面向地球观测变化检测的全面可信AI方法基准测试

中文摘要 AI 辅助

地球观测（EO）中的变化检测对监测地表变化至关重要，但该领域近期研究受限于评估协议不一致，且仅关注预测准确率而未考虑计算效率。为解决此问题，我们提出一种标准化、开源的基准测试，用于评估地球观测变化检测的最新（SOTA）深度学习方法。我们对10种代表性模型架构（从卷积网络（CNNs）到视觉Transformer（ViTs））在10种异构变化检测数据集上开展全面分析，采用相同实验协议严格评估这些模型，对比从头训练的模型与利用预训练权重的模型。此外，我们同步评估预测性能与计算效率，包括参数数量和推理延迟。研究发现，若考虑计算效率，优化良好的经典架构（如孪生U-Net）常优于更复杂的现代模型；且预训练始终能带来显著性能提升，无额外推理成本。为确保完全透明与可复现，所有实验资源（含标准化数据划分、训练脚本、训练日志及模型检查点）均公开提供，并符合FAIR原则（可发现、可访问、可互操作、可重用）。

英文摘要

Change detection in Earth observation (EO) is critical for monitoring land surface transformations, yet recent research in the field is constrained by inconsistent evaluation protocols and a narrow focus on predictive accuracy without regard for computational efficiency. To address this, we present a standardized, open-source benchmark for evaluating state-of-the-art (SOTA) deep learning methods for Earth observation change detection. We conduct a comprehensive analysis of ten representative model architectures, ranging from convolutional networks (CNNs) to vision transformers (ViTs), across ten heterogeneous change detection datasets. We rigorously evaluate these models with identical experimental protocols, comparing models trained from scratch against those utilizing pre-trained weights. Furthermore, we evaluate predictive performance alongside computational efficiency, including parameter counts and inference latency. Our findings reveal that well-optimized classical architectures, such as Siamese U-Nets, frequently outperform more complex contemporary models when computational efficiency is factored in, and that pre-training consistently provides a significant performance boost with no additional inference cost. To ensure complete transparency and reproducibility, all experimental resources, including standardized data splits, training scripts, training logs, and model checkpoints are publicly available and adhere to FAIR principles (Findable, Accessible, Interoperable, and Reusable).

发表机构

• Bias Variance Labs, d.o.o.（Bias Variance Labs有限责任公司）
• University of Ljubljana（卢布尔雅那大学）
• Jožef Stefan Institute（约热夫·斯泰凡研究所）
• Télécom Paris（巴黎电信学院）
• Institut Polytechnique de Paris（巴黎综合理工学院）

机构由 AI 辅助整理，请以论文原文为准。