analiza aiqbench
This research extends Dirichlet Prior Augmentation (DirPA) to a multi-country European Union dataset, validating its ability to stabilize few-shot learning models under severe class imbalance in real-world agricultural monitoring. By proactively simulating prior distributions during training, the method effectively bridges the gap between artificially balanced datasets and long-tailed natural environments without relying on large-scale data collection.
DirPA: Addressing Prior Shift in Imbalanced Few-shot Crop-type Classification
arXiv:2603.12905v2 Announce Type: replace 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.
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.
Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2603.12905 [cs.LG]
(or arXiv:2603.12905v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2603.12905 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 270 cuvinte
Subiecte conexe
Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification
arXiv · 24 aug. 2026
Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs
arXiv · 8 iun. 2026
Learning When to Recur: Token-Adaptive Recursion for Imbalanced Ophthalmic Domain Incremental Learning
arXiv · 30 sept. 2026
I Did This Without Your Knowledge
LessWrong · 17 oct. 2026