Code for my first Kaggle competition "Airbus Ship Detection Challenge"
In this competition I explored a host of new ideas:
- Importance Sampling and image weighting.
- Ship Cropping and image scaling.
- Dice, Brier, and Focal losses.
- U-Nets
- Global Convolutional Nets (GCN)
- Spatial and Channel Squeeze & Excitation (scSE) Blocks
Here are some of the results from my best (0.82) submission. The second column is the prediction and the third column is the ground truth.