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.

Schematic Diagram of the RTAS-Net Architecture.

More »

Fig 1 Expand

Fig 2.

Schematic Diagram of the Improved Encoder Structure and Its Components.

More »

Fig 2 Expand

Fig 3.

The Structure of the ASPP Module.

More »

Fig 3 Expand

Fig 4.

The Structure of the mini-ASPP Module.

More »

Fig 4 Expand

Table 1.

Quantitative comparison on the ISPRS Potsdam dataset. The accuracy for each class is presented in the form of IoU (%). The best results are highlighted in bold.

More »

Table 1 Expand

Fig 5.

Qualitative comparison results of different methods on the Potsdam dataset.

More »

Fig 5 Expand

Table 2.

Quantitative comparison on the ISPRS Vaihingen dataset. The accuracy for each class is presented in the form of IoU (%). The best results are highlighted in bold.

More »

Table 2 Expand

Fig 6.

Qualitative comparison results of different methods on the Vaihingen dataset.

More »

Fig 6 Expand

Table 3.

Performance Comparison of Different Module Combinations (Potsdam).

More »

Table 3 Expand

Fig 7.

Radar Chart of Per-Class IoU for Ablation Models on the Potsdam Dataset.

More »

Fig 7 Expand

Table 4.

Location and Sequential Ablation Results for the Potsdam Dataset (V0–V7).

More »

Table 4 Expand

Fig 8.

Visual Comparison of Segmentation Results from Different Models on the Potsdam Dataset (Red Boxes Highlight Key Comparison Areas).

More »

Fig 8 Expand

Fig 9.

Typical failure cases on the Potsdam dataset.

More »

Fig 9 Expand

Table 5.

Performance Comparison of Different Module Combinations (Vaihingen).

More »

Table 5 Expand

Fig 10.

Radar Chart of Per-Class IoU for Ablation Models on the Vaihingen Dataset.

More »

Fig 10 Expand

Table 6.

Location and Sequential Ablation Results for the Vaihingen Dataset (V0–V7).

More »

Table 6 Expand

Fig 11.

Visual Comparison of Segmentation Results from Different Models on the Vaihingen Dataset (Red Boxes Highlight Key Comparison Areas).

More »

Fig 11 Expand

Fig 12.

Typical failure cases on the Vaihingen dataset.

More »

Fig 12 Expand

Table 7.

Performance Comparison of Different Module Combinations (LoveDA).

More »

Table 7 Expand

Table 8.

Sensitivity to edge-weight λ in the loss function on LoveDA.

More »

Table 8 Expand

Table 9.

Computational efficiency of module-combination models (A–E) and placement/order variants (V0–V7).

More »

Table 9 Expand