Multi-modal, multi-scale representation learning for satellite imagery analysis just needs a good ALiBi
For researchers in satellite imagery analysis, this work provides a novel attention mechanism that handles multiple spatial resolutions and modalities, though improvements are incremental.
The paper introduces Scale-ALiBi, a linear bias attention mechanism for multi-scale, multi-modal satellite imagery, achieving improved performance on the GEO-Bench benchmark.
Vision foundation models have been shown to be effective at processing satellite imagery into representations fit for downstream tasks, however, creating models which operate over multiple spatial resolutions and modes is challenging. This paper presents Scale-ALiBi, a linear bias transformer attention mechanism with a spatial encoding bias to relationships between image patches at different ground sample distance scales. We provide an implementation of Scale-ALiBi over a dataset of aligned high- and low-resolution optical and low-resolution SAR satellite imagery data using a triple-contrastive and reconstructive architecture, show an improvement on the GEO-Bench benchmark, and release the newly curated dataset publicly.