# Distance transform regression for spatially-aware deep semantic segmentation

arXiv: https://arxiv.org/abs/1909.01671 · HTML: https://mlsanity.com/paper/1909.01671/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Context-self contrastive pretraining for crop type semantic segmentation](https://mlsanity.com/paper/2104.04310/) (2021)
- [Contour-Aware Equipotential Learning for Semantic Segmentation](https://mlsanity.com/paper/2210.00223/) (2022)
- [Cardiac Segmentation on CT Images through Shape-Aware Contour Attentions](https://mlsanity.com/paper/2105.13153/) (2021)
- [Deep Distance Map Regression Network with Shape-aware Loss for Imbalanced Medical Image Segmentation](https://mlsanity.com/paper/2501.09116/) (2025)
- [GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation](https://mlsanity.com/paper/2606.00886/) (2026)
- [A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation](https://mlsanity.com/paper/2108.07491/) (2021)
- [TAU: Modeling Temporal Consistency Through Temporal Attentive U-Net for PPG Peak Detection](https://mlsanity.com/paper/2503.10733/) (2025)
- [Learning to Upscale 3D Segmentations in Neuroimaging](https://mlsanity.com/paper/2505.21697/) (2025)
- [GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation](https://mlsanity.com/paper/2608.07405/) (2026)

## Abstract (arXiv)

Understanding visual scenes relies more and more on dense pixel-wise classification obtained via deep fully convolutional neural networks. However, due to the nature of the networks, predictions often suffer from blurry boundaries and ill-segmented shapes, fueling the need for post-processing. This work introduces a new semantic segmentation regularization based on the regression of a distance transform. After computing the distance transform on the label masks, we train a FCN in a multi-task setting in both discrete and continuous spaces by learning jointly classification and distance regression. This requires almost no modification of the network structure and adds a very low overhead to the training process. Learning to approximate the distance transform back-propagates spatial cues that implicitly regularizes the segmentation. We validate this technique with several architectures on various datasets, and we show significant improvements compared to competitive baselines.