通过精确实时特征融合，提升遥感变化检测的精度与鲁棒性。
Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection
- 设计通道级时序差异融合块，捕捉像素级变化细节。
- 在三个数据集上实现更高精度、召回率与交并比，最优达98.7% IoU。
- 适合需要高精度变化检测的环境监测与城市规划场景。
遥感变化检测对监测环境与城市发展至关重要，但面临人工特征提取困难及对噪声敏感等问题。传统方法和早期深度学习模型（如卷积神经网络）难以捕捉复杂场景中长距离依赖与全局上下文信息。尽管基于Transformer的模型缓解了这些问题，其计算开销限制了在高分辨率遥感图像中的应用。本文在ChangeMamba架构基础上，提出精确实时特征融合模块，以捕获通道级时序变化与像素级差异，实现细粒度变化检测。同时，引入轻量级通道缩减机制的增强解码器，以极低计算成本保留局部细节。此外，结合交叉熵、Dice与Lovasz损失的优化损失函数，有效应对类别不平衡问题，提升交并比（IoU）。在SYSU-CD、LEVIR-CD+和WHU-CD数据集上的评估表明，该方法在精确率、召回率、F1分数、IoU和总体准确率方面均优于现有最先进方法，验证了其在遥感变化检测中的鲁棒性。代码与预训练模型已公开于https://github.com/Buddhi19/MambaCD.git。
原文摘要 · Abstract (English)
Remote sensing change detection is vital for monitoring environmental and urban transformations but faces challenges like manual feature extraction and sensitivity to noise. Traditional methods and early deep learning models, such as convolutional neural networks (CNNs), struggle to capture long-range dependencies and global context essential for accurate change detection in complex scenes. While Transformer-based models mitigate these issues, their computational complexity limits their applicability in high-resolution remote sensing. Building upon ChangeMamba architecture, which leverages state space models for efficient global context modeling, this paper proposes precision fusion blocks to capture channel-wise temporal variations and per-pixel differences for fine-grained change detection. An enhanced decoder pipeline, incorporating lightweight channel reduction mechanisms, preserves local details with minimal computational cost. Additionally, an optimized loss function combining Cross Entropy, Dice and Lovasz objectives addresses class imbalance and boosts Intersection-over-Union (IoU). Evaluations on SYSU-CD, LEVIR-CD+, and WHU-CD datasets demonstrate superior precision, recall, F1 score, IoU, and overall accuracy compared to state-of-the-art methods, highlighting the approach's robustness for remote sensing change detection. For complete transparency, the codes and pretrained models are accessible at https://github.com/Buddhi19/MambaCD.git
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。