Activation Regression for Continuous Domain Generalization with Applications to Crop Classification
This addresses domain generalization for crop classification in satellite imagery, offering an incremental improvement with a simple-yet-effective method.
The paper tackles geographic variance in satellite imagery by modeling it as a continuous domain adaptation problem, using climate variables and feature regression to improve crop classification, achieving improved generalizability across the continental United States.
Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions. In this paper, we model geographic generalisation in medium resolution Landsat-8 satellite imagery as a continuous domain adaptation problem, demonstrating how models generalise better with appropriate domain knowledge. We develop a dataset spatially distributed across the entire continental United States, providing macroscopic insight into the effects of geography on crop classification in multi-spectral and temporally distributed satellite imagery. Our method demonstrates improved generalisability from 1) passing geographically correlated climate variables along with the satellite data to a Transformer model and 2) regressing on the model features to reconstruct these domain variables. Combined, we provide a novel perspective on geographic generalisation in satellite imagery and a simple-yet-effective approach to leverage domain knowledge. Code is available at: \url{https://github.com/samar-khanna/cropmap}