mlsanityData to 14 Oct 2026

IRSAMap:Towards Large-Scale, High-Resolution Land Cover Map Vectorization

arXiv 2508.16272 ↗First posted 22 Aug 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

With the enhancement of remote sensing image resolution and the rapid advancement of deep learning, land cover mapping is transitioning from pixel-level segmentation to object-based vector modeling. This shift demands more from deep learning models, requiring precise object boundaries and topological consistency. However, existing datasets face three main challenges: limited class annotations, small data scale, and lack of spatial structural information. To overcome these issues, we introduce IRSAMap, the first global remote sensing dataset for large-scale, high-resolution, multi-feature land cover vector mapping. IRSAMap offers four key advantages: 1) a comprehensive vector annotation system with over 1.8 million instances of 10 typical objects (e.g., buildings, roads, rivers), ensuring semantic and spatial accuracy; 2) an intelligent annotation workflow combining manual and AI-based methods to improve efficiency and consistency; 3) global coverage across 79 regions in six continents, totaling over 1,000 km; and 4) multi-task adaptability for tasks like pixel-level classification, building outline extraction, road centerline extraction, and panoramic segmentation. IRSAMap provides a standardized benchmark for the shift from pixel-based to object-based approaches, advancing geographic feature automation and collaborative modeling. It is valuable for global geographic information updates and digital twin construction. The dataset is publicly available at https://github.com/ucas-dlg/IRSAMap

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 42 of its 90 references that are in the map. First posted on arXiv 22 Aug 2025.

Builds on

42 of 90 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Segment Anythingcited by 8,234
  3. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  4. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 277
  5. 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 261
  6. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 261
  7. 2018SpaceNet: A Remote Sensing Dataset and Challenge Seriescited by 179
  8. 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 167
  9. 2018Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Modelscited by 119
  10. 2018RoadTracer: Automatic Extraction of Road Networks from Aerial Imagescited by 102
  11. 2022OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mappingcited by 82
  12. 2020Sat2Graph: Road Graph Extraction through Graph-Tensor Encodingcited by 55
30 more
  1. 2023Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Modelscited by 44
  2. 2020LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagerycited by 40
  3. 2016Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detectioncited by 38
  4. 2018Learning deep structured active contours end-to-endcited by 38
  5. 2016Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagerycited by 36
  6. 2019Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial Imagescited by 32
  7. 2022Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagerycited by 31
  8. 2019DARNet: Deep Active Ray Network for Building Segmentationcited by 30
  9. 2021Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Imagescited by 28
  10. 2024Segment Anything Model for Road Network Graph Extractioncited by 28
  11. 2020Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusioncited by 27
  12. 2022RNGDet: Road Network Graph Detection by Transformer in Aerial Imagescited by 26
  13. 2022RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancementcited by 24
  14. 2016Dense semantic labeling of sub-decimeter resolution images with convolutional neural networkscited by 19
  15. 2020LandCoverNet: A global benchmark land cover classification training datasetcited by 18
  16. 2020End-to-End Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial Imagerycited by 16
  17. 2022Learning to Extract Building Footprints from Off-Nadir Aerial Imagescited by 13
  18. 2022BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extractioncited by 12
  19. 2024OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Constructioncited by 11
  20. 2022A diverse large-scale building dataset and a novel plug-and-play domain generalization method for building extractioncited by 10
  21. 2024Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Methodcited by 10
  22. 2020MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Imagescited by 8
  23. 2024LOGCAN++: Adaptive Local-global class-aware network for semantic segmentation of remote sensing imagerycited by 7
  24. 2024PolyR-CNN: R-CNN for end-to-end polygonal building outline extractioncited by 6
  25. 2024P2PFormer: A Primitive-to-polygon Method for Regular Building Contour Extraction from Remote Sensing Imagescited by 5
  26. 2025Global Collinearity-aware Polygonizer for Polygonal Building Mapping in Remote Sensingcited by 4
  27. 2018Automatic Pixelwise Object Labeling for Aerial Imagery Using Stacked U-Netscited by 3
  28. 2023Building-road Collaborative Extraction from Remotely Sensed Images via Cross-Interactioncited by 2
  29. 2025A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation viaSynergistic Pseudo-Labeling and Generative Learningcited by 2
  30. 2025GLD-Road:A global-local decoding road network extraction model for remote sensing imagescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imagerycited by 3
  2. 2026ObliCity: A Benchmark and Baseline for Roof-to-Ground Projection Displacement Correctioncited by 1
  3. 2026Vector Map as Language: Toward Unified Remote Sensing Vector Mappingcited by 0
  4. 2026Remote-Sensing City Layout Extraction with MLLMcited by 0
  5. 2026LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagerycited by 0