# Weakly Supervised Semantic Segmentation of Satellite Images

arXiv: https://arxiv.org/abs/1904.03983 · HTML: https://mlsanity.com/paper/1904.03983/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 8 of 8)

- [Semantic Segmentation of Remote Sensing Images with Sparse Annotations](https://mlsanity.com/paper/2101.03492/) (2021)
- [Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement](https://mlsanity.com/paper/2109.09477/) (2021)
- [ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation](https://mlsanity.com/paper/2211.12455/) (2022)
- [Domain Adaptable Self-supervised Representation Learning on Remote Sensing Satellite Imagery](https://mlsanity.com/paper/2304.09874/) (2023)
- [Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery](https://mlsanity.com/paper/2306.16252/) (2023)
- [Learning Semantic Segmentation with Query Points Supervision on Aerial Images](https://mlsanity.com/paper/2309.05490/) (2023)
- [Comparison of Segmentation Methods in Remote Sensing for Land Use Land Cover](https://mlsanity.com/paper/2507.18099/) (2025)
- [A deep multiple instance learning approach based on coarse labels for high-resolution land-cover mapping](https://mlsanity.com/paper/2510.06769/) (2025)

## Abstract (arXiv)

When one wants to train a neural network to perform semantic segmentation, creating pixel-level annotations for each of the images in the database is a tedious task. If he works with aerial or satellite images, which are usually very large, it is even worse. With that in mind, we investigate how to use image-level annotations in order to perform semantic segmentation. Image-level annotations are much less expensive to acquire than pixel-level annotations, but we lose a lot of information for the training of the model. From the annotations of the images, the model must find by itself how to classify the different regions of the image. In this work, we use the method proposed by Anh and Kwak [1] to produce pixel-level annotation from image level annotation. We compare the overall quality of our generated dataset with the original dataset. In addition, we propose an adaptation of the AffinityNet that allows us to directly perform a semantic segmentation. Our results show that the generated labels lead to the same performances for the training of several segmentation networks. Also, the quality of semantic segmentation performed directly by the AffinityNet and the Random Walk is close to the one of the best fully-supervised approaches.