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.

Proposed method architecture: Our proposed method combines three key components: 1) Integration of deformable convolutions within the UNet framework to enhance fine-grained details and object boundary distinction. 2) Introduction of an attention ASPP module for context modeling, utilizing attention mechanisms to capture contextual information at multiple scales. 3) Utilization of the Large Kernel Attention (LKA) module in the decoding path of the UNet to refine features and improve discrimination of object classes. ** Original image was taken from Cityscapes dataset which is freely available on [69].

More »

Fig 1 Expand

Fig 2.

Deformable convolution [16].

More »

Fig 2 Expand

Fig 3.

Channel attention module.

SE block (a) and ECA block (b).

More »

Fig 3 Expand

Fig 4.

Large kernel attention module.

More »

Fig 4 Expand

Fig 5.

Efficient channel attention ASPP.

More »

Fig 5 Expand

Table 1.

Details of large kernel attention modules.

More »

Table 1 Expand

Table 2.

Structure of improved ResNet50.

More »

Table 2 Expand

Table 3.

Different modules used in the proposed UNet-based architectures.

More »

Table 3 Expand

Table 4.

Effect of additional modules on segmentation performance: Ablation study results in Stanford dataset.

More »

Table 4 Expand

Table 5.

Effect of additional modules on segmentation performance: Ablation study results in Cityscapes dataset.

More »

Table 5 Expand

Fig 6.

Ablation study results: Comparative analysis of additional modules on segmentation performance in Cityscapes dataset.

(Original image was taken from Cityscapes dataset which is freely available on [69]).

More »

Fig 6 Expand

Fig 7.

Ablation study results: Comparative analysis of additional modules on segmentation performance in WildPASS and DensPASS datasets.

(Original image was taken from WildPASS and DensPASS datasets which are freely available on [54, 70]).

More »

Fig 7 Expand

Table 6.

Performance comparison of semantic segmentation methods on Cityscapes, DensPASS.

More »

Table 6 Expand

Table 7.

Performance comparison of semantic segmentation methods on Cityscapes.

More »

Table 7 Expand

Table 8.

Class-wise IOU comparison of segmentation models on the Stanford dataset.

More »

Table 8 Expand

Fig 8.

Visual comparison of original [69] and segmented images using state of the art (FCN [27], UNet-R(34) [29], FPN [60], Fast-SCNN [58], UNet++ [30], DeepLabV3#layer 1 [16], S-FPN [60], Segformer-B1 [66], DeepLabV3+ [13], Trans4PASS-S [35], DANet [18]) and proposed method in the Cityscapes dataset.

(Original image was taken from Cityscapes dataset which is freely available on [69]).

More »

Fig 8 Expand