Mind the Gap: Bridging Prior Shift in Realistic Few-Shot Crop-Type Classification
This addresses a domain-specific issue for agricultural AI applications, offering an incremental improvement by mitigating prior shift in few-shot learning.
The paper tackled the problem of label distribution mismatch between artificially balanced training sets and real-world long-tailed distributions in few-shot crop-type classification, proposing Dirichlet Prior Augmentation (DirPA) to simulate unknown skews and improve generalization.
Real-world agricultural distributions often suffer from severe class imbalance, typically following a long-tailed distribution. Labeled datasets for crop-type classification are inherently scarce and remain costly to obtain. When working with such limited data, training sets are frequently constructed to be artificially balanced -- in particular in the case of few-shot learning -- failing to reflect real-world conditions. This mismatch induces a shift between training and test label distributions, degrading real-world generalization. To address this, we propose Dirichlet Prior Augmentation (DirPA), a novel method that simulates an unknown label distribution skew of the target domain proactively during model training. Specifically, we model the real-world distribution as Dirichlet-distributed random variables, effectively performing a prior augmentation during few-shot learning. Our experiments show that DirPA successfully shifts the decision boundary and stabilizes the training process by acting as a dynamic feature regularizer.