SpectralGPT: Spectral Foundation Model
Authors:
- Danfeng HongDanfeng Hong
- Bing ZhangBing Zhang
- Xuyang LiXLXuyang Li
- Yuxuan LiYLYuxuan Li
- Chenyu LiCLChenyu Li
- Jing YaoJing Yao
- Naoto YokoyaNaoto Yokoya
- Hao LiHLHao Li
- Xiuping JiaXJXiuping Jia
- Antonio PlazaAntonio Plaza
- Gamba PaoloGPGamba Paolo
- Jon Atli BenediktssonJon Atli Benediktsson
Preprint
Abstract
The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner. While most foundation models are tailored to effectively process RGB images for various visual tasks, there is a noticeable gap in research focused on spectral data, which offers valuable information for scene understanding, especially in remote sensing (RS) applications. To fill this gap, we created for the first time a universal RS foundation model, named SpectralGPT, which is purpose-built to handle spectral RS images using a novel 3D generative pretrained transformer (GPT). Compared to existing foundation models, SpectralGPT 1) accommodates input images with varying sizes, resolutions, time series, and regions in a progressive training fashion, enabling full utilization of extensive RS big data; 2) leverages 3D token generation for spatial-spectral coupling; 3) captures spectrally sequential patterns via multi-target reconstruction; 4) trains on one million spectral RS images, yielding models with over 600 million parameters. Our evaluation highlights significant performance improvements with pretrained SpectralGPT models, signifying substantial potential in advancing spectral RS big data applications within the field of geoscience across four downstream tasks: single/multi-label scene classification, semantic segmentation, and change detection.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopyNature Machine Intelligence, 2022
- RingMo: A Remote Sensing Foundation Model With Masked Image ModelingIEEE Transactions on Geoscience and Remote Sensing, 2022
- Perspectives in machine learning for wildlife conservationNature Communications, 2022
- Modality Translation in Remote Sensing Time SeriesIEEE Transactions on Geoscience and Remote Sensing, 2021
- Interpretable Hyperspectral Artificial Intelligence: When nonconvex modeling meets hyperspectral remote sensingIEEE Geoscience and Remote Sensing Magazine, 2021
- A versatile deep learning architecture for classification and label-free prediction of hyperspectral imagesNature Machine Intelligence, 2021
- EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
- Deep learning and process understanding for data-driven Earth system scienceNature, 2019
- Deep Learning in Remote Sensing: A Comprehensive Review and List of ResourcesIEEE Geoscience and Remote Sensing Magazine, 2017
- Recent advances in techniques for hyperspectral image processingRemote Sensing of Environment, 2009