|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM356892093 |
| 003 |
DE-627 |
| 005 |
20250304185617.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2023.3274988
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1189.xml
|
| 035 |
|
|
|a (DE-627)NLM356892093
|
| 035 |
|
|
|a (NLM)37186533
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Ye, Dongjie
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a CSformer
|b Bridging Convolution and Transformer for Compressive Sensing
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 23.05.2023
|
| 500 |
|
|
|a Date Revised 23.05.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Convolutional Neural Networks (CNNs) dominate image processing but suffer from local inductive bias, which is addressed by the transformer framework with its inherent ability to capture global context through self-attention mechanisms. However, how to inherit and integrate their advantages to improve compressed sensing is still an open issue. This paper proposes CSformer, a hybrid framework to explore the representation capacity of local and global features. The proposed approach is well-designed for end-to-end compressive image sensing, composed of adaptive sampling and recovery. In the sampling module, images are measured block-by-block by the learned sampling matrix. In the reconstruction stage, the measurements are projected into an initialization stem, a CNN stem, and a transformer stem. The initialization stem mimics the traditional reconstruction of compressive sensing but generates the initial reconstruction in a learnable and efficient manner. The CNN stem and transformer stem are concurrent, simultaneously calculating fine-grained and long-range features and efficiently aggregating them. Furthermore, we explore a progressive strategy and window-based transformer block to reduce the parameters and computational complexity. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing, which achieves superior performance compared to state-of-the-art methods on different datasets. Our codes is available at: https://github.com/Lineves7/CSformer
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Ni, Zhangkai
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Hanli
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Jian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Shiqi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Kwong, Sam
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 32(2023) vom: 26., Seite 2827-2842
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:32
|g year:2023
|g day:26
|g pages:2827-2842
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2023.3274988
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 32
|j 2023
|b 26
|h 2827-2842
|