轻量级模型解决遥感图像空间与通道冗余问题
LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attention
- 用聚焦显著区域的TGFI模块减少空间冗余
- 通过分组注意力机制实现多尺度通道高效处理
- 在12个遥感数据集上兼具高精度与低计算开销
面向遥感视觉分析的轻量级神经网络需克服两大固有冗余：广阔均质背景带来的空间冗余，以及极端尺度变化导致的通道冗余。现有模型多为自然图像设计，难以应对遥感场景下的双重挑战。为此，我们提出LWGANet，一种专为遥感特性优化的轻量级主干网络。该模型引入两项核心创新：顶部K个全局特征交互（TGFI）模块，通过聚焦显著区域降低空间冗余；轻量级分组注意力（LWGA）模块，将通道划分为特定尺度的专用路径以缓解通道冗余。二者协同提升特征表示质量与计算效率。在涵盖四类主要遥感任务（场景分类、定向目标检测、语义分割、变化检测）的十二个不同数据集上，实验表明LWGANet在准确率与效率之间均优于当前最优轻量级主干网络，建立了遥感图像高效视觉分析的新基准。
原文摘要 · Abstract (English)
Light-weight neural networks for remote sensing (RS) visual analysis must overcome two inherent redundancies: spatial redundancy from vast, homogeneous backgrounds, and channel redundancy, where extreme scale variations render a single feature space inefficient. Existing models, often designed for natural images, fail to address this dual challenge in RS scenarios. To bridge this gap, we propose LWGANet, a light-weight backbone engineered for RS-specific properties. LWGANet introduces two core innovations: a Top-K Global Feature Interaction (TGFI) module that mitigates spatial redundancy by focusing computation on salient regions, and a Light-Weight Grouped Attention (LWGA) module that resolves channel redundancy by partitioning channels into specialized, scale-specific pathways. By synergistically resolving these core inefficiencies, LWGANet achieves a superior trade-off between feature representation quality and computational cost. Extensive experiments on twelve diverse datasets across four major RS tasks--scene classification, oriented object detection, semantic segmentation, and change detection--demonstrate that LWGANet consistently outperforms state-of-the-art light-weight backbones in both accuracy and efficiency. Our work establishes a new, robust baseline for efficient visual analysis in RS images.
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。