# Interpreting a Semantic Segmentation Model for Coastline Detection

arXiv: https://arxiv.org/abs/2405.11500 · HTML: https://mlsanity.com/paper/2405.11500/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 13 references that are in the map.
- First posted on arXiv 19 May 2024.

## Builds on (most cited first, 2 of 2)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping](https://mlsanity.com/paper/2002.11434/) (2020)

## Built on by (most cited first, 1 of 1)

- [Enhancing coastal water body segmentation with Landsat Irish Coastal Segmentation (LICS) dataset](https://mlsanity.com/paper/2409.15311/) (2024)

## Abstract (arXiv)

We interpret a deep-learning semantic segmentation model used to classify coastline satellite images into land and water. This is to build trust in the model and gain new insight into the process of coastal water body extraction. Specifically, we seek to understand which spectral bands are important for predicting segmentation masks. This is done using a permutation importance approach. Results show that the NIR is the most important spectral band. Permuting this band lead to a decrease in accuracy of 38.12 percentage points. This is followed by Water Vapour, SWIR 1, and Blue bands with 2.58, 0.78 and 0.19 respectively. Water Vapour is not typically used in water indices and these results suggest it may be useful for water body extraction. Permuting, the Coastal Aerosol, Green, Red, RE1, RE2, RE3, RE4, and SWIR 2 bands did not decrease accuracy. This suggests they could be excluded from future model builds reducing complexity and computational requirements.