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.

YOLOv5 network model.

More »

Fig 1 Expand

Fig 2.

Flow chart of training and testing based on transfer learning.

More »

Fig 2 Expand

Fig 3.

The connection between the smallest bounding box (green) and the center point (red), where the joint area is Su = ωh + ωgthgtWiHi.

More »

Fig 3 Expand

Fig 4.

The overview of CBAM.

More »

Fig 4 Expand

Fig 5.

The principle and working mode of CoordConv.

More »

Fig 5 Expand

Fig 6.

Introduce coordinate information and attention mechanism to YOLOv5 backbone network.

More »

Fig 6 Expand

Fig 7.

CCW-YOLOv5 network architecture diagram.

More »

Fig 7 Expand

Fig 8.

Target model improvement, training, and testing flowchart.

More »

Fig 8 Expand

Table 1.

Parameter settings.

More »

Table 1 Expand

Fig 9.

Loss between prediction box and anchor box during training.

More »

Fig 9 Expand

Fig 10.

Loss between prediction frame and anchor frame during verification.

More »

Fig 10 Expand

Fig 11.

CCW-YOLOv5 model prediction effect diagram.

More »

Fig 11 Expand

Fig 12.

Comparison of validation set mAP test curves.

More »

Fig 12 Expand

Fig 13.

CCW-YOLOv5 P-R curve.

More »

Fig 13 Expand

Fig 14.

Confusion matrix of test results for CCW-YOLOv5.

More »

Fig 14 Expand

Table 2.

Target detection results of each model in forward looking sonar images.

More »

Table 2 Expand

Table 3.

Results of ablation research on various tricks.

More »

Table 3 Expand