LKASeg:Remote-Sensing Image Semantic Segmentation with Large Kernel Attention and Full-Scale Skip Connections

TL;DR

This paper introduces LKASeg, a novel remote sensing image segmentation network that combines large kernel attention and full-scale skip connections to improve global feature extraction and fusion, outperforming existing methods.

Contribution

LKASeg uniquely integrates Large Kernel Attention and Full-Scale Skip Connections for enhanced remote sensing image segmentation.

Findings

Achieved 90.33% mF1 score on ISPRS Vaihingen dataset.

Achieved 82.77% mIoU on ISPRS Vaihingen dataset.

Demonstrated improved global feature extraction and fusion.

Abstract

Semantic segmentation of remote sensing images is a fundamental task in geospatial research. However, widely used Convolutional Neural Networks (CNNs) and Transformers have notable drawbacks: CNNs may be limited by insufficient remote sensing modeling capability, while Transformers face challenges due to computational complexity. In this paper, we propose a remote-sensing image semantic segmentation network named LKASeg, which combines Large Kernel Attention(LSKA) and Full-Scale Skip Connections(FSC). Specifically, we propose a decoder based on Large Kernel Attention (LKA), which extract global features while avoiding the computational overhead of self-attention and providing channel adaptability. To achieve full-scale feature learning and fusion, we apply Full-Scale Skip Connections (FSC) between the encoder and decoder. We conducted experiments by combining the LKA-based decoder with FSC. On the ISPRS Vaihingen dataset, the mF1 and mIoU scores achieved 90.33% and 82.77%.