期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 19, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2021.3062944
关键词
Convolution; Feature extraction; Neural networks; Hyperspectral imaging; Aggregates; Training; Mathematical model; Global and contextual information; graph convolution neural network; hyperspectral image (HSI) classification
类别
资金
- National Natural Science Foundation of China [41404022]
- National Natural Science Foundation of Shanxi Province [2015JM4128]
SAGE-A uses a multi-level graph sample and aggregate (graphSAGE) network to flexibly aggregate new neighbor nodes among arbitrarily structured non-Euclidean data and capture long-range contextual relations. The network utilizes the graph attention mechanism to characterize the importance among spatially neighboring regions, allowing for automatic learning of deep contextual and global information of the graph.
Graph convolutional network (GCN) has shown potential in hyperspectral image (HSI) classification. However, GCN is a transductive learning method, which is difficult to aggregate the new node. The available GCN-based methods fail to understand the global and contextual information of the graph. To address this deficiency, a novel semisupervised network based on graph sample and aggregate-attention (SAGE-A) for HSIs' classification is proposed. Different from the GCN-based method, SAGE-A adopts a multilevel graph sample and aggregate (graphSAGE) network, as it can flexibly aggregate the new neighbor node among arbitrarily structured non-Euclidean data and capture long-range contextual relations. Inspired by the convolution neural network (CNN) self-attention mechanism, the proposed network uses the graph attention mechanism to characterize the importance among spatially neighboring regions, so the deep contextual and global information of the graph can be learned automatically by focusing on important spatial targets. Extensive experimental results on different real hyperspectral data sets demonstrate the performances of our proposed method compared with the state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据