.png){kind=icon}
返回
Hyperspectral Image Classification Using Groupwise Separable Convolutional Vision Transformer Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3377610.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, vision transformer (ViT)-based deep learning (DL) models have achieved remarkable performance gains in hyperspectral image classification (HSIC) due to their abilities to model long-range dependencies and extract global spatial features. However, ViT is built with a stack of Transformer blocks and faces the challenge of learning a large number of parameters when processing hyperspectral data. Besides, the inherent modeling of global correlation in Transformer ignores the effective representation of local spatial and spectral features. To address these issues, we propose a lightweight ViT network known as groupwise separable convolutional ViT (GSC-ViT). First, a groupwise separable convolution (GSC) module, which is a combination of grouped pointwise convolution (GPWC) and group convolution, is designed to significantly decrease the number of convolutional kernel parameters, and effectively capture local spectral-spatial information in hyperspectral image (HSI). Second, a groupwise separable multihead self-attention (GSSA) module is employed to substitute the conventional multihead self-attention (MSA) in ViT, in which the groupwise self-attention (GSA) provides local spatial feature extraction, and the pointwise self-attention (PWSA) provides global spatial feature extraction. Third, a simple pointwise layer with enhanced skip connection mechanism is employed to substitute the multilayer perceptron (MLP) layer in all Transformer blocks of ViT, so as to eliminate unnecessary nonlinear transformations and facilitate the fusion of features derived from GSC and GSSA modules. Extensive experiments on four benchmark hyperspectral datasets reveal that our GSC-ViT can achieve surprising classification performance with relatively few training samples as compared with some existing HSIC approaches. The source code is available at https://github.com/flyzzie/TGRS-GSC-VIT.
Keyword:
Convolution
Feature extraction
Transformers
Computational modeling
Hyperspectral imaging
Standards
Convolutional neural networks
Groupwise separable convolution (GSC)
groupwise separable multihead self-attention (GSSA)
hyperspectral image classification (HSIC)
vision transformer (ViT)
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
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Local Manifold Learning-Based k-Nearest-Neighbor for Hyperspectral Image Classification基于局部流形学习的k近邻高光谱图像分类
PREAI
分享收藏Density and Thermal Conductivity Measurements for Silicon Melt by Electromagnetic Levitation under a Static Magnetic Field在静态磁场下通过电磁悬浮测量硅熔体的密度和热导率
PREAI
分享收藏
查看更多内容