2022 7th International Conference on Image and Signal Processing and Their Applications (ISPA) 2022
DOI: 10.1109/ispa54004.2022.9786367
|View full text |Cite
|
Sign up to set email alerts
|

SwinT-Unet: Hybrid architecture for Medical Image Segmentation Based on Swin transformer block and Dual-Scale Information

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
2
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 11 publications
(4 citation statements)
references
References 19 publications
0
4
0
Order By: Relevance
“…The standard transformer performs global self-attention in images, whose computation is quadratic in complexity to the input vector and is not suitable for high-resolution images, especially for large computational tasks, such as remote sensing data processing 27 33 Swin Transformer proposes to perform self-attention in nonoverlapping windows. Computational complexity of a global MSA module and a window based one W-MSA is Ω(MSA)=4 hωC2+2(hωfalse)2C,Ω(WMSA)=4 hωC2+2M2hωC,where h,ω, and C are the length, width, and number of channels of feature map, respectively, and M is the size of window.…”
Section: Methodsmentioning
confidence: 99%
“…The standard transformer performs global self-attention in images, whose computation is quadratic in complexity to the input vector and is not suitable for high-resolution images, especially for large computational tasks, such as remote sensing data processing 27 33 Swin Transformer proposes to perform self-attention in nonoverlapping windows. Computational complexity of a global MSA module and a window based one W-MSA is Ω(MSA)=4 hωC2+2(hωfalse)2C,Ω(WMSA)=4 hωC2+2M2hωC,where h,ω, and C are the length, width, and number of channels of feature map, respectively, and M is the size of window.…”
Section: Methodsmentioning
confidence: 99%
“…Furthermore, a data-efficient image transformer (DeiT) is presented in [23], indicating that Transformer can be trained on midsize datasets, and a more robust Transformer can be obtained by combining it with the distillation method. In [24], a hierarchical Swin Transformer is developed. The authors of [24] achieved state-of-the-art performance on image classification, object detection, and semantic segmentation by considering Swin Transformer as a vision backbone.…”
Section: Introductionmentioning
confidence: 99%
“…In [24], a hierarchical Swin Transformer is developed. The authors of [24] achieved state-of-the-art performance on image classification, object detection, and semantic segmentation by considering Swin Transformer as a vision backbone. The success of ViT, DeiT, and Swin Transformer in image recognition tasks demonstrates the potential for Transformer to be applied in the vision domain.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation