# Leveraging point annotations in segmentation learning with boundary loss

arXiv: https://arxiv.org/abs/2311.03537 · HTML: https://mlsanity.com/paper/2311.03537/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## Builds on (most cited first, 22 of 22)

- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations](https://mlsanity.com/paper/1904.05044/) (2019)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](https://mlsanity.com/paper/1603.07485/) (2016)
- [Conditional Random Fields as Recurrent Neural Networks](https://mlsanity.com/paper/1502.03240/) (2015)
- [Boundary loss for highly unbalanced segmentation](https://mlsanity.com/paper/1812.07032/) (2018)
- [On Regularized Losses for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1803.09569/) (2018)
- [Normalized Cut Loss for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1804.01346/) (2018)
- [DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation](https://mlsanity.com/paper/1707.00652/) (2017)
- [Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation](https://mlsanity.com/paper/1904.06346/) (2019)
- [DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks](https://mlsanity.com/paper/1605.07866/) (2016)
- [STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/1509.03150/) (2015)
- [Constrained-CNN losses for weakly supervised segmentation](https://mlsanity.com/paper/1805.04628/) (2018)
- [Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision](https://mlsanity.com/paper/2004.06816/) (2020)
- [Going to Extremes: Weakly Supervised Medical Image Segmentation](https://mlsanity.com/paper/2009.11988/) (2020)
- [Scribble-based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentation](https://mlsanity.com/paper/1911.02014/) (2019)
- [Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation](https://mlsanity.com/paper/2107.00583/) (2021)
- [Weakly Supervised Object Detection with 2D and 3D Regression Neural Networks](https://mlsanity.com/paper/1906.01891/) (2019)
- [FastGeodis: Fast Generalised Geodesic Distance Transform](https://mlsanity.com/paper/2208.00001/) (2022)
- [Weakly Supervised Segmentation by A Deep Geodesic Prior](https://mlsanity.com/paper/1908.06498/) (2019)

## Built on by (most cited first, 2 of 2)

- [Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Models](https://mlsanity.com/paper/2404.13239/) (2024)
- [UAVDB: Point-Guided Masks for UAV Detection and Segmentation](https://mlsanity.com/paper/2409.06490/) (2024)

## Abstract (arXiv)

This paper investigates the combination of intensity-based distance maps with boundary loss for point-supervised semantic segmentation. By design the boundary loss imposes a stronger penalty on the false positives the farther away from the object they occur. Hence it is intuitively inappropriate for weak supervision, where the ground truth label may be much smaller than the actual object and a certain amount of false positives (w.r.t. the weak ground truth) is actually desirable. Using intensity-aware distances instead may alleviate this drawback, allowing for a certain amount of false positives without a significant increase to the training loss. The motivation for applying the boundary loss directly under weak supervision lies in its great success for fully supervised segmentation tasks, but also in not requiring extra priors or outside information that is usually required -- in some form -- with existing weakly supervised methods in the literature. This formulation also remains potentially more attractive than existing CRF-based regularizers, due to its simplicity and computational efficiency. We perform experiments on two multi-class datasets; ACDC (heart segmentation) and POEM (whole-body abdominal organ segmentation). Preliminary results are encouraging and show that this supervision strategy has great potential. On ACDC it outperforms the CRF-loss based approach, and on POEM data it performs on par with it. The code for all our experiments is openly available.