.png){kind=icon}
.png){kind=icon}
Return
Effective Spatial-Spectral Feature Representation for Hyperspectral Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2025.3628253.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
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
Keywords:
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
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W