提出线性复杂度2D注意力机制，提升遥感图像处理效率与精度
RSRWKV: A Linear-Complexity 2D Attention Mechanism for Efficient Remote Sensing Vision Task
- 设计2D-WKV扫描机制，实现二维空间上下文建模且保持线性计算复杂度
- 在多个遥感数据集上优于CNN和Transformer基线，分类准确率最高提升3.2%
- 适合高分辨率遥感图像的分类、检测与分割任务，尤其关注效率与全局建模
高分辨率遥感分析面临场景复杂性和尺度多样性带来的全局上下文建模挑战。尽管卷积神经网络（CNN）通过参数共享擅长局部特征提取，但其固定感受野限制了长距离依赖建模。视觉变换器（ViTs）虽能通过自注意力机制捕捉全局语义关系，但其计算复杂度随图像分辨率呈二次增长，对高分辨率影像造成严重效率瓶颈。RWKV模型虽在自然语言处理中实现线性序列建模突破，但其一维扫描机制在视觉任务中存在方向性局限。为此，我们提出RSRWKV，引入新型2D-WKV扫描机制，融合序列处理与二维空间推理能力，同时保持线性复杂度，实现多方向各向同性上下文聚合。MVC-Shift模块增强多尺度感受野覆盖，ECA模块强化跨通道特征交互与语义显著性建模。实验表明，RSRWKV在NWPU RESISC45、VHR-10.v2和GLH-Water数据集上的分类、检测与分割任务中均显著优于CNN和Transformer基线，为高分辨率遥感分析提供可扩展解决方案。
原文摘要 · Abstract (English)
High-resolution remote sensing analysis faces challenges in global context modeling due to scene complexity and scale diversity. While CNNs excel at local feature extraction via parameter sharing, their fixed receptive fields fundamentally restrict long-range dependency modeling. Vision Transformers (ViTs) effectively capture global semantic relationships through self-attention mechanisms but suffer from quadratic computational complexity relative to image resolution, creating critical efficiency bottlenecks for high-resolution imagery. The RWKV model's linear-complexity sequence modeling achieves breakthroughs in NLP but exhibits anisotropic limitations in vision tasks due to its 1D scanning mechanism. To address these challenges, we propose RSRWKV, featuring a novel 2D-WKV scanning mechanism that bridges sequential processing and 2D spatial reasoning while maintaining linear complexity. This enables isotropic context aggregation across multiple directions. The MVC-Shift module enhances multi-scale receptive field coverage, while the ECA module strengthens cross-channel feature interaction and semantic saliency modeling. Experimental results demonstrate RSRWKV's superior performance over CNN and Transformer baselines in classification, detection, and segmentation tasks on NWPU RESISC45, VHR-10.v2, and GLH-Water datasets, offering a scalable solution for high-resolution remote sensing analysis.
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。