Salvato in:
Dettagli Bibliografici
Autori principali: Reuss, Joana, Gikalo, Ekaterina, Körner, Marco
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.16218
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911277393117184
author Reuss, Joana
Gikalo, Ekaterina
Körner, Marco
author_facet Reuss, Joana
Gikalo, Ekaterina
Körner, Marco
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16218
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mind the Gap: Bridging Prior Shift in Realistic Few-Shot Crop-Type Classification
Reuss, Joana
Gikalo, Ekaterina
Körner, Marco
Machine Learning
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.
title Mind the Gap: Bridging Prior Shift in Realistic Few-Shot Crop-Type Classification
topic Machine Learning
url https://arxiv.org/abs/2511.16218