2022
DOI: 10.3390/rs14071638
|View full text |Cite
|
Sign up to set email alerts
|

BES-Net: Boundary Enhancing Semantic Context Network for High-Resolution Image Semantic Segmentation

Abstract: This paper focuses on the high-resolution (HR) remote sensing images semantic segmentation task, whose goal is to predict semantic labels in a pixel-wise manner. Due to the rich complexity and heterogeneity of information in HR remote sensing images, the ability to extract spatial details (boundary information) and semantic context information dominates the performance in segmentation. In this paper, based on the frequently used fully convolutional network framework, we propose a boundary enhancing semantic co… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
10
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8

Relationship

1
7

Authors

Journals

citations
Cited by 27 publications
(10 citation statements)
references
References 49 publications
0
10
0
Order By: Relevance
“…Finally, it adopts a loss function for the edge detection network branch and sets a weight parameter for this loss to balance its proportion with the semantic segmentation loss. Both BES-Nets [22,44] designed edge-extraction branches and use edge loss supervision. Furthermore, they both constructed fusion modules to fuse edge features with high-level semantic features of the main branch.…”
Section: Edge Extractionmentioning
confidence: 99%
See 2 more Smart Citations
“…Finally, it adopts a loss function for the edge detection network branch and sets a weight parameter for this loss to balance its proportion with the semantic segmentation loss. Both BES-Nets [22,44] designed edge-extraction branches and use edge loss supervision. Furthermore, they both constructed fusion modules to fuse edge features with high-level semantic features of the main branch.…”
Section: Edge Extractionmentioning
confidence: 99%
“…In this work, we elaborately devise an edge branch to extract edge features explicitly which is shown in Figure 5. In prior approaches, the most commonly used edge-extraction method is to learn edge information from the intermediate layers through a simple convolutional layer [22,44]. These learnable convolution kernels perform feature extraction on all pixels equally in the feature map and are combined with an edge loss (e.g., BCE loss) to guide model training.…”
Section: Edge Branchmentioning
confidence: 99%
See 1 more Smart Citation
“…As shown in Table 1, there are six categories of land cover (e.g., impervious surface, building, low vegetation, tree, car and clutter) used for evaluating the performance (i.e., mIoU) of the models. Next, some advanced methods are selected for comparison such as Deeplabv3+ [95], GCNet [96] and BES-Net [97] from nature and remote sensing scenes. As reported in the 5th and 7th rows of Table 7, based on ViT-B [14], our proposed CSPT brings 2.27% mIoU gain compared with employing SP(IN1K) on Upernet [73].…”
Section: Object Detectionmentioning
confidence: 99%
“…Semantic segmentation, aiming to predict the semantic category of each pixel in an image, is a fundamental problem of remote sensing [1,2] and multimedia applications [3][4][5]. For example, it is of critical significance to autonomous vehicles, since exact remote scene segmentation at pixel level can ensure the reliable operation of autonomous vehicles in complicated real-world environments.…”
Section: Introductionmentioning
confidence: 99%