# Emerging Semantic Segmentation from Positive and Negative Coarse Label Learning

arXiv: https://arxiv.org/abs/2508.18186 · HTML: https://mlsanity.com/paper/2508.18186/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Builds on (most cited first, 16 of 16)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [Human uncertainty makes classification more robust](https://mlsanity.com/paper/1908.07086/) (2019)
- [Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation](https://mlsanity.com/paper/1502.02734/) (2015)
- [Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion](https://mlsanity.com/paper/1902.03680/) (2019)
- [Learning with Biased Complementary Labels](https://mlsanity.com/paper/1711.09535/) (2017)
- [CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision](https://mlsanity.com/paper/2203.01475/) (2022)
- [Disentangling Human Error from the Ground Truth in Segmentation of Medical Images](https://mlsanity.com/paper/2007.15963/) (2020)
- [L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2204.03206/) (2022)
- [Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning](https://mlsanity.com/paper/1809.10780/) (2018)
- [Fully Convolutional Multi-Class Multiple Instance Learning](https://mlsanity.com/paper/1412.7144/) (2014)
- [Towards a glaucoma risk index based on simulated hemodynamics from fundus images](https://mlsanity.com/paper/1805.10273/) (2018)
- [Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images](https://mlsanity.com/paper/2109.10778/) (2021)
- [Improving Few-Shot Part Segmentation using Coarse Supervision](https://mlsanity.com/paper/2204.05393/) (2022)
- [SpineFM: Leveraging Foundation Models for Automatic Spine X-ray Segmentation](https://mlsanity.com/paper/2411.00326/) (2024)

## Abstract (arXiv)

Large annotated datasets are vital for training segmentation models, but pixel-level labeling is time-consuming, error-prone, and often requires scarce expert annotators, especially in medical imaging. In contrast, coarse annotations are quicker, cheaper, and easier to produce, even by non-experts. In this paper, we propose to use coarse drawings from both positive (target) and negative (background) classes in the image, even with noisy pixels, to train a convolutional neural network (CNN) for semantic segmentation. We present a method for learning the true segmentation label distributions from purely noisy coarse annotations using two coupled CNNs. The separation of the two CNNs is achieved by high fidelity with the characters of the noisy training annotations. We propose to add a complementary label learning that encourages estimating negative label distribution. To illustrate the properties of our method, we first use a toy segmentation dataset based on MNIST. We then present the quantitative results of experiments using publicly available datasets: Cityscapes dataset for multi-class segmentation, and retinal images for medical applications. In all experiments, our method outperforms state-of-the-art methods, particularly in the cases where the ratio of coarse annotations is small compared to the given dense annotations.