Disentangling Hardness from Noise: An Uncertainty-Driven Model-Agnostic Framework for Long-Tailed Remote Sensing Classification

2026-01-01

arXiv.org

AI Summary

This work addresses the challenge of distinguishing hard examples from noisy samples in long-tailed remote sensing classification by proposing DUAL, a model-agnostic, uncertainty-aware framework. Leveraging evidential deep learning, DUAL is the first to explicitly disentangle epistemic uncertainty (EU) and aleatoric uncertainty (AU) in remote sensing scenarios: EU adaptively reweights hard samples from the tail classes, while AU mitigates noise effects through label smoothing. Notably, DUAL requires no modification to the backbone network and consistently outperforms strong baselines such as TGN and SADE across multiple remote sensing datasets and backbone architectures, demonstrating its effectiveness and generalization capability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Remote Sensing / Geospatial AI
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

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.

Problem

• long-tailed classification
• remote sensing
• noise disentanglement
• hard samples
• uncertainty

Innovation

• Uncertainty Disentanglement
• Long-Tailed Classification
• Remote Sensing
• Evidential Deep Learning
• Model-Agnostic Framework