CGEarthEye:A High-Resolution Remote Sensing Vision Foundation Model Based on the Jilin-1 Satellite Constellation

TL;DR

CGEarthEye is a high-resolution remote sensing foundation model based on the Jilin-1 satellite constellation, utilizing self-supervised learning and multiple backbones to achieve state-of-the-art performance across various Earth Observation tasks.

Contribution

The paper introduces CGEarthEye, the first RSVFM tailored for Jilin-1 data, with a novel multi-temporal SSL dataset and multiple pre-training strategies, advancing high-resolution remote sensing modeling.

Findings

Achieves SOTA performance on 10 benchmark datasets

Demonstrates superior feature visualization and model convergence

Enhances practical mapping applications with high-resolution data

Abstract

Deep learning methods have significantly advanced the development of intelligent rinterpretation in remote sensing (RS), with foundational model research based on large-scale pre-training paradigms rapidly reshaping various domains of Earth Observation (EO). However, compared to the open accessibility and high spatiotemporal coverage of medium-resolution data, the limited acquisition channels for ultra-high-resolution optical RS imagery have constrained the progress of high-resolution remote sensing vision foundation models (RSVFM). As the world's largest sub-meter-level commercial RS satellite constellation, the Jilin-1 constellation possesses abundant sub-meter-level image resources. This study proposes CGEarthEye, a RSVFM framework specifically designed for Jilin-1 satellite characteristics, comprising five backbones with different parameter scales with totaling 2.1 billion parameters. To enhance the representational capacity of the foundation model, we developed JLSSD, the first 15-million-scale multi-temporal self-supervised learning (SSL) dataset featuring global coverage with quarterly temporal sampling within a single year, constructed through multi-level representation clustering and sampling strategies. The framework integrates seasonal contrast, augmentation-based contrast, and masked patch token contrastive strategies for pre-training. Comprehensive evaluations across 10 benchmark datasets covering four typical RS tasks demonstrate that the CGEarthEye consistently achieves state-of-the-art (SOTA) performance. Further analysis reveals CGEarthEye's superior characteristics in feature visualization, model convergence, parameter efficiency, and practical mapping applications. This study anticipates that the exceptional representation capabilities of CGEarthEye will facilitate broader and more efficient applications of Jilin-1 data in traditional EO application.