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.

Pipeline of PAM.

More »

Fig 1 Expand

Fig 2.

Pipeline of CAM.

More »

Fig 2 Expand

Fig 3.

Overall framework.

More »

Fig 3 Expand

Fig 4.

Pipeline of SPAM.

More »

Fig 4 Expand

Fig 5.

Pipeline of SCAM.

More »

Fig 5 Expand

Fig 6.

Architecture of MLFD.

More »

Fig 6 Expand

Fig 7.

Illustration of Potsdam dataset.

More »

Fig 7 Expand

Fig 8.

Illustration of DeepGlobe dataset.

More »

Fig 8 Expand

Table 1.

Hyper-parameter settings.

More »

Table 1 Expand

Table 2.

Data properties and partitions.

More »

Table 2 Expand

Table 3.

Comparative methods.

More »

Table 3 Expand

Table 4.

The results of the Potsdam test set with class-wise performance in form of IoU/OA and overall performance with mIoU and OA, where bold indicates the best.

More »

Table 4 Expand

Fig 9.

Visual inspections of random samples from the Potsdam test set.

More »

Fig 9 Expand

Table 5.

The results of the DeepGlobe test set with class-wise performance in form of IoU/OA and overall performance with mIoU and OA, where bold indicates the best.

More »

Table 5 Expand

Fig 10.

Visual inspections of random samples from the DeepGlobe test set.

More »

Fig 10 Expand

Table 6.

Accuracy comparisons in form of mIoU/OA on test set.

More »

Table 6 Expand

Fig 11.

Training loss on Potsdam dataset.

More »

Fig 11 Expand

Fig 12.

Training mIoU on Potsdam dataset.

More »

Fig 12 Expand

Fig 13.

Training loss on DeepGlobe dataset.

More »

Fig 13 Expand

Fig 14.

Training mIoU on DeepGlobe dataset.

More »

Fig 14 Expand

Table 7.

Efficiency comparisons.

More »

Table 7 Expand

Table 8.

Parameter comparisons.

More »

Table 8 Expand

Table 9.

Results of different decoders in form of mIoU/OA.

More »

Table 9 Expand