Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images

TL;DR

This paper introduces MANet, a multi-attention network with a novel kernel attention mechanism, significantly improving semantic segmentation accuracy on high-resolution remote sensing images by efficiently modeling long-range dependencies.

Contribution

The paper proposes a new multi-attention network with a kernel attention mechanism that reduces computational complexity and enhances feature representation for remote sensing image segmentation.

Findings

MANet outperforms existing methods like DeepLab V3+ and PSPNet on large-scale remote sensing datasets.

Kernel attention reduces computational cost while maintaining high accuracy.

Integration of local and global features improves segmentation performance.

Abstract

Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning. Although the accuracy of semantic segmentation in remote sensing images has been increased significantly by deep convolutional neural networks, several limitations exist in standard models. First, for encoder-decoder architectures such as U-Net, the utilization of multi-scale features causes the underuse of information, where low-level features and high-level features are concatenated directly without any refinement. Second, long-range dependencies of feature maps are insufficiently explored, resulting in sub-optimal feature representations associated with each semantic class. Third, even though the dot-product attention mechanism has been introduced and utilized in semantic segmentation to model long-range dependencies, the large time and space demands of attention impede the actual usage of attention in application scenarios with large-scale input. This paper proposed a Multi-Attention-Network (MANet) to address these issues by extracting contextual dependencies through multiple efficient attention modules. A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention. Based on kernel attention and channel attention, we integrate local feature maps extracted by ResNeXt-101 with their corresponding global dependencies and reweight interdependent channel maps adaptively. Numerical experiments on three large-scale fine resolution remote sensing images captured by different satellite sensors demonstrate the superior performance of the proposed MANet, outperforming the DeepLab V3+, PSPNet, FastFCN, DANet, OCRNet, and other benchmark approaches.