Landsat-Bench: Datasets and Benchmarks for Landsat Foundation Models
This addresses a bottleneck for researchers developing foundation models in remote sensing by providing standardized benchmarks, though it is incremental as it adapts existing datasets.
The paper tackles the lack of benchmarks for Landsat-based Geospatial Foundation Models by introducing Landsat-Bench, a suite of three adapted benchmarks with standardized evaluation methods, and shows that pretrained models on SSL4EO-L achieve performance gains of +4% OA and +5.1% mAP on specific tasks compared to ImageNet.
The Landsat program offers over 50 years of globally consistent Earth imagery. However, the lack of benchmarks for this data constrains progress towards Landsat-based Geospatial Foundation Models (GFM). In this paper, we introduce Landsat-Bench, a suite of three benchmarks with Landsat imagery that adapt from existing remote sensing datasets -- EuroSAT-L, BigEarthNet-L, and LC100-L. We establish baseline and standardized evaluation methods across both common architectures and Landsat foundation models pretrained on the SSL4EO-L dataset. Notably, we provide evidence that SSL4EO-L pretrained GFMs extract better representations for downstream tasks in comparison to ImageNet, including performance gains of +4% OA and +5.1% mAP on EuroSAT-L and BigEarthNet-L.