Geospatial Foundational Embedder: Top-1 Winning Solution on EarthVision Embed2Scale Challenge (CVPR 2025)

2025/09/03 by Xu, Zirui, Tang, Raphael, Bianco, Mike +4
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2509.06993

Abstract

EarthVision Embed2Scale challenge (CVPR 2025) aims to develop foundational geospatial models to embed SSL4EO-S12 hyperspectral geospatial data cubes into embedding vectors that faciliatetes various downstream tasks, e.g., classification, regression, etc. In this technical report, we introduce our proposed method for the Top-1 winning solution on the Embed2Scale Challenge.

Citations

• SSL4EO-S12 v1.1: A Multimodal, Multiseasonal Dataset for Pretraining, Updated
• TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
• Emerging Properties in Self-Supervised Vision Transformers
• Emerging Properties in Self-Supervised Vision Transformers
• Learning Transferable Visual Models From Natural Language Supervision
• Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization

Related

• S2Vec: Self-Supervised Geospatial Embeddings
• Tile Compression and Embeddings for Multi-Label Classification in GeoLifeCLEF 2024
• GAIR: Improving Multimodal Geo-Foundation Model with Geo-Aligned Implicit Representations
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
• TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning