mlsanityData to 14 Oct 2026

AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation

arXiv 2306.06842 ↗First posted 12 Jun 2023cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Aerial Image Segmentation is a top-down perspective semantic segmentation and has several challenging characteristics such as strong imbalance in the foreground-background distribution, complex background, intra-class heterogeneity, inter-class homogeneity, and tiny objects. To handle these problems, we inherit the advantages of Transformers and propose AerialFormer, which unifies Transformers at the contracting path with lightweight Multi-Dilated Convolutional Neural Networks (MD-CNNs) at the expanding path. Our AerialFormer is designed as a hierarchical structure, in which Transformer encoder outputs multi-scale features and MD-CNNs decoder aggregates information from the multi-scales. Thus, it takes both local and global contexts into consideration to render powerful representations and high-resolution segmentation. We have benchmarked AerialFormer on three common datasets including iSAID, LoveDA, and Potsdam. Comprehensive experiments and extensive ablation studies show that our proposed AerialFormer outperforms previous state-of-the-art methods with remarkable performance. Our source code will be publicly available upon acceptance.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 82 of its 121 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

82 of 121 references.

References · 82

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  8. 2020End-to-End Object Detection with Transformerscited by 7,414
  9. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  10. 2016Layer Normalizationcited by 5,669
  11. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  12. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
38 more
  1. 2017Squeeze-and-Excitation Networkscited by 4,789
  2. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  8. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  9. 2016Pyramid Scene Parsing Networkcited by 2,479
  10. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  11. 2017Non-local Neural Networkscited by 2,293
  12. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  13. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  14. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  15. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  16. 2017Deformable Convolutional Networkscited by 1,488
  17. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  18. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  19. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  20. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  21. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  22. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  23. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  24. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
  25. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  26. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  27. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 573
  28. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
  29. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  30. 2018Context Encoding for Semantic Segmentationcited by 290
  31. 2019Cross-Modal Self-Attention Network for Referring Image Segmentationcited by 263
  32. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 261
  33. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 214
  34. 2019iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Imagescited by 197
  35. 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 167
  36. 2018Pyramid Attention Network for Semantic Segmentationcited by 149
  37. 2022Advancing Plain Vision Transformer Towards Remote Sensing Foundation Modelcited by 149
  38. 2019Expectation-Maximization Attention Networks for Semantic Segmentationcited by 147

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 11; 2026: 3.

23 papers.

Sort:

By area:

  1. 2024MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretrainingcited by 66
  2. 2024GiT: Towards Generalist Vision Transformer through Universal Language Interfacecited by 24
  3. 2024Towards Open-Vocabulary Remote Sensing Image Semantic Segmentationcited by 19
  4. 2023OpenForest: A data catalogue for machine learning in forest monitoringcited by 15
  5. 2025SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentationcited by 8
  6. 2025Dynamic Dictionary Learning for Remote Sensing Image Segmentationcited by 7
  7. 2024Learning from Unlabelled Data with Transformers: Domain Adaptation for Semantic Segmentation of High Resolution Aerial Imagescited by 4
  8. 2025CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentationcited by 3
  9. 2025Remote Sensing Semantic Segmentation Quality Assessment based on Vision Language Modelcited by 3
  10. 2024Semantic Segmentation of Unmanned Aerial Vehicle Remote Sensing Images using SegFormercited by 2
  11. 2023SolarFormer: Multi-scale Transformer for Solar PV Profilingcited by 1
  12. 2024Neural Embedding Compression For Efficient Multi-Task Earth Observation Modellingcited by 1
11 more
  1. 2024Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagerycited by 1
  2. 2025LightFormer: A lightweight and efficient decoder for remote sensing image segmentationcited by 1
  3. 2025ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Networkcited by 1
  4. 2025WakeupUrban: Unsupervised Semantic Segmentation of Mid-20th century Urban Landscapes with Satellite Imagerycited by 1
  5. 2025Stratify or Die: Rethinking Data Splits in Image Segmentationcited by 1
  6. 2025ChromaFormer: A Scalable and Accurate Transformer Architecture for Land Cover Classificationcited by 0
  7. 2025Differential Morphological Profile Neural Networks for Semantic Segmentationcited by 0
  8. 2025BiCoR-Seg: Bidirectional Co-Refinement Framework for High-Resolution Remote Sensing Image Segmentationcited by 0
  9. 2026Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentationcited by 0
  10. 2026Hierarchical Adaptive Feature Refinement Network for VHR Remote Sensing Image Segmentationcited by 0
  11. 2026CRISP: Calibration-Aware Visual State Space Duality for Remote Sensing Semantic Segmentationcited by 0