A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
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, mem...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/4/1/2 |
| _version_ | 1797445825983414272 |
|---|---|
| author | Nermeen Abou Baker Nico Zengeler Uwe Handmann |
| author_facet | Nermeen Abou Baker Nico Zengeler Uwe Handmann |
| author_sort | Nermeen Abou Baker |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T13:32:23Z |
| format | Article |
| id | doaj.art-ac7b08eb38104990b2f7ccb32fab2e06 |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-03-09T13:32:23Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-ac7b08eb38104990b2f7ccb32fab2e062023-11-30T21:16:48ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902022-01-0141224110.3390/make4010002A Transfer Learning Evaluation of Deep Neural Networks for Image ClassificationNermeen Abou Baker0Nico Zengeler1Uwe Handmann2Computer Science Institute, Ruhr West University of Applied Sciences, 46236 Bottrop, GermanyComputer Science Institute, Ruhr West University of Applied Sciences, 46236 Bottrop, GermanyComputer Science Institute, Ruhr West University of Applied Sciences, 46236 Bottrop, GermanyTransfer 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.https://www.mdpi.com/2504-4990/4/1/2transfer learningimage classificationdeep neural network |
| spellingShingle | Nermeen Abou Baker Nico Zengeler Uwe Handmann A Transfer Learning Evaluation of Deep Neural Networks for Image Classification Machine Learning and Knowledge Extraction transfer learning image classification deep neural network |
| title | A Transfer Learning Evaluation of Deep Neural Networks for Image Classification |
| title_full | A Transfer Learning Evaluation of Deep Neural Networks for Image Classification |
| title_fullStr | A Transfer Learning Evaluation of Deep Neural Networks for Image Classification |
| title_full_unstemmed | A Transfer Learning Evaluation of Deep Neural Networks for Image Classification |
| title_short | A Transfer Learning Evaluation of Deep Neural Networks for Image Classification |
| title_sort | transfer learning evaluation of deep neural networks for image classification |
| topic | transfer learning image classification deep neural network |
| url | https://www.mdpi.com/2504-4990/4/1/2 |
| work_keys_str_mv | AT nermeenaboubaker atransferlearningevaluationofdeepneuralnetworksforimageclassification AT nicozengeler atransferlearningevaluationofdeepneuralnetworksforimageclassification AT uwehandmann atransferlearningevaluationofdeepneuralnetworksforimageclassification AT nermeenaboubaker transferlearningevaluationofdeepneuralnetworksforimageclassification AT nicozengeler transferlearningevaluationofdeepneuralnetworksforimageclassification AT uwehandmann transferlearningevaluationofdeepneuralnetworksforimageclassification |