Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation

1 code implementation • 26 Oct 2023 • Rafael Pires de Lima, Behzad Vahedi, Morteza Karimzadeh

Up-to-date sea ice charts are crucial for safer navigation in ice-infested waters.

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

1 code implementation • 26 Oct 2023 • Morteza Karimzadeh, Rafael Pires de Lima

Deploying deep learning on Synthetic Aperture Radar (SAR) data is becoming more common for mapping purposes.

Transfer Learning

Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions

1 code implementation • 26 Oct 2023 • Rafael Pires de Lima, Behzad Vahedi, Nick Hughes, Andrew P. Barrett, Walter Meier, Morteza Karimzadeh

Multiclass ice type classification is more challenging, and even though our models achieve 2% improvement in weighted F1 average compared to the baseline U-Net, test weighted F1 is generally between 0. 6 and 0. 80.

Binary Classification Image Segmentation +1