Multistage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images
Multistage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images
复制标题
DOI：
10.1109/lgrs.2021.3063381
复制
发表时间：
2020-11
影响因子：
4.8
通讯作者：
Rui Li-;Jianlin Su;Chenxi Duan;Shunyi Zheng
中科院分区：
文献类型：
--
作者：
Rui Li-;Jianlin Su;Chenxi Duan;Shunyi Zheng
注意机制可以对提取的特征图进行细化，提高深度网络的分类性能，已成为计算机视觉和自然语言处理中的一项重要技术。然而，点积注意机制的内存和计算成本随着输入的时空大小呈二次增长。这种增长在具有大规模输入的应用场景中极大地阻碍了注意机制的使用。在这封信中，我们提出了一种线性注意机制（LAM）来解决这个问题，它近似等同于计算效率的点积注意。这样的设计使得注意力机制和深度网络之间的结合更加灵活和通用。在此基础上，对原始U-Net中的跳过连接进行重构，设计了一种多阶段注意力重构网络（MAResU-Net），用于精细分辨率遥感图像的语义分割。在Vaihingen数据集上进行的实验证明了我们的MAResU-Net的有效性和效率。我们的代码可在https://github.com/lironui/MAResU-Net上获得。
The attention mechanism can refine the extracted feature maps and boost the classification performance of the deep network, which has become an essential technique in computer vision and natural language processing. However, the memory and computational costs of the dot-product attention mechanism increase quadratically with the spatiotemporal size of the input. Such growth hinders the usage of attention mechanisms considerably in application scenarios with large-scale inputs. In this letter, we propose a linear attention mechanism (LAM) to address this issue, which is approximately equivalent to dot-product attention with computational efficiency. Such a design makes the incorporation between attention mechanisms and deep networks much more flexible and versatile. Based on the proposed LAM, we refactor the skip connections in the raw U-Net and design a multistage attention ResU-Net (MAResU-Net) for semantic segmentation from fine-resolution remote sensing images. Experiments conducted on the Vaihingen data set demonstrated the effectiveness and efficiency of our MAResU-Net. Our code is available at https://github.com/lironui/MAResU-Net.