Activation Regression for Continuous Domain Generalization with Applications to Crop Classification [article]

Samar Khanna, Bram Wallace, Kavita Bala, Bharath Hariharan
2022 arXiv   pre-print
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
more » ... fication 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:
arXiv:2204.07030v1 fatcat:kbu5fnyd45gmjnhdux5jl45rp4