# Semantic Segmentation of Remote Sensing Images with Sparse Annotations

arXiv: https://arxiv.org/abs/2101.03492 · HTML: https://mlsanity.com/paper/2101.03492/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 10 Jan 2021.

## Builds on (most cited first, 9 of 9)

- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [Deep learning in remote sensing: a review](https://mlsanity.com/paper/1710.03959/) (2017)
- [Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery](https://mlsanity.com/paper/1606.02585/) (2016)
- [High-Resolution Semantic Labeling with Convolutional Neural Networks](https://mlsanity.com/paper/1611.01962/) (2016)
- [Self-Supervised Representation Learning via Neighborhood-Relational Encoding](https://mlsanity.com/paper/1908.10455/) (2019)
- [Weakly Supervised Semantic Segmentation of Satellite Images](https://mlsanity.com/paper/1904.03983/) (2019)
- [Decision fusion with multiple spatial supports by conditional random fields](https://mlsanity.com/paper/1808.08024/) (2018)

## Built on by (most cited first, 30 of 30)

- [Self-supervised Learning in Remote Sensing: A Review](https://mlsanity.com/paper/2206.13188/) (2022)
- [The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot](https://mlsanity.com/paper/2306.16623/) (2023)
- [A Review on Deep Learning in UAV Remote Sensing](https://mlsanity.com/paper/2101.10861/) (2021)
- [Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark](https://mlsanity.com/paper/2202.07054/) (2022)
- [Towards Open-Vocabulary Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2412.19492/) (2024)
- [DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing](https://mlsanity.com/paper/2201.01047/) (2022)
- [Consistency-Regularized Region-Growing Network for Semantic Segmentation of Urban Scenes with Point-Level Annotations](https://mlsanity.com/paper/2202.03740/) (2022)
- [Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery](https://mlsanity.com/paper/2202.13487/) (2022)
- [Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2202.03501/) (2022)
- [Handling Image and Label Resolution Mismatch in Remote Sensing](https://mlsanity.com/paper/2211.15790/) (2022)
- [Weakly-supervised continual learning for class-incremental segmentation](https://mlsanity.com/paper/2201.01029/) (2022)
- [RAIS: Robust and Accurate Interactive Segmentation via Continual Learning](https://mlsanity.com/paper/2210.10984/) (2022)
- [PixelDINO: Semi-Supervised Semantic Segmentation for Detecting Permafrost Disturbances](https://mlsanity.com/paper/2401.09271/) (2024)
- [Performance of Human Annotators in Object Detection and Segmentation of Remotely Sensed Data](https://mlsanity.com/paper/2409.10272/) (2024)
- [Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusion](https://mlsanity.com/paper/2512.23035/) (2025)
- [Process-Guided Concept Bottleneck Model](https://mlsanity.com/paper/2601.10562/) (2026)
- [Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery](https://mlsanity.com/paper/2306.16252/) (2023)
- [SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentation](https://mlsanity.com/paper/2510.10163/) (2025)
- [Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data](https://mlsanity.com/paper/2106.00799/) (2021)
- [Segmentation of VHR EO Images using Unsupervised Learning](https://mlsanity.com/paper/2108.04222/) (2021)
- [Habitat classification from satellite observations with sparse annotations](https://mlsanity.com/paper/2209.12995/) (2022)
- [Spannotation: Enhancing Semantic Segmentation for Autonomous Navigation with Efficient Image Annotation](https://mlsanity.com/paper/2402.18084/) (2024)
- [Specialized Change Detection using Segment Anything](https://mlsanity.com/paper/2408.06644/) (2024)
- [Segment Using Just One Example](https://mlsanity.com/paper/2408.07393/) (2024)
- [Weakly Supervised Framework Considering Multi-temporal Information for Large-scale Cropland Mapping with Satellite Imagery](https://mlsanity.com/paper/2411.18475/) (2024)
- [LC-SLab -- An object-based deep learning framework for large-scale land cover classification from satellite imagery and sparse in-situ labels](https://mlsanity.com/paper/2509.15868/) (2025)
- [Hierarchical Semi-Supervised Active Learning for Remote Sensing](https://mlsanity.com/paper/2511.18058/) (2025)
- [Wetland mapping from sparse annotations with satellite image time series and temporal-aware segment anything model](https://mlsanity.com/paper/2601.11400/) (2026)
- [iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervision](https://mlsanity.com/paper/2606.10136/) (2026)
- [Frequency and Edge-Guided Segment Anything Model for Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2608.15054/) (2026)

## Abstract (arXiv)

Training Convolutional Neural Networks (CNNs) for very high resolution images requires a large quantity of high-quality pixel-level annotations, which is extremely labor- and time-consuming to produce. Moreover, professional photo interpreters might have to be involved for guaranteeing the correctness of annotations. To alleviate such a burden, we propose a framework for semantic segmentation of aerial images based on incomplete annotations, where annotators are asked to label a few pixels with easy-to-draw scribbles. To exploit these sparse scribbled annotations, we propose the FEature and Spatial relaTional regulArization (FESTA) method to complement the supervised task with an unsupervised learning signal that accounts for neighbourhood structures both in spatial and feature terms.