Semi-Supervised Multiscale Dynamic Graph Convolution Network for Hyperspectral Image Classification是西电发表在TNNLS(IEEE Transactions on Neural Networks and Learning Systems)的一项高光谱图像分类工作。 本文作者提出了 DMSGer 模型,一个基于多尺度和动态GCN的高光谱图像分类模型。 DMSGer 下面抽丝剥茧一点点分析...
Deep learning techniques have brought substantial performance gains to remote sensing image classification. Among them, convolutional neural networks (CNN) can extract rich spatial and spectral features from hyperspectral images in a short-range region, whereas graph convolutional networks (GCN) ca...
Danfeng Hong, Lianru Gao, Jing Yao, Bing Zhang, Antonio Plaza, Jocelyn Chanussot. Graph Convolutional Networks for Hyperspectral Image Classification, IEEE TGRS, 2021. - Hysen-B/IEEE_TGRS_GCN
CNN-Enhanced Graph Convolutional Network with Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification has been accepted by IEEE Transactions on Geoscience and Remote Sensing (TGRS) Abstract: Recently, the graph convolutional network (GCN) has drawn increasing attention in hyperspe...
Graph convolutional network (GCN) has shown potential in hyperspectral image (HSI) classification. However, GCN is a transductive learning method, which is... Y Ding,X Zhao,Z Zhang,... - 《IEEE Geoscience & Remote Sensing Letters》 被引量: 0发表: 2022年 Incorporating multi-interest into rec...
Spatial-Pooling-Based Graph Attention U-Net for Hyperspectral Image Classification In recent years, graph convolutional networks (GCNs) have attracted increasing attention in hyperspectral image (HSI) classification owing to their excepti... Q Diao,Y Dai,J Wang,... - 《Remote Sensing》 被引量: ...
文献阅读记录:Graph Convolutional Networks for Hyperspectral Image Classification CNN和GCN的对比 GCN的相关paper Shahraki and Prasad [33] proposed to cascade 1-D CNNs and GCNs for HS image classification. CNN和GCN级联 Qin et al. [34] extended the original GCNs to a second-order version by sim...
Multi-scale feature learning via residual dynamic graph convolutional network for hyperspectral image classification Thanks to the relevant spectral-spatial information, hyperspectral images (HSIs) have been widely exploited in Earth observation. Recently, graph convoluti... R Chen,G Vivone,DJ Chanussot ...
HDECGCN: A Heterogeneous Dual Enhanced Network Based on Hybrid CNNs Joint Multiscale Dynamic GCNs for Hyperspectral Image Classification The hybrid enhanced CNN branch uses the groupable convolutions with a mixed spectral stacking and residual nonlocal block at the hybrid convolution output ... X ...
To the best if the authors' knowledge, this paper introduces the exploitation of GCNs for hyperspectral image classification (HSI-GCN) for the first time. HSI-GCN is able to extract deep joint spatial鈥搒pectral features more rapidly and accurately despite the shortage of training samples. The ...