Salvato in:
Dettagli Bibliografici
Autori principali: Elbarz, Walid, Bourriz, Mohamed, Hajji, Hicham, Abdelali, Hamd Ait, Bourzeix, François
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.11576
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918159995371520
author Elbarz, Walid
Bourriz, Mohamed
Hajji, Hicham
Abdelali, Hamd Ait
Bourzeix, François
author_facet Elbarz, Walid
Bourriz, Mohamed
Hajji, Hicham
Abdelali, Hamd Ait
Bourzeix, François
contents Foundation models are transforming Earth observation, but their potential for hyperspectral crop mapping remains underexplored. This study benchmarks three foundation models for cereal crop mapping using hyperspectral imagery: HyperSigma, DOFA, and Vision Transformers pre-trained on the SpectralEarth dataset (a large multitemporal hyperspectral archive). Models were fine-tuned on manually labeled data from a training region and evaluated on an independent test region. Performance was measured with overall accuracy (OA), average accuracy (AA), and F1-score. HyperSigma achieved an OA of 34.5% (+/- 1.8%), DOFA reached 62.6% (+/- 3.5%), and the SpectralEarth model achieved an OA of 93.5% (+/- 0.8%). A compact SpectralEarth variant trained from scratch achieved 91%, highlighting the importance of model architecture for strong generalization across geographic regions and sensor platforms. These results provide a systematic evaluation of foundation models for operational hyperspectral crop mapping and outline directions for future model development.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11576
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping
Elbarz, Walid
Bourriz, Mohamed
Hajji, Hicham
Abdelali, Hamd Ait
Bourzeix, François
Computer Vision and Pattern Recognition
Foundation models are transforming Earth observation, but their potential for hyperspectral crop mapping remains underexplored. This study benchmarks three foundation models for cereal crop mapping using hyperspectral imagery: HyperSigma, DOFA, and Vision Transformers pre-trained on the SpectralEarth dataset (a large multitemporal hyperspectral archive). Models were fine-tuned on manually labeled data from a training region and evaluated on an independent test region. Performance was measured with overall accuracy (OA), average accuracy (AA), and F1-score. HyperSigma achieved an OA of 34.5% (+/- 1.8%), DOFA reached 62.6% (+/- 3.5%), and the SpectralEarth model achieved an OA of 93.5% (+/- 0.8%). A compact SpectralEarth variant trained from scratch achieved 91%, highlighting the importance of model architecture for strong generalization across geographic regions and sensor platforms. These results provide a systematic evaluation of foundation models for operational hyperspectral crop mapping and outline directions for future model development.
title Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.11576