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

arXiv: https://arxiv.org/abs/2103.01849 · HTML: https://mlsanity.com/paper/2103.01849/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 73 references that are in the map.
- First posted on arXiv 2 Mar 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Gated-SCNN: Gated Shape CNNs for Semantic Segmentation](https://mlsanity.com/paper/1907.05740/) (2019)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Deep learning in remote sensing: a review](https://mlsanity.com/paper/1710.03959/) (2017)
- [Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models](https://mlsanity.com/paper/1807.05713/) (2018)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks](https://mlsanity.com/paper/1711.08681/) (2017)
- [Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform](https://mlsanity.com/paper/1511.03328/) (2015)
- [Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images](https://mlsanity.com/paper/1812.00645/) (2018)
- [Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection](https://mlsanity.com/paper/1612.01337/) (2016)
- [Vehicle Instance Segmentation from Aerial Image and Video Using a Multi-Task Learning Residual Fully Convolutional Network](https://mlsanity.com/paper/1805.10485/) (2018)
- [DeepUNet: A Deep Fully Convolutional Network for Pixel-level Sea-Land Segmentation](https://mlsanity.com/paper/1709.00201/) (2017)
- [Building Footprint Generation by IntegratingConvolution Neural Network with Feature PairwiseConditional Random Field (FPCRF)](https://mlsanity.com/paper/2002.04600/) (2020)
- [A novel Deep Structure U-Net for Sea-Land Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2003.07784/) (2020)
- [Potential of nonlocally filtered pursuit monostatic TanDEM-X data for coastline detection](https://mlsanity.com/paper/1901.01548/) (2019)

## Built on by (most cited first, 13 of 13)

- [A Comprehensive Review on Deep Supervision: Theories and Applications](https://mlsanity.com/paper/2207.02376/) (2022)
- [AMD-HookNet for Glacier Front Segmentation](https://mlsanity.com/paper/2302.02744/) (2023)
- [Globally Scalable Glacier Mapping by Deep Learning Matches Expert Delineation Accuracy](https://mlsanity.com/paper/2401.15113/) (2024)
- [A Deep Active Contour Model for Delineating Glacier Calving Fronts](https://mlsanity.com/paper/2307.03461/) (2023)
- [Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning](https://mlsanity.com/paper/2501.05281/) (2025)
- [Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions](https://mlsanity.com/paper/2306.05912/) (2023)
- [Multi-Sensor Deep Learning for Glacier Mapping](https://mlsanity.com/paper/2409.12034/) (2024)
- [SSL4SAR: Self-Supervised Learning for Glacier Calving Front Extraction from SAR Imagery](https://mlsanity.com/paper/2507.01747/) (2025)
- [Multi-temporal Calving Front Segmentation](https://mlsanity.com/paper/2512.11560/) (2025)
- [Dam reservoir extraction from remote sensing imagery using tailored metric learning strategies](https://mlsanity.com/paper/2207.05807/) (2022)
- [AMD-HookNet++: Evolution of AMD-HookNet with Hybrid CNN-Transformer Feature Enhancement for Glacier Calving Front Segmentation](https://mlsanity.com/paper/2512.14639/) (2025)
- [Automatic measurement of coverage area of water-based pesticides-surfactant formulation on plant leaves using deep learning tools](https://mlsanity.com/paper/2401.08593/) (2023)
- [CCESAR: Coastline Classification-Extraction From SAR Images Using CNN-U-Net Combination](https://mlsanity.com/paper/2501.12384/) (2025)

## Abstract (arXiv)

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 urlhttps://github.com/khdlr/HED-UNet.