2022
DOI: 10.1109/tits.2022.3154407
|View full text |Cite
|
Sign up to set email alerts
|

External Attention Based TransUNet and Label Expansion Strategy for Crack Detection

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
2025
2025

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 41 publications
(10 citation statements)
references
References 36 publications
0
10
0
Order By: Relevance
“…Chen et al [53] proposed the TransUNet for medical image segmentation, which merits both transformers and U-Net. Fang et al [54] presented the external attention-based TransUNet for crack detection. In addition, transformer-based methods were also used in remote sensing images.…”
Section: Transformer-based Methods In CVmentioning
confidence: 99%
“…Chen et al [53] proposed the TransUNet for medical image segmentation, which merits both transformers and U-Net. Fang et al [54] presented the external attention-based TransUNet for crack detection. In addition, transformer-based methods were also used in remote sensing images.…”
Section: Transformer-based Methods In CVmentioning
confidence: 99%
“…However, the most common CNN denoising model that is based on full-connection architecture often encounters some shortcoming to be solved, such as being unable to effectively remove the relative broadband noise, requiring a lot of training time and a large number of training samples to be effective ( Zhang et al, 2018 ). In this work, several new CNN models, namely, the fast and flexible denoising convolutional neural network (FFDNet) and Pyramid Real Image Denoising Network (PRIDNet), for flexible, effective, and fast discriminative denoising, the PRIDNet is specifically presented in detail for blind denoising of cell images through three sequential stages ( Al-Kofahi et al, 2018 ; Chen et al, 2021b ; Fang et al, 2022 ).…”
Section: Methodsmentioning
confidence: 99%
“…Fang et al [ 31 ] proposed an attention-based TransUNet for crack detection in road surfaces. The TransUNet takes the detailed texture information of detected cracks from the shallow layers and passes it to deep layers through skip connections.…”
Section: Related Workmentioning
confidence: 99%