mlsanityData to 14 Oct 2026

Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model

arXiv 2208.03987 ↗First posted 8 Aug 2022cs.CVcited by 149

Not on the map. Why?

Abstract (arXiv)

Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability. However, large-scale models in remote sensing (RS) have not yet been sufficiently explored. In this paper, we resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models tailored to RS tasks and investigate how such large models perform. To handle the large sizes and objects of arbitrary orientations in RS images, we propose a new rotated varied-size window attention to replace the original full attention in transformers, which can significantly reduce the computational cost and memory footprint while learning better object representation by extracting rich context from the generated diverse windows. Experiments on detection tasks show the superiority of our model over all state-of-the-art models, achieving 81.24% mAP on the DOTA-V1.0 dataset. The results of our models on downstream classification and segmentation tasks also show competitive performance compared to existing advanced methods. Further experiments show the advantages of our models in terms of computational complexity and data efficiency in transferring.

Key facts. Cited by 149 papers in the map (data through 14 Oct 2026). Builds on 67 of its 90 references that are in the map. First posted on arXiv 8 Aug 2022.

Builds on

67 of 90 references.

References · 67

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  9. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  10. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  11. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  12. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
38 more
  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  2. 2016Pyramid Scene Parsing Networkcited by 2,479
  3. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  4. 2017Non-local Neural Networkscited by 2,293
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  6. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,274
  7. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  8. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  9. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  10. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  11. 2021Scaling Vision Transformerscited by 999
  12. 2021Florence: A New Foundation Model for Computer Visioncited by 804
  13. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 797
  14. 2021Scaling Vision with Sparse Mixture of Expertscited by 747
  15. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  16. 2019Panoptic Feature Pyramid Networkscited by 645
  17. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  18. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  19. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 553
  20. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  21. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  22. 2016AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classificationcited by 347
  23. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 340
  24. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 261
  25. 2021Oriented R-CNN for Object Detectioncited by 231
  26. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  27. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 215
  28. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 203
  29. 2019iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Imagescited by 197
  30. 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 194
  31. 2020Geography-Aware Self-Supervised Learningcited by 190
  32. 2020Align Deep Features for Oriented Object Detectioncited by 187
  33. 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 167
  34. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  35. 2019Gliding vertex on the horizontal bounding box for multi-oriented object detectioncited by 134
  36. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  37. 2022ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyondcited by 117
  38. 2020Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Thingscited by 111

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 36; 2024: 51; 2025: 45; 2026: 16.

149 papers.

Sort:

By area:

  1. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 363
  2. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 328
  3. 2023SpectralGPT: Spectral Remote Sensing Foundation Modelcited by 252
  4. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 207
  5. 2023SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagerycited by 205
  6. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 195
  7. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domaincited by 184
  8. 2023RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensingcited by 151
  9. 2024Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observationcited by 104
  10. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  11. 2023Vision-Language Models in Remote Sensing: Current Progress and Future Trendscited by 93
  12. 2024HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Modelcited by 73
38 more
  1. 2024PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Modelscited by 68
  2. 2024MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretrainingcited by 66
  3. 2023A Billion-scale Foundation Model for Remote Sensing Imagescited by 62
  4. 2023ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformerscited by 56
  5. 2023Adaptive Rotated Convolution for Rotated Object Detectioncited by 51
  6. 2023CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understandingcited by 48
  7. 2024LSKNet: A Foundation Lightweight Backbone for Remote Sensingcited by 44
  8. 2024MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generationcited by 42
  9. 2025BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster responsecited by 41
  10. 2025RemoteSAM: Towards Segment Anything for Earth Observationcited by 39
  11. 2025TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysiscited by 39
  12. 2023SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Modelcited by 38
  13. 2024Towards Vision-Language Geo-Foundation Model: A Surveycited by 36
  14. 2024TaxaBind: A Unified Embedding Space for Ecological Applicationscited by 35
  15. 2024On the Foundations of Earth and Climate Foundation Modelscited by 33
  16. 2024Large Language Models for Captioning and Retrieving Remote Sensing Imagescited by 30
  17. 2024Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretrainingcited by 28
  18. 2024CityBench: Evaluating the Capabilities of Large Language Models for Urban Taskscited by 27
  19. 2024CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentationcited by 27
  20. 2025SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensingcited by 26
  21. 2024SARATR-X: Toward Building A Foundation Model for SAR Target Recognitioncited by 25
  22. 2023AerialFormer: Multi-resolution Transformer for Aerial Image Segmentationcited by 23
  23. 2024Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Modelscited by 23
  24. 2023Domain-Controlled Prompt Learningcited by 22
  25. 2024Masked Angle-Aware Autoencoder for Remote Sensing Imagescited by 22
  26. 2023Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advancescited by 20
  27. 2025A Survey on Remote Sensing Foundation Models: From Vision to Multimodalitycited by 19
  28. 2023Domain Prompt Learning with Quaternion Networkscited by 17
  29. 2024Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidancecited by 17
  30. 2025HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagerycited by 17
  31. 2025RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretationcited by 16
  32. 2024RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learningcited by 15
  33. 2025REOBench: Benchmarking Robustness of Earth Observation Foundation Modelscited by 15
  34. 2025Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detectioncited by 14
  35. 2023When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence Systemcited by 13
  36. 2024GRA: Detecting Oriented Objects through Group-wise Rotating and Attentioncited by 13
  37. 2023DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classificationcited by 12
  38. 2023Spatial Transform Decoupling for Oriented Object Detectioncited by 12

50 most cited of 149 All 149 (JSON)