Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ...
Deploying deep learning on Synthetic Aperture Radar (SAR) data is becoming more common for mapping purposes. One such case is sea ice, which is highly dynamic and rapidly changes as a result of the combined effect of wind, temperature, and ocean currents. Therefore, frequent mapping of sea ice is ne...
| Main Authors: | , |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | unknown |
| Published: |
arXiv
2023
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.48550/arxiv.2310.17126 https://arxiv.org/abs/2310.17126 |
| id |
ftdatacite:10.48550/arxiv.2310.17126 |
|---|---|
| record_format |
openpolar |
| spelling |
ftdatacite:10.48550/arxiv.2310.17126 2023-12-03T10:30:08+01:00 Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ... Karimzadeh, Morteza de Lima, Rafael Pires 2023 https://dx.doi.org/10.48550/arxiv.2310.17126 https://arxiv.org/abs/2310.17126 unknown arXiv https://dx.doi.org/10.1109/igarss52108.2023.10281892 Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering ScholarlyArticle Text article-journal Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2310.1712610.1109/igarss52108.2023.10281892 2023-11-03T11:11:09Z Deploying deep learning on Synthetic Aperture Radar (SAR) data is becoming more common for mapping purposes. One such case is sea ice, which is highly dynamic and rapidly changes as a result of the combined effect of wind, temperature, and ocean currents. Therefore, frequent mapping of sea ice is necessary to ensure safe marine navigation. However, there is a general shortage of expert-labeled data to train deep learning algorithms. Fine-tuning a pre-trained model on SAR imagery is a potential solution. In this paper, we compare the performance of deep learning models trained from scratch using randomly initialized weights against pre-trained models that we fine-tune for this purpose. Our results show that pre-trained models lead to better results, especially on test samples from the melt season. ... Article in Journal/Newspaper Sea ice DataCite Metadata Store (German National Library of Science and Technology) |
| institution |
Open Polar |
| collection |
DataCite Metadata Store (German National Library of Science and Technology) |
| op_collection_id |
ftdatacite |
| language |
unknown |
| topic |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering |
| spellingShingle |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering Karimzadeh, Morteza de Lima, Rafael Pires Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ... |
| topic_facet |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering |
| description |
Deploying deep learning on Synthetic Aperture Radar (SAR) data is becoming more common for mapping purposes. One such case is sea ice, which is highly dynamic and rapidly changes as a result of the combined effect of wind, temperature, and ocean currents. Therefore, frequent mapping of sea ice is necessary to ensure safe marine navigation. However, there is a general shortage of expert-labeled data to train deep learning algorithms. Fine-tuning a pre-trained model on SAR imagery is a potential solution. In this paper, we compare the performance of deep learning models trained from scratch using randomly initialized weights against pre-trained models that we fine-tune for this purpose. Our results show that pre-trained models lead to better results, especially on test samples from the melt season. ... |
| format |
Article in Journal/Newspaper |
| author |
Karimzadeh, Morteza de Lima, Rafael Pires |
| author_facet |
Karimzadeh, Morteza de Lima, Rafael Pires |
| author_sort |
Karimzadeh, Morteza |
| title |
Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ... |
| title_short |
Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ... |
| title_full |
Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ... |
| title_fullStr |
Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ... |
| title_full_unstemmed |
Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ... |
| title_sort |
deep learning on sar imagery: transfer learning versus randomly initialized weights ... |
| publisher |
arXiv |
| publishDate |
2023 |
| url |
https://dx.doi.org/10.48550/arxiv.2310.17126 https://arxiv.org/abs/2310.17126 |
| genre |
Sea ice |
| genre_facet |
Sea ice |
| op_relation |
https://dx.doi.org/10.1109/igarss52108.2023.10281892 |
| op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
| op_doi |
https://doi.org/10.48550/arxiv.2310.1712610.1109/igarss52108.2023.10281892 |
| _version_ |
1784255809497071616 |