mlsanityData to 14 Oct 2026

SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models

arXiv 2304.11619 ↗First posted 23 Apr 2023cs.CV cs.AI cs.LGcited by 15

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Interpreting remote sensing imagery enables numerous downstream applications ranging from land-use planning to deforestation monitoring. Robustly classifying this data is challenging due to the Earth's geographic diversity. While many distinct satellite and aerial image classification datasets exist, there is yet to be a benchmark curated that suitably covers this diversity. In this work, we introduce SATellite ImageNet (SATIN), a metadataset curated from 27 existing remotely sensed datasets, and comprehensively evaluate the zero-shot transfer classification capabilities of a broad range of vision-language (VL) models on SATIN. We find SATIN to be a challenging benchmark-the strongest method we evaluate achieves a classification accuracy of 52.0%. We provide a hrefhttps://satinbenchmark.github.iopublic leaderboard to guide and track the progress of VL models in this important domain.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 40 of its 89 references that are in the map. First posted on arXiv 23 Apr 2023.

Builds on

40 of 89 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  6. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  8. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  9. 2022A ConvNet for the 2020scited by 3,579
  10. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  11. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,729
  12. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
28 more
  1. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  2. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  3. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  4. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
  5. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 797
  6. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 627
  7. 2021Datasets: A Community Library for Natural Language Processingcited by 530
  8. 2021SLIP: Self-supervision meets Language-Image Pre-trainingcited by 436
  9. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 425
  10. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
  11. 2016AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classificationcited by 347
  12. 2017Functional Map of the Worldcited by 338
  13. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  14. 2019BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understandingcited by 234
  15. 2017Exploring Models and Data for Remote Sensing Image Caption Generationcited by 197
  16. 2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
  17. 2022CyCLIP: Cyclic Contrastive Language-Image Pretrainingcited by 127
  18. 2018Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Modelscited by 119
  19. 2017PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrievalcited by 97
  20. 2020MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understandingcited by 59
  21. 2022Open High-Resolution Satellite Imagery: The WorldStrat Dataset -- With Application to Super-Resolutioncited by 40
  22. 2022EarthNets: Empowering AI in Earth Observationcited by 40
  23. 2015DeepSat - A Learning framework for Satellite Imagerycited by 38
  24. 2019Relation Network for Multi-label Aerial Image Classificationcited by 26
  25. 2019So2Sat LCZ42: A Benchmark Dataset for Global Local Climate Zones Classificationcited by 24
  26. 2022Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classificationcited by 18
  27. 2022NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Researchcited by 18
  28. 2021MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Imagescited by 7

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 6; 2025: 6.

15 papers.

Sort:

By area:

  1. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 363
  2. 2023GPT4GEO: How a Language Model Sees the World's Geographycited by 68
  3. 2025RemoteSAM: Towards Segment Anything for Earth Observationcited by 39
  4. 2024Towards Vision-Language Geo-Foundation Model: A Surveycited by 36
  5. 2023Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMscited by 34
  6. 2025Vision-Language Models for Edge Networks: A Comprehensive Surveycited by 29
  7. 2024A Practitioner's Guide to Continual Multimodal Pretrainingcited by 23
  8. 2025Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectivescited by 18
  9. 2024Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignmentcited by 15
  10. 2024GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Modelscited by 3
  11. 2025AI Benchmark Democratization and Carpentrycited by 3
  12. 2025OpenEarthSensing: Large-Scale Fine-Grained Benchmark for Open-World Remote Sensingcited by 2
3 more
  1. 2025An MLCommons Scientific Benchmarks Ontologycited by 2
  2. 2024Advancements in Visual Language Models for Remote Sensing: Datasets, Capabilities, and Enhancement Techniquescited by 1
  3. 2024Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing
  2. 2026OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMs
  3. 2024Pushing the Limits of Vision-Language Models in Remote Sensing without Human Annotations
  4. 2024VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
  5. 2025Falcon: A Remote Sensing Vision-Language Foundation Model (Technical Report)
  6. 2024Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification
  7. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmark
  8. 2026OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks