Spectral-Spatial Attention Networks for Hyperspectral Image Classification

By Hao Sun, Xiangtao Zheng, Xiaoqiang Lu, Siyuan Wu. Remote Sensing, 2019

570 citations recorded by the source corpus.

Many deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN), have been successfully applied to extracting deep features for hyperspectral tasks. Hyperspectral image classification allows distinguishing the characterization of land covers by utilizing their abundant information. Motivated by the attention mechanism of the human visual system, in this study, we propose a spectral-spatial attention network for hyperspectral image classification. In our method, RNN with attention can learn inner spectral correlations within a continuous spectrum, while CNN with attention is designed to focus on saliency features and spatial relevance between neighboring pixels in the spatial dimension. Experimental results demonstrate that our method can fully utilize the spectral and spatial information to obtain competitive performance.

Subfields: Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/4d2d78ea1ba6967eee257e9eac89fc1c9fded70d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

1. Matteo Matteucci
2. Sara Comai
3. Jingxiang Yang
4. Ava Vali

In Media Technology

1. Qichao Liu
2. Zhihui Wei
3. Matteo Matteucci
4. Sara Comai
5. Jingxiang Yang
6. Liang Xiao
7. Ava Vali

Citations in the corpus

• Attention, please! A survey of neural attention models in deep learning (2021, background): “2018c), remote sensing data (Zhang et al. 2019h; Fang et al. 2019a; Wang et al. 2018d; Mei et al. 2019), audio-video (Hori et al.”
• CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification (2020, background): “Other recently advanced CNN architectures have also been explored, such as the spectral and spatial attention networks [37], [38].”
• Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review (2020, background): “The authors of [116] introduce the attention network structure for hyperspectral image classification that includes 3D-CNN based spatial, spectral and attention modules; the latter one is designed to extract the discriminative features from attention areas of HSI cubes.”