Embeddings based Anomaly Detection for Cleaning Global Crop Type Reference Datasets
作者: Syed Roshaan Ali Shah, Kristof Van Tricht, Christina Butsko, Jeroen Degerickx, Zoltan Szantoi
分类: cs.CV
发布日期: 2026-07-27
💡 一句话要点
提出基于嵌入的异常检测以清理全球作物类型参考数据集
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 异常检测 作物类型映射 地球观测 数据清理 嵌入学习 模型训练 农业监测
📋 核心要点
- 现有作物类型映射方法面临高质量参考数据不足的问题，数据来源多样且存在偏差与噪声。
- 本文提出了一种基于嵌入的异常检测框架，利用预训练的地球观测编码器对数据进行清理。
- 实验结果显示，清理异常数据后，模型在作物类型和土地覆盖的准确性上均有所提升，AUROC达到0.84。
📝 摘要（中文）
高质量的参考数据是作物类型映射的关键瓶颈。现有系统如WorldCereal从不同来源聚合标签，存在偏差和噪声。本文提出了一种基于预训练地球观测编码器的嵌入式异常检测框架，通过对同一区域内相同作物的样本进行评分，识别并处理异常数据。实验表明，清理后的数据显著提高了作物类型模型的准确性，尤其在五个宏观区域的评估中表现突出。
🔬 方法详解
问题定义：本文旨在解决作物类型参考数据集中存在的标签错误和位置错误问题。现有方法无法有效处理来自不同来源的数据噪声和偏差。
核心思路：提出基于嵌入的异常检测框架，通过对同一区域内相同作物样本的嵌入进行比较，识别出异常样本并进行清理，以提高模型的准确性。
技术框架：该框架包括数据预处理、嵌入生成、异常检测和模型训练四个主要模块。首先，利用预训练的地球观测编码器生成样本的嵌入，然后通过比较相似样本进行异常检测，最后在清理后的数据上训练模型。
关键创新：最重要的创新在于提出了一种实用的、基于嵌入的异常检测方法，能够有效识别和清理标签错误，显著提高模型性能。与传统方法相比，该方法更具局部性和适应性。
关键设计：在设计中，采用了预训练的嵌入模型，设置了合理的阈值来判断异常样本，并通过实验验证了清理策略的有效性。
🖼️ 关键图片
📊 实验亮点
实验结果显示，检测器在合成真值数据上能够将标签错误的检测率提高2.5-5倍，AUROC达到0.84。在真实数据上，清理后的模型在作物类型和土地覆盖的准确性上均有显著提升，验证了该方法的有效性。
🎯 应用场景
该研究的潜在应用领域包括农业监测、环境保护和土地管理等。通过清理作物类型参考数据集，可以提高作物监测系统的准确性和可靠性，进而支持更有效的农业决策和资源管理。
📄 摘要（原文）
High quality reference data remain a critical bottleneck for crop-type mapping at any spatial and temporal scale. Operational systems such as WorldCereal aggregate labels from heterogeneous sources such as parcel registers, national databases, field surveys, and map-derived products, each with their own biases, coverage gaps and unknown label noise. Simple global rules are inadequate, since crop phenology and observation conditions vary strongly across regions and seasons. In this study, we focus on a single, operationally relevant question: whether embeddings produced through geospatial foundation models are a viable basis for cleaning the reference data. We propose a practical, locality-aware, embedding-based anomaly (EBA) detection framework that operates on the embeddings of a pretrained Earth-observation encoder. We score each labelled sample against other samples of the same crop in the same area using a pretrained embedding, flag the ones that stand out, and test whether removing or down-weighting them before training yields a better model. We establish that the flagged points are genuinely mislabelled or misplaced in two independent ways: against synthetic ground truth, the detector concentrates injected label errors 2.5-5x above chance in its flagged set (detection AUROC up to 0.84); and on real data, a model-independent test shows that removing or confidence-weighting the flagged held-out points raises measured accuracy in trained models, for both crop type and land cover. Acting on the flags then improves the WorldCereal crop-type model across five macro-regions, evaluated on a fixed held-out split under three views. We find conservative cleaning helps while over-cleaning hurts. The EBA detector approach is designed to be reproducible and extensible, and can serve as a template for cleaning large, noisy Earth observation reference datasets beyond crop mapping.