Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Structure of original GhostNet model.

a. The convolutional layer, b. The Ghost module.

More »

Fig 1 Expand

Fig 2.

Structure of Ghost bottlenecks.

More »

Fig 2 Expand

Table 1.

Original overall architecture of GhostNet.

More »

Table 1 Expand

Table 2.

Modified overall architecture of GhostNet.

More »

Table 2 Expand

Table 3.

The parameters of UAV images dataset.

More »

Table 3 Expand

Fig 3.

Combination of rotation and noise interference.

a) 90° + high noise, b) 180° + high noise, c) 270° + high noise, d) 90° + low noise, e) 180° + low noise, f) 270° + low noise.

More »

Fig 3 Expand

Fig 4.

Combination of rotation and different brightness and contrast augmentation.

(a) 90° + α = 1.4, β = 0.6. (b) 180° + α = 1.4, β = 0.6. (c) 270° + α = 1.4, β = 0.6. (d) 90° + α = 0.8, β = 1.2. (e) 180° + α = 0.8, β = 1.2. (f) 270° + α = 0.8, β = 1.2.

More »

Fig 4 Expand

Fig 5.

Feature maps derived from different layers.

(a) The 8th layer. (b) The 9th layer. (c) The 10th layer. (d) The 11th layer.

More »

Fig 5 Expand

Fig 6.

The entire training strategy of the Modified GhostNet model.

More »

Fig 6 Expand

Table 4.

The samples of a single category in training set before and after augmentation.

More »

Table 4 Expand

Table 5.

The average accuracy of GhostNet before and after image augmentation.

More »

Table 5 Expand

Fig 7.

The loss and accuracy of the GhostNet model before and after UCMerced image augmentation.

(a) Loss of training set. (b) Accuracy of training set. (c) Loss of validation set. (d) Accuracy of validation set.

More »

Fig 7 Expand

Fig 8.

The loss and accuracy of the GhostNet model before and after AID image augmentation.

(a) Loss of training set. (b) Accuracy of training set. (c) Loss of validation set. (d) Accuracy of validation set.

More »

Fig 8 Expand

Fig 9.

The loss and accuracy of the GhostNet model before and after NWPU-RESISC image augmentation.

(a) Loss of training set. (b) Accuracy of training set. (c) Loss of validation set. (d) Accuracy of validation set.

More »

Fig 9 Expand

Table 6.

FLOPs of different models on UCMerced dataset.

More »

Table 6 Expand

Table 7.

The memory usage and predicted time of different models.

More »

Table 7 Expand

Table 8.

The average accuracy of different models.

More »

Table 8 Expand

Fig 10.

The average accuracy of dropout position.

More »

Fig 10 Expand

Fig 11.

The average accuracy of the model before and after using transfer learning.

More »

Fig 11 Expand