计算机科学
突出
人工智能
水准点(测量)
相似性(几何)
特征(语言学)
目标检测
GSM演进的增强数据速率
计算机视觉
遥感
模式识别(心理学)
对象(语法)
方向(向量空间)
特征提取
感知
边缘检测
遥感应用
特征学习
数据挖掘
人工神经网络
校准
相似性度量
语义学(计算机科学)
鉴定(生物学)
图像(数学)
语义特征
视觉对象识别的认知神经科学
作者
Xin Wang,Xian Fang,Mingfeng Jiang,Jinchao Zhu,Zhigao Li
标识
DOI:10.1109/tgrs.2025.3636733
摘要
Salient object detection in optical remote sensing images (ORSI-SOD) aims to segment salient regions from high-resolution remote sensing images. However, most existing ORSI-SOD methods primarily rely on feature learning of regions to address the issue of blurred edges, while neglecting the potential advantages of similarity calculation in inferring edge clues. To overcome this issue, we propose a novel network with similarity perception termed edge-guided refinement network (ERNet), which distinguishes the edge region of salient objects from coarse to fine through two-stage similarity calculation. Firstly, we introduce the adaptive uncertainty calibration module (AUCM), which utilizes the proposed similarity-based edge perception mechanism (SEPM) to adaptively calibrate edge uncertain information. Secondly, to effectively capture global semantic information, we propose the hierarchical semantic reconstruction module (HSRM), which comprehensively correlates different levels of semantic clues from both internal and external perspectives. Finally, to supplement the local detail of salient objects, we design the dynamic detail interaction module (DDIM), which dynamically extracts detail information of objects at different scales. Extensive experiments on three challenging benchmark datasets have demonstrated the remarkable superiority of our ERNet compared to 30 state-of-the-art models. The source codes will be publicly available at https://github.com/xinwang11/ERNet.
科研通智能强力驱动
Strongly Powered by AbleSci AI