Local-Global Gated Convolutional Neural Network for Hyperspectral Image Classification

被引:5
作者
Fu, Wei [1 ]
Ding, Kexin [2 ]
Kang, Xudong [2 ]
Wang, Dong [3 ]
机构
[1] Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410082, Peoples R China
[2] Hunan Univ, Coll Elect & Informat Engn, Changsha 410082, Peoples R China
[3] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China
基金
中国国家自然科学基金;
关键词
Logic gates; Feature extraction; Convolutional neural networks; Convolution; Hyperspectral imaging; Kernel; Image classification; Deep learning (DL); gated convolutional; hyperspectral images classification (HSIC); local-global features; TRANSFORMER;
D O I
10.1109/LGRS.2023.3332226
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
How to learn the most valuable and useful features in convolutional neural networks (CNNs) is the key for accurate hyperspectral image classification (HSIC). Focused on this issue, we developed a local-global gated CNN (LGG-CNN), in this letter. The core is the simultaneous construction of local and global gated convolution blocks, with the aim to select highly discriminative information and filtering redundant information in hyperspectral images (HSIs). Different from traditional CNN methods treating all spectral-spatial features equally, the gated convolutions help in learning a normalized soft mask to guide the network to focus on valid features and neglect the invalid ones. Here, based on the CNN backbone, multilayer local features are first learned via gated convolutional architecture, which mainly consists of convolution operators and nonlinearly activation functions. At the same time, a global gated block (GGB) is designed to conduct feature serialization-mapping-patching operations, to learn global features from deeper layers with larger receptive fields. As a result, the local/GGBs can dynamically learn discriminative feature selection mechanisms for each channel at each spatial location. Then, the local and global features are fused at both the feature-level and decision-level. In this manner, the effective fusion of features by the multilayer LGG convolution blocks enables spatial interaction across layers, leading to further improvement in classification accuracy. Extensive experiments on three benchmark HSIC datasets demonstrate the superiority of LGG-CNN over some state-of-the-art methods. The source code of the proposed method is available at https://github.com/Ding-Kexin/LGG-CNN.
引用
收藏
页码:1 / 5
页数:5
相关论文
共 20 条
[1]   Random forest in remote sensing: A review of applications and future directions [J].
Belgiu, Mariana ;
Dragut, Lucian .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2016, 114 :24-31
[2]   Classification of hyperspectral data from urban areas based on extended morphological profiles [J].
Benediktsson, JA ;
Palmason, JA ;
Sveinsson, JR .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (03) :480-491
[3]   Global-Local Transformer Network for HSI and LiDAR Data Joint Classification [J].
Ding, Kexing ;
Lu, Ting ;
Fu, Wei ;
Li, Shutao ;
Ma, Fuyan .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[4]   Classification of Hyperspectral Images via Multitask Generative Adversarial Networks [J].
Hang, Renlong ;
Zhou, Feng ;
Liu, Qingshan ;
Ghamisi, Pedram .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (02) :1424-1436
[5]   Optimized Input for CNN-Based Hyperspectral Image Classification Using Spatial Transformer Network [J].
He, Xin ;
Chen, Yushi .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2019, 16 (12) :1884-1888
[6]   Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification [J].
Hong, Danfeng ;
Wu, Xin ;
Ghamisi, Pedram ;
Chanussot, Jocelyn ;
Yokoya, Naoto ;
Zhu, Xiao Xiang .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (06) :3791-3808
[7]   Grouped Multi-Attention Network for Hyperspectral Image Spectral-Spatial Classification [J].
Lu, Ting ;
Liu, Mengkai ;
Fu, Wei ;
Kang, Xudong .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
[8]   SCL-Net: An End-to-End Supervised Contrastive Learning Network for Hyperspectral Image Classification [J].
Lu, Ting ;
Hu, Yaochen ;
Fu, Wei ;
Ding, Kexin ;
Bai, Beifang ;
Fang, Leyuan .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[9]   Classification of hyperspectral remote sensing images with support vector machines [J].
Melgani, F ;
Bruzzone, L .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2004, 42 (08) :1778-1790
[10]   Attention-Based Adaptive SpectralSpatial Kernel ResNet for Hyperspectral Image Classification [J].
Roy, Swalpa Kumar ;
Manna, Suvojit ;
Song, Tiecheng ;
Bruzzone, Lorenzo .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (09) :7831-7843