用基础模型自动修复遥感土地利用图的噪声标签
SAModified: A Foundation Model-Based Zero-Shot Approach for Refining Noisy Land-Use Land-Cover Maps
- 基于SAM模型分割地块，按局部标签统计重标不确定像素
- 使下游分割模型性能提升约5%
- 无需标注即可处理不同地理区域，适合遥感数据清洗
土地利用与土地覆盖（LULC）分析在遥感中至关重要，广泛应用于农业、公共事业和城市规划等领域。然而，由于标签噪声，机器学习自动化生成LULC地图面临挑战。现有真实标签（如ESRI LULC、MapBioMass）常含噪声，影响模型学习精度，并扭曲评估指标。传统方法依赖无监督算法修正模糊标签，但存在可扩展性差、跨区域泛化能力弱的问题。为此，我们提出一种基于基础模型Segment Anything Model（SAM）的零样本方法：自动分割土地区块，利用每个区域内的局部标签统计信息重标不确定像素。实验表明，该方法显著降低标签噪声，使用去噪后标签训练的下游分割模型性能提升约5%。
原文摘要 · Abstract (English)
Land-use and land cover (LULC) analysis is critical in remote sensing, with wide-ranging applications across diverse fields such as agriculture, utilities, and urban planning. However, automating LULC map generation using machine learning is rendered challenging due to noisy labels. Typically, the ground truths (e.g. ESRI LULC, MapBioMass) have noisy labels that hamper the model's ability to learn to accurately classify the pixels. Further, these erroneous labels can significantly distort the performance metrics of a model, leading to misleading evaluations. Traditionally, the ambiguous labels are rectified using unsupervised algorithms. These algorithms struggle not only with scalability but also with generalization across different geographies. To overcome these challenges, we propose a zero-shot approach using the foundation model, Segment Anything Model (SAM), to automatically delineate different land parcels/regions and leverage them to relabel the unsure pixels by using the local label statistics within each detected region. We achieve a significant reduction in label noise and an improvement in the performance of the downstream segmentation model by $\approx 5\%$ when trained with denoised labels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。