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.

Dual-modal object detection based on deep learning.

More »

Fig 1 Expand

Fig 2.

Overall framework of the proposed DEF-Net.

More »

Fig 2 Expand

Fig 3.

The backbone network architecture of Darknet53.

More »

Fig 3 Expand

Fig 4.

Dual-branch backbone structure.

More »

Fig 4 Expand

Fig 5.

Feature interaction and enhancement structure.

More »

Fig 5 Expand

Fig 6.

Cross attention fusion network structure.

More »

Fig 6 Expand

Fig 7.

Illustration of Cross attention weight.

More »

Fig 7 Expand

Table 1.

Training Hyperparameter Configuration.

More »

Table 1 Expand

Fig 8.

SYUGV Datasets.

More »

Fig 8 Expand

Table 2.

Comparative experimental results of different models.

More »

Table 2 Expand

Fig 9.

Comparison of model training on the SYUGV dataset.

More »

Fig 9 Expand

Fig 10.

Comparison of detection effects of different models on the SYUGV dataset.

More »

Fig 10 Expand

Fig 11.

Comparison of model training on the LLVIP dataset.

More »

Fig 11 Expand

Table 3.

Comparative experimental results of different models.

More »

Table 3 Expand

Fig 12.

Comparison of detection effects of different models on the LLVIP dataset.

More »

Fig 12 Expand

Table 4.

Model detection performance of different modal inputs.

More »

Table 4 Expand

Fig 13.

P-R curves of different modal inputs.

More »

Fig 13 Expand

Fig 14.

Grad-CAM heatmap of dual branch model.

More »

Fig 14 Expand

Table 5.

Model detection performance of different backbone networks.

More »

Table 5 Expand

Table 6.

Ablation study of different module combinations on the SYUGV dataset.

More »

Table 6 Expand

Table 7.

Ablation study of different module combinations on the LLVIP dataset.

More »

Table 7 Expand

Fig 15.

mAP@0.5 curves of ablation studies on the(a) SYUGV and (b) LLVIP datasets.

More »

Fig 15 Expand

Fig 16.

Visualization of feature activation (heatmaps) for different model variants.

More »

Fig 16 Expand