UAGLNet：基于合作CNN-Transformer的不确定性聚合全局-局部融合网络用于建筑物提取
UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction
AI总结：
UAGLNet通过合作CNN-Transformer架构和不确定性聚合解码器，提升遥感图像中建筑物提取的准确性和鲁棒性。
摘要：
从遥感图像中提取建筑物是一项具有挑战性的任务，由于建筑物的复杂结构变化。现有方法采用卷积或自注意力块来捕捉分割模型中的多尺度特征，但特征金字塔的固有差距和局部-全局特征整合不足导致提取结果不准确且模糊。为了解决这个问题，本文提出了一种不确定性聚合全局-局部融合网络（UAGLNet），该网络能够在不确定性建模的指导下利用高质量的全局-局部视觉语义。具体来说，我们提出了一种新的合作编码器，它在不同阶段采用混合CNN和Transformer层来分别捕捉局部和全局视觉语义。一个中间合作交互块（CIB）被设计用来缩小网络变深时局部和全局特征之间的差距。随后，我们提出了一种全局-局部融合（GLF）模块来互补融合全局和局部表示。此外，为了减轻不确定区域的分割模糊性，我们提出了一种不确定性聚合解码器（UAD）来明确估计像素级不确定性以提高分割精度。大量实验表明，我们的方法在其他最先进的方法上实现了优越的性能。我们的代码可在https://github.com/Dstate/UAGLNet上获得。
英文摘要：
Building extraction from remote sensing images is a challenging task due to the complex structure variations of the buildings. Existing methods employ convolutional or self-attention blocks to capture the multi-scale features in the segmentation models, while the inherent gap of the feature pyramids and insufficient global-local feature integration leads to inaccurate, ambiguous extraction results. To address this issue, in this paper, we present an Uncertainty-Aggregated Global-Local Fusion Network (UAGLNet), which is capable to exploit high-quality global-local visual semantics under the guidance of uncertainty modeling. Specifically, we propose a novel cooperative encoder, which adopts hybrid CNN and transformer layers at different stages to capture the local and global visual semantics, respectively. An intermediate cooperative interaction block (CIB) is designed to narrow the gap between the local and global features when the network becomes deeper. Afterwards, we propose a Global-Local Fusion (GLF) module to complementarily fuse the global and local representations. Moreover, to mitigate the segmentation ambiguity in uncertain regions, we propose an Uncertainty-Aggregated Decoder (UAD) to explicitly estimate the pixel-wise uncertainty to enhance the segmentation accuracy. Extensive experiments demonstrate that our method achieves superior performance to other state-of-the-art methods. Our code is available at https://github.com/Dstate/UAGLNet
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
