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.

Representative samples from the TV-RSI dataset.

All sampling, annotations, panel composition, and graphics are original works by the authors and are released under CC BY 4.0.

More »

Fig 1 Expand

Fig 2.

Regional distribution of semantic objects.

More »

Fig 2 Expand

Fig 3.

Heat map of the object’s position.

More »

Fig 3 Expand

Fig 4.

Overall architecture diagram of MPLNet.

More »

Fig 4 Expand

Fig 5.

Structure of the Mamba Fusion Module (MFM).

More »

Fig 5 Expand

Table 1.

Experimental results on the TV-RSI dataset (pixel accuracy Acc and IoU per class).

More »

Table 1 Expand

Fig 6.

Qualitative comparisons on TV-RSI.

Ground truth masks and model outputs are shown for representative tiles. Base imagery (where visible) was obtained from the Geospatial Data Cloud (GF-2) for non-commercial academic use. All overlays, annotations, and panel layouts are original works by the authors and are released under CC BY 4.0.

More »

Fig 6 Expand

Fig 7.

Ablation of the Mamba Fusion Module (MFM).

Visual comparisons among Backbone, MPLNet (w/o MFM), and MPLNet demonstrate sharper boundaries and reduced omissions with MFM. Base imagery (where visible) was obtained from the Geospatial Data Cloud (GF-2) for non-commercial academic use. All derived visualizations are author-original and released under CC BY 4.0.

More »

Fig 7 Expand

Table 2.

Ablation results of MFM.

More »

Table 2 Expand

Fig 8.

Ablation of prompt learning (PL).

Compared with the student baseline, MPLNet with PL recovers fine structures and reduces confusion in mixed land-cover zones. Base imagery (where visible) was obtained from the Geospatial Data Cloud (GF-2) for non-commercial academic use. All annotations and compositions are original works by the authors and are released under CC BY 4.0.

More »

Fig 8 Expand

Table 3.

Ablation results for prompt learning.

More »

Table 3 Expand

Table 4.

Quantitative comparison results for the Vaihingen dataset.

More »

Table 4 Expand

Table 5.

Quantitative comparison results for the Potsdam dataset.

More »

Table 5 Expand

Table 6.

Comparison of model parameters and computational complexity.

More »

Table 6 Expand