Long-Tailed distributions are pervasive in remote sensing due to the inherently imbalanced occurrence of grounded objects. However, a critical challenge remains largely overlooked, i.e., disentangling hard tail data samples from noisy ambiguous ones. Conventional methods often indiscriminately emphasize all low-confidence samples, leading to overfitting on noisy data. To bridge this gap, building upon Evidential Deep Learning, we propose a model-agnostic uncertainty-aware framework termed DUAL, which dynamically disentangles prediction uncertainty into Epistemic Uncertainty (EU) and Aleatoric Uncertainty (AU). Specifically, we introduce EU as an indicator of sample scarcity to guide a reweighting strategy for hard-to-learn tail samples, while leveraging AU to quantify data ambiguity, employing an adaptive label smoothing mechanism to suppress the impact of noise. Extensive experiments on multiple datasets across various backbones demonstrate the effectiveness and generalization of our framework, surpassing strong baselines such as TGN and SADE. Ablation studies provide further insights into the crucial choices of our design.

翻译：长尾分布因地面物体固有的不平衡出现而在遥感领域普遍存在。然而，一个关键挑战在很大程度上被忽视，即如何将困难的尾部数据样本与模糊的噪声样本区分开来。传统方法往往不加区分地强调所有低置信度样本，导致对噪声数据的过拟合。为弥补这一差距，我们在证据深度学习的基础上，提出了一种模型无关的不确定性感知框架，称为DUAL，该框架动态地将预测不确定性解耦为认知不确定性（EU）和偶然不确定性（AU）。具体而言，我们引入EU作为样本稀缺性的指标，以指导针对难学习的尾部样本的重新加权策略，同时利用AU来量化数据模糊性，采用自适应标签平滑机制来抑制噪声的影响。在多种骨干网络和多个数据集上的大量实验证明了我们框架的有效性和泛化能力，其性能超越了TGN和SADE等强基线。消融研究进一步揭示了设计中关键选择的重要性。