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.

Corrosion of metallic facilities in the marine environment.

More »

Fig 1 Expand

Table 1.

Advantages and disadvantages of different corrosion detection methods.

More »

Table 1 Expand

Fig 2.

YOLOv5s model structure framework.

More »

Fig 2 Expand

Fig 3.

CBG-YOLOv5s model structure framework.

More »

Fig 3 Expand

Fig 4.

CBAM model structure framework.

More »

Fig 4 Expand

Fig 5.

BiFPN-CBAM structure framework.

More »

Fig 5 Expand

Fig 6.

Convolution contrast diagram.

(a) Ordinary convolution operation. (b) Ghost convolution operation.

More »

Fig 6 Expand

Fig 7.

C3Ghost module.

More »

Fig 7 Expand

Fig 8.

Processing flow of metal surface corrosion data.

More »

Fig 8 Expand

Fig 9.

Corrosion of different types of metal surfaces.

More »

Fig 9 Expand

Fig 10.

Demonstration of the effects of data enhancement.

More »

Fig 10 Expand

Table 2.

Division of metal surface corrosion datasets.

More »

Table 2 Expand

Table 3.

Experiment environment.

More »

Table 3 Expand

Table 4.

YOLOv5s model performance.

More »

Table 4 Expand

Table 5.

CBG-YOLOv5s model performance.

More »

Table 5 Expand

Table 6.

Performance comparison between YOLOv5s and CBG-YOLOv5s.

More »

Table 6 Expand

Fig 11.

YOLOv5s detection effect diagram.

More »

Fig 11 Expand

Fig 12.

CBG-YOLOv5s detection effect diagram.

More »

Fig 12 Expand

Table 7.

Comparison with typical models.

More »

Table 7 Expand

Fig 13.

Recognition effect of each model.

More »

Fig 13 Expand

Table 8.

Ablation experiments.

More »

Table 8 Expand

Fig 14.

Curve of changes in each evaluation indicator during the training process.

More »

Fig 14 Expand