DirPA: Addressing Prior Shift in Imbalanced Few-shot Crop-type Classification

TL;DR

This paper introduces DirPA, a method that improves crop-type classification in agriculture by addressing distribution shifts caused by class imbalance, demonstrating robustness across multiple European regions.

Contribution

The study extends DirPA's evaluation to diverse European regions, showing its effectiveness in handling long-tailed distributions in real-world agricultural data.

Findings

DirPA enhances model robustness across different regions.

It stabilizes training under extreme class imbalance.

It improves class-specific performance by simulating priors.

Abstract

Real-world agricultural monitoring is often hampered by severe class imbalance and high label acquisition costs, resulting in significant data scarcity. In few-shot learning (FSL) -- a framework specifically designed for data-scarce settings -- , training sets are often artificially balanced. However, this creates a disconnect from the long-tailed distributions observed in nature, leading to a distribution shift that undermines the model's ability to generalize to real-world agricultural tasks. We previously introduced Dirichlet Prior Augmentation (DirPA; Reuss et al., 2026a) to proactively mitigate the effects of such label distribution skews during model training. In this work, we extend the original study's geographical scope. Specifically, we evaluate this extended approach across multiple countries in the European Union (EU), moving beyond localized experiments to test the method's resilience across diverse agricultural environments. Our results demonstrate the effectiveness of DirPA across different geographical regions. We show that DirPA not only improves system robustness and stabilizes training under extreme long-tailed distributions, regardless of the target region, but also substantially improves individual class-specific performance by proactively simulating priors.