SATNet: A Spatial Attention Based Network for Hyperspectral Image Classification

In order to categorize feature classes by capturing subtle differences, hyperspectral images (HSIs) have been extensively used due to the rich spectral-spatial information. The 3D convolution-based neural networks (3DCNNs) have been widely used in HSI classification because of their powerful feature extraction capability. However, the 3DCNN-based HSI classification approach could only extract local features, and the feature maps it produces include a lot of spatial information redundancy, which lowers the classification accuracy. To solve the above problems, we proposed a spatial attention network (SATNet) by combining 3D OctConv and ViT. Firstly, 3D OctConv divided the feature maps into high-frequency maps and low-frequency maps to reduce spatial information redundancy. Secondly, the ViT model was used to obtain global features and effectively combine local-global features for classification. To verify the effectiveness of the method in the paper, a comparison with various mainstream methods on three publicly available datasets was performed, and the results showed the superiority of the proposed method in terms of classification evaluation performance.

[1]  Y. Zhan,et al.  AF2GNN: Graph convolution with adaptive filters and aggregator fusion for hyperspectral image classification , 2022, Inf. Sci..

[2]  Ding Yao,et al.  Deep hybrid: Multi-graph neural network collaboration for hyperspectral image classification , 2022, Defence Technology.

[3]  Ying Zhan,et al.  Semi-Supervised Locality Preserving Dense Graph Neural Network With ARMA Filters and Context-Aware Learning for Hyperspectral Image Classification , 2021, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Lianru Gao,et al.  SpectralFormer: Rethinking Hyperspectral Image Classification With Transformers , 2021, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Zhili Zhang,et al.  Graph Sample and Aggregate-Attention Network for Hyperspectral Image Classification , 2021, IEEE Geoscience and Remote Sensing Letters.

[6]  Zhili Zhang,et al.  Unsupervised Self-Correlated Learning Smoothy Enhanced Locality Preserving Graph Convolution Embedding Clustering for Hyperspectral Images , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Zhili Zhang,et al.  Self-Supervised Locality Preserving Low-Pass Graph Convolutional Embedding for Large-Scale Hyperspectral Image Clustering , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Xianchuan Yu,et al.  Convolutional Transformer Network for Hyperspectral Image Classification , 2022, IEEE Geoscience and Remote Sensing Letters.

[9]  Zhihui Wei,et al.  From Local to Global: Class Feature Fused Fully Convolutional Network for Hyperspectral Image Classification , 2021, Remote. Sens..

[10]  Cong Bai,et al.  3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples , 2021, Remote. Sens..

[11]  Mercedes Eugenia Paoletti,et al.  Adaptable Convolutional Network for Hyperspectral Image Classification , 2021, Remote. Sens..

[12]  Kenneth A. McIsaac,et al.  Distance Transform-Based Spectral-Spatial Feature Vector for Hyperspectral Image Classification with Stacked Autoencoder , 2021, Remote. Sens..

[13]  Q. Du,et al.  Kernel low-rank representation with elastic net for China coastal wetland land cover classification using GF-5 hyperspectral imagery , 2021, ISPRS Journal of Photogrammetry and Remote Sensing.

[14]  Fang Liu,et al.  Residual Spectral-Spatial Attention Network for Hyperspectral Image Classification , 2021, IEEE Trans. Geosci. Remote. Sens..

[15]  Yi Ma,et al.  Hyperspectral Classification Using Deep Belief Networks Based on Conjugate Gradient Update and Pixel-Centric Spectral Block Features , 2020, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[16]  Binge Cui,et al.  A Sparse Representation-Based Sample Pseudo-Labeling Method for Hyperspectral Image Classification , 2020, Remote. Sens..

[17]  Bidyut Baran Chaudhuri,et al.  HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification , 2019, IEEE Geoscience and Remote Sensing Letters.

[18]  Guo Cao,et al.  Active Semi-Supervised Random Forest for Hyperspectral Image Classification , 2019, Remote. Sens..

[19]  Deyu Meng,et al.  Spectral-Spatial Hyperspectral Image Classification via Robust Low-Rank Feature Extraction and Markov Random Field , 2019, Remote. Sens..

[20]  Jun Li,et al.  Active Learning With Convolutional Neural Networks for Hyperspectral Image Classification Using a New Bayesian Approach , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Patrick Lambert,et al.  3-D Deep Learning Approach for Remote Sensing Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Zhiming Luo,et al.  Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Ying Li,et al.  Convolutional Neural Networks Based Hyperspectral Image Classification Method with Adaptive Kernels , 2017, Remote. Sens..

[24]  Qian Du,et al.  Hyperspectral Image Classification Using Deep Pixel-Pair Features , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Cong Wang,et al.  A multi-label Hyperspectral image classification method with deep learning features , 2016, ICIMCS.

[26]  Antonio J. Plaza,et al.  Sparse Unmixing-Based Change Detection for Multitemporal Hyperspectral Images , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[27]  Sildomar T. Monteiro,et al.  Consistency of Measurements of Wavelength Position From Hyperspectral Imagery: Use of the Ferric Iron Crystal Field Absorption at $\sim$900 nm as an Indicator of Mineralogy , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Ben Somers,et al.  Heathland conservation status mapping through integration of hyperspectral mixture analysis and decision tree classifiers , 2012 .

[30]  Anne-Katrin Mahlein,et al.  Recent advances in sensing plant diseases for precision crop protection , 2012, European Journal of Plant Pathology.

[31]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[32]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.