Fig. 1. In-class diversity. (a) (b) (c) Church category; (d) (e) (f) railway station category
Fig. 2. Between-class similarity. (a) (b) freeway versus runway; (c) (d) industrial area versus railway station; (e) (f) stadium versus train station
Fig. 3. Shortcut connection of resnet
Fig. 4. Network structure diagram
Fig. 5. Graphic example of jump connection
Fig. 6. UC Merced Land Use remote sensing image dataset. (a) Beach; (b) baseball field; (c) overpass
Fig. 7. Google of SIRI-WHU sensing image dataset. (a) River; (b) pond; (c) harbor
Fig. 8. NWPU-RESISC45 sensing image dataset. (a) Forest; (b) circular farmland; (c) river
Fig. 9. UC Merced Land Use data set classification results
Fig. 10. Google of SIRI-WHU data set classification results
Fig. 11. NWPU-RESISC45 data set classification results
Experimental environment | Environment configuration |
---|
Operating system | Ubuntu 16.04 | Software environment | Python 2.7,pytorch 0.4.1 | CPU | Xeon(R).W-2123 | Internal memory | DDR4,32G |
|
Table 1. Introduction of experimental environment
Model | OA |
---|
DCA[7] | 96.90 | AlexNet+MSCP[14] | 96.70 | SCCov[16] | 98.04 | ResNet | 96.70 | Ours | 99.76 |
|
Table 2. Comparison of the classification results obtained for the UC Merced Land Use dataset unit: %
Model | OA |
---|
SRSCNN[17] | 93.40 | AlexNet+Softmax[18] | 95.63 | AlexNet+SVM[18] | 95.83 | ResNet | 93.75 | Ours | 97.91 |
|
Table 3. Comparison of the classification results obtained for the Google of SIRI-WHU dataset unit: %
Model | OA |
---|
DCNN[9] | 89.22 | VGG+MSCP[14] | 88.93 | SCCov[16] | 89.30 | ResNet | 87.61 | Ours | 92.45 |
|
Table 4. Comparison of the classification results obtained for the NWPU-RESISC45 dataset unit: %