Remote Sensing Image Classification Based on Grouped Spatial Coordinate Attention and Mamba

Table 1. Performance comparison of image classification methods on the UCM dataset
View table
Table 1. Performance comparison of image classification methods on the UCM dataset
Method P /% R /% F₁ /%
ResNet-50 91.90 91.84 91.79
EfficientNet-B3 89.91 88.98 89.12
ViT-B 91.09 90.79 90.77
Swin-B 91.85 91.74 91.62
ViM 92.92 92.54 92.43
VMamba 93.66 93.33 93.08
RSMamba-H 95.47 95.23 95.25
Ours 97.28 97.15 97.13

Table 2. Performance comparison of image classification methods on the AID dataset
View table
Table 2. Performance comparison of image classification methods on the AID dataset
Method P /% R /% F₁ /%
ResNet-50 89.83 88.89 88.62
EfficientNet-B3 87.80 87.10 87.03
ViT-B 88.71 88.26 88.30
Swin-B 89.86 89.36 89.39
ViM 90.81 90.42 90.48
VMamba 92.58 91.75 91.76
RSMamba-H 92.97 92.51 92.63
Ours 94.60 94.35 94.41

Table 3. Performance comparison of image classification methods on the NWPU-RESISC45 dataset
View table
Table 3. Performance comparison of image classification methods on the NWPU-RESISC45 dataset
Method P /% R /% F₁ /%
ResNet-50 92.58 92.21 92.21
EfficientNet-B3 89.21 88.25 87.52
ViT-B 89.36 88.25 87.88
Swin-B 93.63 91.58 93.56
ViM 93.03 92.89 92.86
VMamba 94.32 94.25 94.22
RSMamba-H 95.22 95.19 95.18
Ours 96.41 96.35 96.33

Table 4. Validation of the effectiveness of each module

View table

Table 4. Validation of the effectiveness of each module

Method	UCM			AID			NWPU-RESISC45
Method	P	R	F₁	P	R	F₁	P	R	F₁
BL	92.92	92.54	92.43	90.81	90.42	90.48	93.03	92.89	92.86
BL+GSCA	95.18	94.76	94.66	93.03	92.65	92.61	95.35	95.30	95.29
BL+DMME	94.67	94.44	94.37	92.66	92.33	92.33	94.55	94.47	94.44
Ours	97.28	97.15	97.13	94.60	94.35	94.41	96.41	96.35	96.33

Table 5. Effectiveness verification of the combination of spatial information extraction and attention mechanism
View table
Table 5. Effectiveness verification of the combination of spatial information extraction and attention mechanism
Method F₁ /%
UCM AID NWPU-RESISC45
None 94.37 92.33 94.44
CA 95.23 93.13 95.32
GSCA 97.13 94.41 96.33

Tools

Get Citation

Copy Citation Text

Hui Chen, Zixu Li. Remote Sensing Image Classification Based on Grouped Spatial Coordinate Attention and Mamba[J]. Acta Optica Sinica, 2025, 45(15): 1528001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Remote Sensing and Sensors

Received: Apr. 17, 2025

Accepted: May. 12, 2025

Published Online: Aug. 8, 2025

The Author Email: Zixu Li (1074301430@qq.com)

DOI:10.3788/AOS250956

CSTR:32393.14.AOS250956

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Performance comparison of image classification methods on the UCM dataset

Table 1. Performance comparison of image classification methods on the UCM dataset

Table 2. Performance comparison of image classification methods on the AID dataset

Table 2. Performance comparison of image classification methods on the AID dataset

Table 3. Performance comparison of image classification methods on the NWPU-RESISC45 dataset

Table 3. Performance comparison of image classification methods on the NWPU-RESISC45 dataset

Table 4. Validation of the effectiveness of each module

Table 4. Validation of the effectiveness of each module

Table 5. Effectiveness verification of the combination of spatial information extraction and attention mechanism

Table 5. Effectiveness verification of the combination of spatial information extraction and attention mechanism