Chrome Extension
WeChat Mini Program
Use on ChatGLM

One for All: Toward Unified Foundation Models for Earth Vision

IGARSS(2024)

Technical University of Munich Chair of Data Science in Earth Observation

Cited 2|Views18
Abstract
Foundation models characterized by extensive parameters and trained onlarge-scale datasets have demonstrated remarkable efficacy across variousdownstream tasks for remote sensing data. Current remote sensing foundationmodels typically specialize in a single modality or a specific spatialresolution range, limiting their versatility for downstream datasets. Whilethere have been attempts to develop multi-modal remote sensing foundationmodels, they typically employ separate vision encoders for each modality orspatial resolution, necessitating a switch in backbones contingent upon theinput data. To address this issue, we introduce a simple yet effective method,termed OFA-Net (One-For-All Network): employing a single, shared Transformerbackbone for multiple data modalities with different spatial resolutions. Usingthe masked image modeling mechanism, we pre-train a single Transformer backboneon a curated multi-modal dataset with this simple design. Then the backbonemodel can be used in different downstream tasks, thus forging a path towards aunified foundation backbone model in Earth vision. The proposed method isevaluated on 12 distinct downstream tasks and demonstrates promisingperformance.
More
Translated text
Key words
Foundation models,remote sensing,Earth observation,self-supervised learning
PDF
Bibtex
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Related Papers
Michael J. Smith, Luke Fleming,James E. Geach
2023

被引用1 | 浏览

Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper

要点】:本文提出了一种名为OFA-Net的统一基础模型,通过使用单一共享的Transformer backbone处理多种数据模态和不同空间分辨率的遥感数据,实现了遥感领域基础模型的通用性。

方法】:采用单一Transformer backbone,结合掩码图像建模机制,在精心策划的多模态数据集上进行预训练。

实验】:在12个不同的下游任务中评估OFA-Net模型,使用的数据集名称未具体提及,但结果显示模型具有优异的性能。