mlsanityData to 14 Oct 2026

Functional Map of the World

arXiv 1711.07846 ↗First posted 21 Nov 2017cs.CVcited by 338

Not on the map. Why?

Cited by 33 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a new dataset, Functional Map of the World (fMoW), which aims to inspire the development of machine learning models capable of predicting the functional purpose of buildings and land use from temporal sequences of satellite images and a rich set of metadata features. The metadata provided with each image enables reasoning about location, time, sun angles, physical sizes, and other features when making predictions about objects in the image. Our dataset consists of over 1 million images from over 200 countries. For each image, we provide at least one bounding box annotation containing one of 63 categories, including a "false detection" category. We present an analysis of the dataset along with baseline approaches that reason about metadata and temporal views. Our data, code, and pretrained models have been made publicly available.

Key facts. Cited by 338 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 26; 2022: 51; 2023: 59; 2024: 73; 2025: 85; 2026: 44.

338 papers.

Sort:

By area:

  1. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  2. 2021Robust fine-tuning of zero-shot modelscited by 797
  3. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  4. 2021Domain Generalization: A Surveycited by 764
  5. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  6. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  7. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  8. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 408
  9. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 308
  10. 2022Exploring Visual Prompts for Adapting Large-Scale Modelscited by 274
  11. 2023SpectralGPT: Spectral Remote Sensing Foundation Modelcited by 252
  12. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 249
38 more
  1. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  2. 2023SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagerycited by 205
  3. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  4. 2022Datamodels: Predicting Predictions from Training Datacited by 189
  5. 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationcited by 187
  6. 2022SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understandingcited by 167
  7. 2023RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensingcited by 151
  8. 2023SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagerycited by 151
  9. 2022Finetune like you pretrain: Improved finetuning of zero-shot vision modelscited by 150
  10. 2022Leveraging Unlabeled Data to Predict Out-of-Distribution Performancecited by 145
  11. 2022On Feature Learning in the Presence of Spurious Correlationscited by 145
  12. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Modelcited by 138
  13. 2021On Calibration and Out-of-domain Generalizationcited by 134
  14. 2023DiffusionSat: A Generative Foundation Model for Satellite Imagerycited by 131
  15. 2023SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensingcited by 125
  16. 2022SuS-X: Training-Free Name-Only Transfer of Vision-Language Modelscited by 119
  17. 2024Scalable Pre-training of Large Autoregressive Image Modelscited by 115
  18. 2024Multimodal Autoregressive Pre-training of Large Vision Encoderscited by 109
  19. 2022An Empirical Study of Remote Sensing Pretrainingcited by 105
  20. 2024Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observationcited by 104
  21. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  22. 2022Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shiftcited by 94
  23. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 90
  24. 2021Extending the WILDS Benchmark for Unsupervised Adaptationcited by 86
  25. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  26. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  27. 2024EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialoguescited by 85
  28. 2024Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagerycited by 83
  29. 2022DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentationcited by 78
  30. 2024Mission Critical -- Satellite Data is a Distinct Modality in Machine Learningcited by 77
  31. 2024MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learningcited by 77
  32. 2024AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalitiescited by 74
  33. 2024HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Modelcited by 73
  34. 2024TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Datacited by 70
  35. 2023CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representationscited by 69
  36. 2024PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Modelscited by 68
  37. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  38. 2024MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretrainingcited by 66

50 most cited of 338 All 338 (JSON)