.png){kind=icon}
返回
Hyperspectral Image Classification With Mamba
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3521411.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Local and global spectral and spatial information is crucial for hyperspectral image (HSI) classification. However, modeling the global context has been challenging due to the limitations of receptive fields and quadratic complexity. Mamba's ability to leverage long-range dependencies with linear computational complexity offers an effective approach to alleviate this issue; however, it does lead to the loss of local detail information. To address this challenge, we propose a novel local-to-global Mamba for HSI classification, termed MambaLG. MambaLG consists of a dual-branch strategy, comprising two core modules: a local and global spatial modeling module (SpaM) and a short- and long-range spectral dynamic perception module (SpeM). In the SpaM, the local and global spatial information is sequentially extracted and integrated, aiming to capture global spatial semantics while preserving the integrity of local 2-D spatial structures. In the SpeM, we utilize local spectral extraction, spectral grouping, and spectral dynamic correlation clustering (SDCC) modules, leveraging Mamba's strengths in exploring long-range dependencies for more precise short- and long-range spectral feature modeling. Additionally, we introduce a gate attention unit into MambaLG and design a more efficient and interpretable manner for merging spatial and spectral features. Experimental results across multiple datasets (encompassing urban and agricultural scenes) indicate that MambaLG surpasses state-of-the-art algorithms regarding classification accuracy (CA) and inference speed. Comprehensive ablation studies substantiate the advantages of MambaLG in modeling local and global spatial context, enhancing short- and long-range spectral perception, and fusing spatial and spectral information. The codes will be openly available at https://github.com/danfenghong/IEEE_TGRS_MambaLG to facilitate the reproduction of experimental results.
Keyword:
Feature extraction
Data mining
Correlation
Logic gates
Computational modeling
Complexity theory
Transformers
Context modeling
Visualization
Three-dimensional displays
Decoupling and fusion
hyperspectral image (HSI) classification
local and global spatial context
Mamba
short- and long-range spectral dependencies
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks跨城市事务: 使用高分辨率域适应网络进行跨城市语义分割的多模态遥感基准数据集
OAAI
OAAI分享收藏Critical evaluation of hyperspectral imaging technology for detection and quantification of microplastics in soil高光谱成像技术检测和定量土壤中微塑料的临界评价
PREAI
分享收藏Formation of nitrosyl complexes in the reaction between platinum (II) nitro complexes and concentrated hydrochloric acid在铂 (II) 硝基配合物与浓盐酸之间的反应中形成亚硝基配合物
PREAI
分享收藏PROSAIL-Net: A transfer learning-based dual stream neural network to estimate leaf chlorophyll and leaf angle of crops from UAV hyperspectral imagesPROSAIL-Net: 基于转移学习的双流神经网络，用于从无人机高光谱图像估计农作物的叶片叶绿素和叶片角度
OAAI
OAAI分享收藏Adaptive Spectral-Spatial Multiscale Contextual Feature Extraction for Hyperspectral Image Classification用于高光谱图像分类的自适应光谱-空间多尺度上下文特征提取
PREAI
分享收藏Spatial Niche Partitioning in Sub-Tropical Solitary Ungulates: Four-Horned Antelope and Barking Deer in Nepal.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容