HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline

TL;DR

HED-UNet is a novel deep learning model that combines coastline segmentation and edge detection to improve Antarctic coastline monitoring, utilizing multi-scale supervision and attention mechanisms for enhanced accuracy.

Contribution

This paper introduces a unified deep learning model that integrates segmentation and edge detection for coastline monitoring, inspired by UNet and HED architectures.

Findings

Outperforms traditional methods on Antarctic Sentinel-1 data

Effective multi-scale training with deep supervision

Hierarchical attention improves prediction accuracy

Abstract

Deep learning-based coastline detection algorithms have begun to outshine traditional statistical methods in recent years. However, they are usually trained only as single-purpose models to either segment land and water or delineate the coastline. In contrast to this, a human annotator will usually keep a mental map of both segmentation and delineation when performing manual coastline detection. To take into account this task duality, we therefore devise a new model to unite these two approaches in a deep learning model. By taking inspiration from the main building blocks of a semantic segmentation framework (UNet) and an edge detection framework (HED), both tasks are combined in a natural way. Training is made efficient by employing deep supervision on side predictions at multiple resolutions. Finally, a hierarchical attention mechanism is introduced to adaptively merge these multiscale predictions into the final model output. The advantages of this approach over other traditional and deep learning-based methods for coastline detection are demonstrated on a dataset of Sentinel-1 imagery covering parts of the Antarctic coast, where coastline detection is notoriously difficult. An implementation of our method is available at \url{https://github.com/khdlr/HED-UNet}.