Multistage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images

By Jianlin Su, Chenxi Duan, Shunyi Zheng. IEEE Geoscience and Remote Sensing Letters, 2020

302 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/e3834cb7f77edfdd7ce0ea210ef71d256e006d48

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery (2021, unknown): “(Li et al., 2021c) but also outperform recent Transformer-based lightweight networks, such as Segmenter (Strudel et al., 2021) and BANet (Wang et al., 2021b).”
MARE: Self-Supervised Multi-Attention REsu-Net for Semantic Segmentation in Remote Sensing (2021, methodology): “Particularly, we decided to train the encoder of the Multistage Attention ResU-Net (MAResU-Net), that is a ResNet-18 [19], with the Online Bag of Words (OBoW) method, given its high capability of learning visual representations, that are effective for several downstream task.”
CMTFNet: CNN and Multiscale Transformer Fusion Network for Remote-Sensing Image Semantic Segmentation (2023, background): “Li et al. [36] designed a multistage attention reconstruction network (MAResU-Net), where long-range dependencies are established by adding a linear attention mechanism (LAM) to the skip connections of the original UNet.”
A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images (2021, methodology): “The detailed information about our previous work on attention mechanism can be referred to [17].”
A Multilevel Multimodal Fusion Transformer for Remote Sensing Semantic Segmentation (2024, methodology): “…benchmarked the performance of the proposed FTransUNet against twelve representative state-of-the-art methods, namely ABCNet [61], PSPNet [62], MAResU-Net [63], vFuseNet [15], FuseNet [14], ESANet [33], Tran-sUNet [31], SA-GATE [64], UNetFormer [44], CMFNet [19], MFTransNet [59], and CMGFNet [47].”