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.

Comparison of the Swin Transformer and the Vision Transformer.

(A) Swin Transformer; (B)Vision Transformer.

More »

Fig 1 Expand

Fig 2.

Swin Transformer structure.

More »

Fig 2 Expand

Fig 3.

Two consecutive swin transformer blocks.

More »

Fig 3 Expand

Fig 4.

Self-attention computed based on shifted windows.

More »

Fig 4 Expand

Fig 5.

Calculation of self-attention of moving windows based on cyclic shifting.

More »

Fig 5 Expand

Fig 6.

Abstract view of object detection systems.

More »

Fig 6 Expand

Fig 7.

SwinT-YOLOv4 structure.

More »

Fig 7 Expand

Fig 8.

SPP network structure.

More »

Fig 8 Expand

Fig 9.

PANet network structure.

More »

Fig 9 Expand

Table 1.

Setting of training parameters.

More »

Table 1 Expand

Fig 10.

SwinT-YOLOv4 loss function curve.

More »

Fig 10 Expand

Table 2.

Comparison of YOLOv4 and SwinT-YOLOv4 results.

More »

Table 2 Expand

Fig 11.

mAP of SwinT-YOLOv4 and YOLOv4.

(A) mAP of YOLOv4; (B) mAP of SwinT-YOLOv4.

More »

Fig 11 Expand

Table 3.

Comparison of Fps and FLOPs between YOLOv4 and SwinT-YOLOv4.

More »

Table 3 Expand

Fig 12.

Comparison of the detection effect of SwinT-YOLOv4 and YOLOv4.

(A) Detection effect of YOLOv4; (B) Detection effect of SwinT-YOLOv4.

More »

Fig 12 Expand

Table 4.

The performance comparison of existing model.

More »

Table 4 Expand