Table 7.
The classification accuracy (OA (%) and SD) of the examined method and the reference methods, with 60% and 40% of WHU-RS dataset as a training set.
| Method | 60% of WHU-RS Dataset as a Training Set | 40% of WHU-RS Dataset as a Training Set |
|---|---|---|
| Bag of SIFT [29] | 85.52 ± 1.23 | / |
| MS-CLBP + BoVW [67] | 89.29 ± 1.30 | / |
| GoogLeNet [44] | 94.71 ± 1.33 | 93.12 ± 0.82 |
| VGG-VD-16 [44] | 96.05 ± 0.91 | 95.44 ± 0.60 |
| CaffeNet [44] | 96.24 ± 0.56 | 95.11 ± 1.20 |
| salM3LBP-CLM [60] | 96.38 ± 0.82 | 95.35 ± 0.76 |
| TEX-Net-LF 61] | 96.62 ± 0.49 | 95.89 ± 0.37 |
| InceptionV3 mixed_8 (PCA) + ResNet50 avg pooling (Ours) | 98.13 ± 0.51 | / |
| DCA by addition [64] | 98.70 ± 0.22 | 97.61 ± 0.36 |
| Fusion with saliency detection [50] | 98.92 ± 0.52 | 98.23 ± 0.56 |
| DenseNet121 conv5_block16_concat (PCA) + ResNet50 avg pooling (Ours) | / | 98.26 ± 0.40 |