提出SCA注意力模块，提升遥感图像中建筑轮廓提取精度
SCANet: Split Coordinate Attention Network for Building Footprint Extraction
- 用双空间池化捕捉远距离空间关系，分通道编码x/y方向特征
- 在WHU和麻省数据集上分别达91.61%和75.49%的IoU，优于当前最优方法
- 可插拔设计，适合需要高精度建筑轮廓提取的研究与应用
建筑轮廓提取在遥感图像分析中具有重要意义，广泛应用于城市规划、土地利用、环境监测和灾害评估。尽管传统方法与深度学习方法已取得进展，但仍面临诸多挑战。本文提出一种新型可插拔注意力模块——分割坐标注意力（Split Coordinate Attention, SCA），通过采用两个空间范围的池化核，分别沿x和y平面编码各通道特征，并对每组特征进行分段操作，有效捕捉远程空间交互，实现更高效的语义特征提取。将SCA嵌入2D CNN构建SCANet，在公开的武汉大学（WHU）建筑数据集和麻省建筑数据集上，各项指标均超越近期最先进方法。特别地，SCANet在两个数据集上的交并比（IoU）分别达到91.61%和75.49%。代码已开源：https://github.com/AiEson/SCANet。
原文摘要 · Abstract (English)
Building footprint extraction holds immense significance in remote sensing image analysis and has great value in urban planning, land use, environmental protection and disaster assessment. Despite the progress made by conventional and deep learning approaches in this field, they continue to encounter significant challenges. This paper introduces a novel plug-and-play attention module, Split Coordinate Attention (SCA), which ingeniously captures spatially remote interactions by employing two spatial range of pooling kernels, strategically encoding each channel along x and y planes, and separately performs a series of split operations for each feature group, thus enabling more efficient semantic feature extraction. By inserting into a 2D CNN to form an effective SCANet, our SCANet outperforms recent SOTA methods on the public Wuhan University (WHU) Building Dataset and Massachusetts Building Dataset in terms of various metrics. Particularly SCANet achieves the best IoU, 91.61% and 75.49% for the two datasets. Our code is available at https://github.com/AiEson/SCANet
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。