RDNet: 用于光学遥感图像的区域比例感知动态自适应显著目标检测网络
RDNet: Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network in Optical Remote Sensing Images
AI总结：
RDNet通过引入SwinTransformer和三个关键模块，提升光学遥感图像中显著目标检测的鲁棒性和定位精度。
摘要：
在遥感图像中进行显著目标检测（SOD）面临重大挑战，因为物体尺寸变化大，自注意力机制的计算成本高，以及基于CNN的提取器在捕捉全局上下文和长距离依赖关系方面存在限制。现有依赖固定卷积核的方法难以适应多样的物体尺度，导致细节丢失或无关特征聚合。为了解决这些问题，本文旨在增强对尺度变化的鲁棒性并实现精确的目标定位。我们提出了区域比例感知动态自适应显著目标检测网络（RDNet），它用SwinTransformer取代CNN主干以进行全局上下文建模，并引入了三个关键模块：（1）动态自适应细节感知（DAD）模块，通过物体区域比例引导应用不同卷积核；（2）频率匹配上下文增强（FCE）模块，通过小波交互和注意力丰富上下文信息；（3）区域比例感知定位（RPL）模块，通过交叉注意力突出语义细节，并整合比例引导（PG）块以协助DAD模块。通过结合这些模块，RDNet实现了对尺度变化的鲁棒性和准确的定位，相较于最先进的方法，检测性能更优。
英文摘要：
Salient object detection (SOD) in remote sensing images faces significant challenges due to large variations in object sizes, the computational cost of self-attention mechanisms, and the limitations of CNN-based extractors in capturing global context and long-range dependencies. Existing methods that rely on fixed convolution kernels often struggle to adapt to diverse object scales, leading to detail loss or irrelevant feature aggregation. To address these issues, this work aims to enhance robustness to scale variations and achieve precise object localization. We propose the Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network (RDNet), which replaces the CNN backbone with the SwinTransformer for global context modeling and introduces three key modules: (1) the Dynamic Adaptive Detail-aware (DAD) module, which applies varied convolution kernels guided by object region proportions; (2) the Frequency-matching Context Enhancement (FCE) module, which enriches contextual information through wavelet interactions and attention; and (3) the Region Proportion-aware Localization (RPL) module, which employs cross-attention to highlight semantic details and integrates a Proportion Guidance (PG) block to assist the DAD module. By combining these modules, RDNet achieves robustness against scale variations and accurate localization, delivering superior detection performance compared with state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
