mlsanityData to 7 Oct 2026

PhilEO Bench: Evaluating Geo-Spatial Foundation Models

arXiv 2401.04464 ↗First posted 9 Jan 2024cs.CV cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Massive amounts of unlabelled data are captured by Earth Observation (EO) satellites, with the Sentinel-2 constellation generating 1.6 TB of data daily. This makes Remote Sensing a data-rich domain well suited to Machine Learning (ML) solutions. However, a bottleneck in applying ML models to EO is the lack of annotated data as annotation is a labour-intensive and costly process. As a result, research in this domain has focused on Self-Supervised Learning and Foundation Model approaches. This paper addresses the need to evaluate different Foundation Models on a fair and uniform benchmark by introducing the PhilEO Bench, a novel evaluation framework for EO Foundation Models. The framework comprises of a testbed and a novel 400 GB Sentinel-2 dataset containing labels for three downstream tasks, building density estimation, road segmentation, and land cover classification. We present experiments using our framework evaluating different Foundation Models, including Prithvi and SatMAE, at multiple n-shots and convergence rates.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 9 Jan 2024.

Builds on

22 of 38 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  4. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 402
  5. 2023ClimaX: A foundation model for weather and climatecited by 325
  6. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 302
  7. 2023A Cookbook of Self-Supervised Learningcited by 248
  8. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 214
  9. 2017Multi-task Self-Supervised Visual Learningcited by 200
  10. 2020Geography-Aware Self-Supervised Learningcited by 190
  11. 2023SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagerycited by 148
  12. 2023Foundation Models for Generalist Geospatial Artificial Intelligencecited by 143
10 more
  1. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  2. 2023GEO-Bench: Toward Foundation Models for Earth Monitoringcited by 122
  3. 2023Towards Geospatial Foundation Models via Continual Pretrainingcited by 109
  4. 2023Lightweight, Pre-trained Transformers for Remote Sensing Timeseriescited by 102
  5. 2022SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observationcited by 82
  6. 2021Geographical Knowledge-driven Representation Learning for Remote Sensing Imagescited by 37
  7. 2023USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagerycited by 28
  8. 2023The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learningcited by 27
  9. 2023Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matterscited by 27
  10. 2022Embedding Earth: Self-supervised contrastive pre-training for dense land cover classificationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 13; 2026: 7.

25 papers.

Sort:

  1. 2025TerraMind: Large-Scale Generative Multimodality for Earth Observationcited by 101
  2. 2025Towards a Unified Copernicus Foundation Model for Earth Visioncited by 52
  3. 2024On the Foundations of Earth and Climate Foundation Modelscited by 31
  4. 2026No One Knows the State of the Art in Geospatial Foundation Modelscited by 9
  5. 2024Evaluating and Benchmarking Foundation Models for Earth Observation and Geospatial AIcited by 7
  6. 2025Ice-FMBench: A Foundation Model Benchmark for Sea Ice Type Segmentationcited by 5
  7. 2025SSL4Eco: A Global Seasonal Dataset for Geospatial Foundation Models in Ecologycited by 5
  8. 2025SciVid: Cross-Domain Evaluation of Video Models in Scientific Applicationscited by 5
  9. 2025Deploying Geospatial Foundation Models in the Real World: Lessons from WorldCerealcited by 5
  10. 2025Foundation Models for Environmental Science: A Survey of Emerging Frontierscited by 4
  11. 2026MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Trainingcited by 4
  12. 2025Towards Efficient Benchmarking of Foundation Models in Remote Sensing: A Capabilities Encoding Approachcited by 3
13 more
  1. 2026TESSERA v2: Scaling Pixel-wise Earth Foundation Modelscited by 3
  2. 2024SatSwinMAE: Efficient Autoencoding for Multiscale Time-series Satellite Imagerycited by 2
  3. 2025Building Age Estimation: A New Multi-Modal Benchmark Dataset and Community Challengecited by 2
  4. 2026Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Datacited by 2
  5. 2026Benchmarking Geospatial Foundation Models for Agriculture Applicationscited by 2
  6. 2024Improving satellite imagery segmentation using multiple Sentinel-2 revisitscited by 1
  7. 2025CARE: Confidence-Aware Regression Estimation of building density fine-tuning EO Foundation Modelscited by 1
  8. 2025Scaling Laws for Geospatial Foundation Models: A case study on PhilEO Benchcited by 1
  9. 2024Improving EO Foundation Models with Confidence Assessment for enhanced Semantic segmentationcited by 0
  10. 2025Rethinking deep learning: linear regression remains a key benchmark in predicting terrestrial water storagecited by 0
  11. 2025Context-Aware Multimodal Representation Learning for Spatio-Temporally Explicit Environmental Modellingcited by 0
  12. 2026Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inferencecited by 0
  13. 2026RSPDBench: Benchmarking Vision Foundation Models on Earth Observation Tasks Under Physically Grounded Remote-Sensing Product Degradationscited by 0