机译:Hybrid 2-D-3-D深剩余注意网络,具有结构张量限制,用于RGB图像的光谱超分辨率
Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China|CAS Key Lab Spectral Imaging Technol Xian 710119 Peoples R China;
Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China;
Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China;
Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China;
Shandong Normal Univ Sch Informat Sci & Engn Jinan 250358 Peoples R China;
Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China;
Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China;
Attention mechanism; hybrid 2-D-3-D deep residual attentional network (HDRAN); spatial-spectral context information; spectral super-resolution (SSR); structure tensor;
机译:多尺度深残留通道关注网络联合优化的肺结节图像超分辨率
机译:用于高光谱图像分类的深度混合扩张残差网络
机译:多谱卫星图像单图像超分辨率的深度剩余学习
机译:谱超分辨率使用混合2D-3D结构张量关注网络,具有相机光谱灵敏度
机译:自适应光谱加权结构张量应用于高光谱图像的张量各向异性非线性扩散。
机译:对抗网络用于从单个RGB重构尺度特征关注光谱图像
机译:通过组合2-D CNN和3-D CNN,深度协作关注网络进行高光谱图像分类