.doi.org/10.14569/IJACSA.2022.0130193 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.100857 |
---|---|
record_format |
eprints |
spelling |
my.utm.1008572023-05-07T06:16:12Z http://eprints.utm.my/id/eprint/100857/ Transfer learning based performance comparison of the pre-trained deep neural networks Kumar, Jayapalan Senthil Anuar, Syahid Hassan, Noor Hafizah T Technology (General) Deep learning has grown tremendously in recent years, having a substantial impact on practically every discipline. Transfer learning allows us to transfer the knowledge of a model that has been formerly trained for a particular task to a new model that is attempting to solve a related but not identical problem. Specific layers of a pre-trained model must be retrained while the others must remain unmodified to adapt it to a new task effectively. There are typical issues in selecting the layers to be enabled for training and layers to be frozen, setting hyperparameter values, and all these concerns have a substantial effect on training capabilities as well as classification performance. The principal aim of this study is to compare the network performance of the selected pre-trained models based on transfer learning to help the selection of a suitable model for image classification. To accomplish the goal, we examined the performance of five pre-trained networks, such as SqueezeNet, GoogleNet, ShuffleNet, Darknet-53, and Inception-V3 with different Epochs, Learning Rates, and Mini-Batch Sizes to compare and evaluate the network’s performance using confusion matrix. Based on the experimental findings, Inception-V3 has achieved the highest accuracy of 96.98%, as well as other evaluation metrics, including precision, sensitivity, specificity, and f1-score of 92.63%, 92.46%, 98.12%, and 92.49%, respectively. Science and Information Organization 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/100857/1/JayapalanSenthilKumar2022_TransferLearningbasedPerformanceComparison.pdf Kumar, Jayapalan Senthil and Anuar, Syahid and Hassan, Noor Hafizah (2022) Transfer learning based performance comparison of the pre-trained deep neural networks. International Journal of Advanced Computer Science and Applications, 13 (1). pp. 797-805. ISSN 2158-107X http://dx.doi.org/10.14569/IJACSA.2022.0130193 DOI: 10.14569/IJACSA.2022.0130193 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
language |
English |
topic |
T Technology (General) |
spellingShingle |
T Technology (General) Kumar, Jayapalan Senthil Anuar, Syahid Hassan, Noor Hafizah Transfer learning based performance comparison of the pre-trained deep neural networks |
description |
Deep learning has grown tremendously in recent years, having a substantial impact on practically every discipline. Transfer learning allows us to transfer the knowledge of a model that has been formerly trained for a particular task to a new model that is attempting to solve a related but not identical problem. Specific layers of a pre-trained model must be retrained while the others must remain unmodified to adapt it to a new task effectively. There are typical issues in selecting the layers to be enabled for training and layers to be frozen, setting hyperparameter values, and all these concerns have a substantial effect on training capabilities as well as classification performance. The principal aim of this study is to compare the network performance of the selected pre-trained models based on transfer learning to help the selection of a suitable model for image classification. To accomplish the goal, we examined the performance of five pre-trained networks, such as SqueezeNet, GoogleNet, ShuffleNet, Darknet-53, and Inception-V3 with different Epochs, Learning Rates, and Mini-Batch Sizes to compare and evaluate the network’s performance using confusion matrix. Based on the experimental findings, Inception-V3 has achieved the highest accuracy of 96.98%, as well as other evaluation metrics, including precision, sensitivity, specificity, and f1-score of 92.63%, 92.46%, 98.12%, and 92.49%, respectively. |
format |
Article |
author |
Kumar, Jayapalan Senthil Anuar, Syahid Hassan, Noor Hafizah |
author_facet |
Kumar, Jayapalan Senthil Anuar, Syahid Hassan, Noor Hafizah |
author_sort |
Kumar, Jayapalan Senthil |
title |
Transfer learning based performance comparison of the pre-trained deep neural networks |
title_short |
Transfer learning based performance comparison of the pre-trained deep neural networks |
title_full |
Transfer learning based performance comparison of the pre-trained deep neural networks |
title_fullStr |
Transfer learning based performance comparison of the pre-trained deep neural networks |
title_full_unstemmed |
Transfer learning based performance comparison of the pre-trained deep neural networks |
title_sort |
transfer learning based performance comparison of the pre-trained deep neural networks |
publisher |
Science and Information Organization |
publishDate |
2022 |
url |
http://eprints.utm.my/id/eprint/100857/1/JayapalanSenthilKumar2022_TransferLearningbasedPerformanceComparison.pdf http://eprints.utm.my/id/eprint/100857/ http://dx.doi.org/10.14569/IJACSA.2022.0130193 |
_version_ |
1768006576510074880 |
score |
13.19449 |