mlsanityData to 14 Oct 2026

NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observation

arXiv 2510.17914 ↗First posted 19 Oct 2025cs.LG cs.AI cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We introduce NeuCo-Bench, a novel benchmark framework for evaluating (lossy) neural compression and representation learning in the context of Earth Observation (EO). Our approach builds on fixed-size embeddings that act as compact, task-agnostic representations applicable to a broad range of downstream tasks. NeuCo-Bench comprises three components: (i) an evaluation pipeline built around embeddings, (ii) a challenge mode with a hidden-task leaderboard designed to mitigate pretraining bias, and (iii) a scoring system that balances accuracy and stability. To support reproducibility, we release SSL4EO-S12-downstream, a curated multispectral, multitemporal EO dataset. We present results from a public challenge at the 2025 CVPR EARTHVISION workshop and conduct ablations with state-of-the-art foundation models. NeuCo-Bench provides a step towards community-driven, standardized evaluation of neural embeddings for EO and beyond.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 41 of its 79 references that are in the map. First posted on arXiv 19 Oct 2025.

Builds on

41 of 79 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  6. 2018Variational image compression with a scale hyperpriorcited by 935
  7. 2016End-to-end Optimized Image Compressioncited by 696
  8. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
  9. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 363
  10. 2017Lossy Image Compression with Compressive Autoencoderscited by 294
  11. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 264
  12. 2021COIN: COmpression with Implicit Neural representationscited by 233
29 more
  1. 2023CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoderscited by 169
  2. 2021Implicit Neural Representations for Image Compressioncited by 162
  3. 2023SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagerycited by 151
  4. 2022Advancing Plain Vision Transformer Towards Remote Sensing Foundation Modelcited by 149
  5. 2023Foundation Models for Generalist Geospatial Artificial Intelligencecited by 149
  6. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  7. 2025AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label datacited by 137
  8. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 107
  9. 2024Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observationcited by 104
  10. 2020A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagerycited by 88
  11. 2019Methods and open-source toolkit for analyzing and visualizing challenge resultscited by 60
  12. 2025Towards a Unified Copernicus Foundation Model for Earth Visioncited by 53
  13. 2018Towards Image Understanding from Deep Compression without Decodingcited by 52
  14. 2021Lossy Compression for Lossless Predictioncited by 52
  15. 2021Image coding for machines: an end-to-end learned approachcited by 47
  16. 2020End-to-end Learning of Compressible Featurescited by 43
  17. 2020End-to-end optimized image compression for machines, a studycited by 30
  18. 2021Representation Learning Beyond Linear Prediction Functionscited by 21
  19. 2021Learned Image Compression for Machine Perceptioncited by 14
  20. 2024AGBD: A Global-scale Biomass Datasetcited by 13
  21. 2021End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimizationcited by 12
  22. 2021Boosting Neural Image Compression for Machines Using Latent Space Maskingcited by 11
  23. 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
  24. 2021End-to-end optimized image compression for multiple machine taskscited by 9
  25. 2025SSL4EO-S12 v1.1: A Multimodal, Multiseasonal Dataset for Pretraining, Updatedcited by 9
  26. 2025Towards a Unified Representation Evaluation Framework Beyond Downstream Taskscited by 7
  27. 2024Earth+: on-board satellite imagery compression leveraging historical earth observationscited by 6
  28. 2025GSR4B: Biomass Map Super-Resolution with Sentinel-1/2 Guidancecited by 3
  29. 2024Neural Embedding Compression For Efficient Multi-Task Earth Observation Modellingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Earth Embeddings as Products: Taxonomy, Ecosystem, and Standardized Accesscited by 5
  2. 2026TESSERA v2: Scaling Pixel-wise Earth Foundation Modelscited by 5
  3. 2026Inferring Height from Earth Embeddings: First insights using Google AlphaEarthcited by 4
  4. 2026How to Embed Matters: Evaluation of EO Embedding Design Choicescited by 1
  5. 2026How do Self-Supervised Remote Sensing Vision Models Transfer to Downstream Tasks?cited by 0
  6. 2026Curated retrieval versus open web search in public AI information services: a coverage-trust trade-offcited by 0
  7. 2026Earth Embeddingscited by 0