Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights ...

• Main Authors: Karimzadeh, Morteza, de Lima, Rafael Pires
• Format: Article in Journal/Newspaper
• Language: unknown
• Published: arXiv 2023
• Subjects: 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; Sea ice
• Online Access: https://dx.doi.org/10.48550/arxiv.2310.17126; https://arxiv.org/abs/2310.17126

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. ...