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.

The HKMask framework for instance segmentation.

More »

Fig 1 Expand

Fig 2.

The schema of the original residual module (a) and the hybrid kernel module (b). Hybrid kernel module introduces attention mechanism and mixed convolution on the basis of the original Resnet module.

More »

Fig 2 Expand

Table 1.

Details of ResNet-50 and hybrid kernel module-50.

More »

Table 1 Expand

Fig 3.

The improved squeeze-excitation networks.

The max pooling is used to retain texture information and the average pooling retains global information of the feature map.

More »

Fig 3 Expand

Fig 4.

Original remote sensing image (a) and corresponding binary image (b).

More »

Fig 4 Expand

Fig 5.

Feature maps of three datasets in different stages.

Compared to the original method, ours has a significant suppressing effect on unrelated background pixels, while enhancing the pixels of the target instance. This is conducive to the convergence speed in the process of model training.

More »

Fig 5 Expand

Table 2.

The gains of ISE component in our design.

More »

Table 2 Expand

Table 3.

The gains of hybrid kernel component in our design.

More »

Table 3 Expand

Table 4.

Quantitative results on COCO 2017val.

More »

Table 4 Expand

Fig 6.

Qualitative result of different methods on xBD and COCO datasets.

More »

Fig 6 Expand