mlsanityData to 7 Oct 2026

Semantic Segmentation of Remote Sensing Images with Sparse Annotations

arXiv 2101.03492 ↗First posted 10 Jan 2021cs.CVcited by 30

Not on the map. Why?

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.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 9 of its 19 references that are in the map. First posted on arXiv 10 Jan 2021.

Builds on

9 of 19 references.

References · 9

  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  2. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  3. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  4. 2017Deep learning in remote sensing: a reviewcited by 128
  5. 2016Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagerycited by 36
  6. 2016High-Resolution Semantic Labeling with Convolutional Neural Networkscited by 11
  7. 2019Self-Supervised Representation Learning via Neighborhood-Relational Encodingcited by 10
  8. 2019Weakly Supervised Semantic Segmentation of Satellite Imagescited by 8
  9. 2018Decision fusion with multiple spatial supports by conditional random fieldscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 2; 2024: 7; 2025: 4; 2026: 4.

30 papers.

Sort:

  1. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  2. 2023The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shotcited by 83
  3. 2021A Review on Deep Learning in UAV Remote Sensingcited by 32
  4. 2022Universal Adversarial Examples in Remote Sensing: Methodology and Benchmarkcited by 24
  5. 2024Towards Open-Vocabulary Remote Sensing Image Semantic Segmentationcited by 18
  6. 2022DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensingcited by 17
  7. 2022Consistency-Regularized Region-Growing Network for Semantic Segmentation of Urban Scenes with Point-Level Annotationscited by 10
  8. 2022Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagerycited by 10
  9. 2022Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Imagescited by 7
  10. 2022Handling Image and Label Resolution Mismatch in Remote Sensingcited by 3
  11. 2022Weakly-supervised continual learning for class-incremental segmentationcited by 2
  12. 2022RAIS: Robust and Accurate Interactive Segmentation via Continual Learningcited by 2
18 more
  1. 2024PixelDINO: Semi-Supervised Semantic Segmentation for Detecting Permafrost Disturbancescited by 2
  2. 2024Performance of Human Annotators in Object Detection and Segmentation of Remotely Sensed Datacited by 2
  3. 2026Process-Guided Concept Bottleneck Modelcited by 2
  4. 2023Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagerycited by 1
  5. 2025SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentationcited by 1
  6. 2025Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusioncited by 1
  7. 2021Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral datacited by 0
  8. 2021Segmentation of VHR EO Images using Unsupervised Learningcited by 0
  9. 2022Habitat classification from satellite observations with sparse annotationscited by 0
  10. 2024Spannotation: Enhancing Semantic Segmentation for Autonomous Navigation with Efficient Image Annotationcited by 0
  11. 2024Specialized Change Detection using Segment Anythingcited by 0
  12. 2024Segment Using Just One Examplecited by 0
  13. 2024Weakly Supervised Framework Considering Multi-temporal Information for Large-scale Cropland Mapping with Satellite Imagerycited by 0
  14. 2025LC-SLab -- An object-based deep learning framework for large-scale land cover classification from satellite imagery and sparse in-situ labelscited by 0
  15. 2025Hierarchical Semi-Supervised Active Learning for Remote Sensingcited by 0
  16. 2026Wetland mapping from sparse annotations with satellite image time series and temporal-aware segment anything modelcited by 0
  17. 2026iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervisioncited by 0
  18. 2026Frequency and Edge-Guided Segment Anything Model for Remote Sensing Image Semantic Segmentationcited by 0