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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Vinge, Rikard, Wittmann, Isabelle, Schneider, Jannik, Marszalek, Michael, Gilch, Luis, Brunschwiler, Thomas, Albrecht, Conrad M
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910051225042944
author Vinge, Rikard
Wittmann, Isabelle
Schneider, Jannik
Marszalek, Michael
Gilch, Luis
Brunschwiler, Thomas
Albrecht, Conrad M
author_facet Vinge, Rikard
Wittmann, Isabelle
Schneider, Jannik
Marszalek, Michael
Gilch, Luis
Brunschwiler, Thomas
Albrecht, Conrad M
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17914
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observation
Vinge, Rikard
Wittmann, Isabelle
Schneider, Jannik
Marszalek, Michael
Gilch, Luis
Brunschwiler, Thomas
Albrecht, Conrad M
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observation
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.17914