mlsanityData to 7 Oct 2026

Uncertainty, Edge, and Reverse-Attention Guided Generative Adversarial Network for Automatic Building Detection in Remotely Sensed Images

arXiv 2112.05335 ↗First posted 10 Dec 2021cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Despite recent advances in deep-learning based semantic segmentation, automatic building detection from remotely sensed imagery is still a challenging problem owing to large variability in the appearance of buildings across the globe. The errors occur mostly around the boundaries of the building footprints, in shadow areas, and when detecting buildings whose exterior surfaces have reflectivity properties that are very similar to those of the surrounding regions. To overcome these problems, we propose a generative adversarial network based segmentation framework with uncertainty attention unit and refinement module embedded in the generator. The refinement module, composed of edge and reverse attention units, is designed to refine the predicted building map. The edge attention enhances the boundary features to estimate building boundaries with greater precision, and the reverse attention allows the network to explore the features missing in the previously estimated regions. The uncertainty attention unit assists the network in resolving uncertainties in classification. As a measure of the power of our approach, as of December 4, 2021, it ranks at the second place on DeepGlobe's public leaderboard despite the fact that main focus of our approach -- refinement of the building edges -- does not align exactly with the metrics used for leaderboard rankings. Our overall F1-score on DeepGlobe's challenging dataset is 0.745. We also report improvements on the previous-best results for the challenging INRIA Validation Dataset for which our network achieves an overall IoU of 81.28% and an overall accuracy of 97.03%. Along the same lines, for the official INRIA Test Dataset, our network scores 77.86% and 96.41% in overall IoU and accuracy.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 93 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

34 of 93 references.

References · 34

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Mask R-CNNcited by 7,259
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  8. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  9. 2015Holistically-Nested Edge Detectioncited by 590
  10. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  11. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  12. 2014Deeply-Supervised Netscited by 364
22 more
  1. 2019Panoptic-DeepLabcited by 362
  2. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 276
  3. 2020Hierarchical Multi-Scale Attention for Semantic Segmentationcited by 183
  4. 2018SpaceNet: A Remote Sensing Dataset and Challenge Seriescited by 178
  5. 2019Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networkscited by 116
  6. 2018Reverse Attention for Salient Object Detectioncited by 113
  7. 2020Improving Semantic Segmentation via Decoupled Body and Edge Supervisioncited by 98
  8. 2019FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentationcited by 70
  9. 2017SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentationcited by 49
  10. 2015Training Deeper Convolutional Networks with Deep Supervisioncited by 36
  11. 2019A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenescited by 33
  12. 2019SpaceNet MVOI: a Multi-View Overhead Imagery Datasetcited by 29
  13. 2018TernausNetV2: Fully Convolutional Network for Instance Segmentationcited by 25
  14. 2017Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networkscited by 24
  15. 2020Machine-learned Regularization and Polygonization of Building Segmentation Maskscited by 22
  16. 2018A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalizationcited by 4
  17. 2019ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Imagescited by 4
  18. 2019Semantic Segmentation from Remote Sensor Data and the Exploitation of Latent Learning for Classification of Auxiliary Taskscited by 4
  19. 2018Automatic Pixelwise Object Labeling for Aerial Imagery Using Stacked U-Netscited by 3
  20. 2020Semantic Labeling of Large-Area Geographic Regions Using Multi-View and Multi-Date Satellite Images and Noisy OSM Training Labelscited by 3
  21. 2020Adversarial Loss for Semantic Segmentation of Aerial Imagerycited by 1
  22. 2020Contextual Pyramid Attention Network for Building Segmentation in Aerial Imagerycited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025SatDepth: A Novel Dataset for Satellite Image Matchingcited by 1