OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery

While the pretraining of Foundation Models (FMs) for remote sensing (RS) imagery is on the rise, models remain restricted to a few hundred million parameters. Scaling models to billions of parameters has been shown to yield unprecedented benefits including emergent abilities, but requires data scali...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org
Hauptverfasser:	Dias, Philipe, Tsaris, Aristeidis, Bowman, Jordan, Potnis, Abhishek, Arndt, Jacob, Yang, H Lexie, Dalton Lunga
Format:	Paper
Sprache:	Englisch
Veröffentlicht:	Ithaca Cornell University Library, arXiv.org 25.10.2024
Schlagworte:	Best practice Computation High resolution Image classification Image resolution Image segmentation Object recognition Parameters Remote sensing Satellite imagery Scaling Semantic segmentation
ISSN:	2331-8422
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!