MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image Classification
Deep learning has achieved remarkable success in hyperspectral image (HSI) classification, attributed to its powerful feature extraction capabilities. However, existing methods face several challenges: Convolutional Neural Networks (CNNs) are limited in modeling long-range spectral dependencies beca...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/13/2208 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850115539686391808 |
|---|---|
| author | Xiaofei Yang Lin Li Suihua Xue Sihuan Li Wanjun Yang Haojin Tang Xiaohui Huang |
| author_facet | Xiaofei Yang Lin Li Suihua Xue Sihuan Li Wanjun Yang Haojin Tang Xiaohui Huang |
| author_sort | Xiaofei Yang |
| collection | DOAJ |
| description | Deep learning has achieved remarkable success in hyperspectral image (HSI) classification, attributed to its powerful feature extraction capabilities. However, existing methods face several challenges: Convolutional Neural Networks (CNNs) are limited in modeling long-range spectral dependencies because of their limited receptive fields; Transformers are constrained by their quadratic computational complexity; and Mamba-based methods fail to fully exploit spatial–spectral interactions when handling high-dimensional HSI data. To address these limitations, we propose MRFP-Mamba, a novel Multi-Receptive-Field Parallel Mamba architecture that integrates hierarchical spatial feature extraction with efficient modeling of spatial–spectral dependencies. The proposed MRFP-Mamba introduces two key innovation modules: (1) A multi-receptive-field convolutional module employing parallel <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1</mn><mo>×</mo><mn>1</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3</mn><mo>×</mo><mn>3</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5</mn><mo>×</mo><mn>5</mn></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7</mn><mo>×</mo><mn>7</mn></mrow></semantics></math></inline-formula> kernels to capture fine-to-coarse spatial features, thereby improving discriminability for multi-scale objects; and (2) a parameter-optimized Vision Mamba branch that models global spatial–spectral relationships through structured state space mechanisms. Experimental results demonstrate that the proposed MRFP-Mamba consistently surpasses existing CNN-, Transformer-, and state space model (SSM)-based approaches across four widely used hyperspectral image (HSI) benchmark datasets: PaviaU, Indian Pines, Houston 2013, and WHU-Hi-LongKou. Compared with MambaHSI, our MRFP-Mamba achieves improvements in Overall Accuracy (OA) by 0.69%, 0.30%, 0.40%, and 0.97%, respectively, thereby validating its superior classification capability and robustness. |
| format | Article |
| id | doaj-art-d8f74417a2ee4e3484162c485becf646 |
| institution | OA Journals |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-d8f74417a2ee4e3484162c485becf6462025-08-20T02:36:33ZengMDPI AGRemote Sensing2072-42922025-06-011713220810.3390/rs17132208MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image ClassificationXiaofei Yang0Lin Li1Suihua Xue2Sihuan Li3Wanjun Yang4Haojin Tang5Xiaohui Huang6School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Information Engineering, East China Jiaotong University, Nanchang 330044, ChinaDeep learning has achieved remarkable success in hyperspectral image (HSI) classification, attributed to its powerful feature extraction capabilities. However, existing methods face several challenges: Convolutional Neural Networks (CNNs) are limited in modeling long-range spectral dependencies because of their limited receptive fields; Transformers are constrained by their quadratic computational complexity; and Mamba-based methods fail to fully exploit spatial–spectral interactions when handling high-dimensional HSI data. To address these limitations, we propose MRFP-Mamba, a novel Multi-Receptive-Field Parallel Mamba architecture that integrates hierarchical spatial feature extraction with efficient modeling of spatial–spectral dependencies. The proposed MRFP-Mamba introduces two key innovation modules: (1) A multi-receptive-field convolutional module employing parallel <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1</mn><mo>×</mo><mn>1</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3</mn><mo>×</mo><mn>3</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5</mn><mo>×</mo><mn>5</mn></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7</mn><mo>×</mo><mn>7</mn></mrow></semantics></math></inline-formula> kernels to capture fine-to-coarse spatial features, thereby improving discriminability for multi-scale objects; and (2) a parameter-optimized Vision Mamba branch that models global spatial–spectral relationships through structured state space mechanisms. Experimental results demonstrate that the proposed MRFP-Mamba consistently surpasses existing CNN-, Transformer-, and state space model (SSM)-based approaches across four widely used hyperspectral image (HSI) benchmark datasets: PaviaU, Indian Pines, Houston 2013, and WHU-Hi-LongKou. Compared with MambaHSI, our MRFP-Mamba achieves improvements in Overall Accuracy (OA) by 0.69%, 0.30%, 0.40%, and 0.97%, respectively, thereby validating its superior classification capability and robustness.https://www.mdpi.com/2072-4292/17/13/2208hyperspectral image classificationMambasdeep learning |
| spellingShingle | Xiaofei Yang Lin Li Suihua Xue Sihuan Li Wanjun Yang Haojin Tang Xiaohui Huang MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image Classification Remote Sensing hyperspectral image classification Mambas deep learning |
| title | MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image Classification |
| title_full | MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image Classification |
| title_fullStr | MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image Classification |
| title_full_unstemmed | MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image Classification |
| title_short | MRFP-Mamba: Multi-Receptive Field Parallel Mamba for Hyperspectral Image Classification |
| title_sort | mrfp mamba multi receptive field parallel mamba for hyperspectral image classification |
| topic | hyperspectral image classification Mambas deep learning |
| url | https://www.mdpi.com/2072-4292/17/13/2208 |
| work_keys_str_mv | AT xiaofeiyang mrfpmambamultireceptivefieldparallelmambaforhyperspectralimageclassification AT linli mrfpmambamultireceptivefieldparallelmambaforhyperspectralimageclassification AT suihuaxue mrfpmambamultireceptivefieldparallelmambaforhyperspectralimageclassification AT sihuanli mrfpmambamultireceptivefieldparallelmambaforhyperspectralimageclassification AT wanjunyang mrfpmambamultireceptivefieldparallelmambaforhyperspectralimageclassification AT haojintang mrfpmambamultireceptivefieldparallelmambaforhyperspectralimageclassification AT xiaohuihuang mrfpmambamultireceptivefieldparallelmambaforhyperspectralimageclassification |