用大核注意力与全尺度跳跃连接提升遥感图像分割精度
LKASeg:Remote-Sensing Image Semantic Segmentation with Large Kernel Attention and Full-Scale Skip Connections
- 引入大核注意力模块，高效捕获全局特征
- 在Vaihingen数据集上达90.33% mF1和82.77% mIoU
- 适合需要高精度遥感分割的应用场景
遥感图像语义分割是地理空间研究的基础任务。然而，广泛使用的卷积神经网络（CNN）在建模能力上存在局限，而变换器（Transformer）则面临计算复杂度高的问题。本文提出一种名为LKASeg的遥感图像语义分割网络，融合大核注意力（LSKA）与全尺度跳跃连接（FSC）。具体而言，设计基于大核注意力（LKA）的解码器，可在避免自注意力计算开销的同时提取全局特征，并具备通道自适应能力。为实现全尺度特征学习与融合，在编码器与解码器间引入全尺度跳跃连接（FSC）。实验表明，将基于LKA的解码器与FSC结合后，在ISPRS Vaihingen数据集上达到90.33%的mF1和82.77%的mIoU。
原文摘要 · Abstract (English)
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%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。