.png){kind=icon}
返回
DBCTNet: Double Branch Convolution-Transformer Network for Hyperspectral Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3368141.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Currently, deep learning (DL) methods represented by convolutional neural networks (CNNs) or Transformers are of great interest in hyperspectral image (HSI) classification. And recent works show that hybrid models using CNN and Transformer modules are expected to achieve better performance than when they are used alone. However, these hybrid models applied to HSI classification consider the combination of 2-D CNN and Transformer, which makes the models have high computational complexity. And the information of multiple spectral dimensions different from ordinary RGB images has not been fully excavated. Based on this, we propose, a double branch Convolution-Transformer network (DBCTNet). Specifically, a MSpeFE module is used for multiscale spectral feature extraction at the early stage of the proposed network. Then, a ConvTE block is designed to improve the original Transformer encoder (TE), where a Conv spectral projection unit and a convolutional multihead self-attention (CMHSA) unit are proposed to extract spatial and global spectral features. A double branch module is further built based on 3-D CNN and ConvTE. This module can fully integrate spatial and local-global spectral features, while also having low computational complexity. Experiment results on four public datasets, Pavia University, Houston, WHU-Hi-LongKou, and HuangHeKou, show that DBCTNet achieves satisfactory performance with a small number of parameters and relatively excellent efficiency compared to nine other networks.
Keyword:
Feature extraction
Transformers
Convolution
Three-dimensional displays
Convolutional neural networks
Kernel
Standards
Convolutional neural networks (CNNs)
hyperspectral image (HIS) classification
multiscale
Transformer
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
Investigation on the genotoxicity of different sizes of gold nanoparticles administered to the lungs of rats不同粒径纳米金对大鼠肺的遗传毒性研究
.png){kind=icon}
PREAI
分享收藏Molecular and Pharmacological Characterization of GABAA Receptors in the Rat Pituitary大鼠垂体中GABAA 受体的分子和药理学特征
PREAI
分享收藏Mesh Type With Ventral Hernia Repair: A Systematic Review and Meta-analysis of Randomized Trials腹壁疝修补术中的网片类型：随机试验的系统评价和Meta分析
PREAI
分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏分享收藏A Self-Improving Convolution Neural Network for the Classification of Hyperspectral Data一种用于高光谱数据分类的自改进卷积神经网络
OAAI
OAAI分享收藏Hyperspectral and LiDAR Data Classification Based on Structural Optimization Transmission基于结构优化传输的高光谱与激光雷达数据分类
PREAI
分享收藏
查看更多内容