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.

Network of YOLOv5-LiNet.

LiNet backbone including neck of BiFPN, PANet and FPN.

More »

Fig 1 Expand

Fig 2.

Backbone component of YOLOv5-LiNet.

Stem, ResNet, Shuffle_Block, SPPF and C3 incorporated into neck network.

More »

Fig 2 Expand

Table 1.

List of trained models.

More »

Table 1 Expand

Fig 3.

Output for box validation loss.

More »

Fig 3 Expand

Fig 4.

Output for segmentation validation loss.

More »

Fig 4 Expand

Fig 5.

Output for box F1 score.

More »

Fig 5 Expand

Fig 6.

Output for segmentation F1 score.

More »

Fig 6 Expand

Fig 7.

Output for box mAP@0.5.

More »

Fig 7 Expand

Fig 8.

Output for segmentation mAP@0.5.

More »

Fig 8 Expand

Fig 9.

Image results of YOLOv4-tiny.

More »

Fig 9 Expand

Fig 10.

Image results of YOLOv5-Efficientlite.

More »

Fig 10 Expand

Fig 11.

Image results of YOLOv5-MobileNetv3.

More »

Fig 11 Expand

Fig 12.

Image results of YOLOv5-GhostNet.

More »

Fig 12 Expand

Fig 13.

Image results of YOLOv5-ShuffleNetv2.

More »

Fig 13 Expand

Fig 14.

Image results of YOLOv5n.

More »

Fig 14 Expand

Fig 15.

Image results of YOLOv5-LiNetFPN.

More »

Fig 15 Expand

Fig 16.

Image results of YOLOv5-LiNetBiFPN.

More »

Fig 16 Expand

Fig 17.

Image results of YOLOv5-LiNetC.

More »

Fig 17 Expand

Fig 18.

Image results of YOLOv5-LiNet.

More »

Fig 18 Expand

Table 2.

Compared summary performance of the tested models.

More »

Table 2 Expand