| Autor: |
Karimzadeh, Morteza, de Lima, Rafael Pires |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, 2023, pp. 1983-1986 |
| Druh dokumentu: |
Working Paper |
| DOI: |
10.1109/IGARSS52108.2023.10281892 |
| Popis: |
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. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
