.png){kind=icon}
返回
Effective Spatial-Spectral Feature Representation for Hyperspectral Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2025.3628253.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Hyperspectral images (HSIs), with their rich spectral information and spatial details, have demonstrated significant potential for classification tasks in fields such as remote sensing, agriculture, and environmental monitoring. However, existing methods still exhibit limitations in feature representation, primarily manifested in insufficient contextual modeling and the inability to effectively address spectral redundancy and significant variations in spatial scales. To address these challenges, this article proposes an enhanced MambaHSI-based framework for HSI classification, focusing on improving the representation capability of spatial-spectral features. The proposed method consists of three key innovations: 1) a hierarchical DualGroupMamba module that progressively models intragroup and intergroup spectral dependencies to enhance fine-grained spectral discrimination and global contextual awareness; 2) a lightweight hyperspectral channel attention (HCA) that dynamically adjusts the importance of feature channels based on the spatial-spectral information of different bands, effectively suppressing redundant information and highlighting discriminative features; and 3) a hybrid feature enhancer (HFE) module that effectively represents and fuses multiscale spatial features by extracting local texture details and perceiving the overall spatial distribution of scenes, thereby enhancing the model's adaptability to complex spatial structures. Through a systematic evaluation on four benchmark hyperspectral datasets, the proposed method achieved an average overall classification accuracy of 95.64%, outperforming the current best method by 1.89%. The experimental results validate the superior performance of the proposed approach in enhancing the representation of spatial-spectral features. The latest logs are now available at https://github.com/Tomyaya/EFR
Keyword:
Hyperspectral imaging
Feature extraction
Context modeling
Computational modeling
Image classification
Transformers
Deep learning
Adaptation models
Representation learning
Nearest neighbor methods
Dynamic channel adjustment
hyperspectral image (HSI) classification
Mamba architecture
multiscale spatial features
remote sensing
spatial-spectral feature representation
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object DetectionHCF-Net：用于红外小目标检测的层次化上下文融合网络
PREAI
分享收藏分享收藏Beyond the Patchwise Classification: Spectral-Spatial Fully Convolutional Networks for Hyperspectral Image Classification超越Patchwise分类: 用于高光谱图像分类的光谱空间完全卷积网络
PREAI
分享收藏Hierarchical Discriminative Feature Learning for Hyperspectral Image Classification用于高光谱图像分类的分层判别特征学习
PREAI
分享收藏IGroupSS-Mamba: Interval Group Spatial-Spectral Mamba for Hyperspectral Image ClassificationIgroupss-mamba: 用于高光谱图像分类的间隔组空间光谱Mamba
PREAI
分享收藏
查看更多内容