2021
DOI: 10.3390/electronics10101187
|View full text |Cite
|
Sign up to set email alerts
|

Attention Mechanisms in CNN-Based Single Image Super-Resolution: A Brief Review and a New Perspective

Abstract: With the advance of deep learning, the performance of single image super-resolution (SR) has been notably improved by convolution neural network (CNN)-based methods. However, the increasing depth of CNNs makes them more difficult to train, which hinders the SR networks from achieving greater success. To overcome this, a wide range of related mechanisms has been introduced into the SR networks recently, with the aim of helping them converge more quickly and perform better. This has resulted in many research pap… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
17
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 38 publications
(17 citation statements)
references
References 69 publications
0
17
0
Order By: Relevance
“…Sparse encoding method uses compact dictionary trained by sparse signal representation [43]. Recently, CNN based image enhancement has been of interest, and contributes to significant improvement [44]. This work employs VDSR that shows superior performance compared to super-resolution CNN [45] in that VDSR has larger number of hidden layers and uses larger receptive field to utilize more image information.…”
Section: Intrinsic Parametersmentioning
confidence: 99%
“…Sparse encoding method uses compact dictionary trained by sparse signal representation [43]. Recently, CNN based image enhancement has been of interest, and contributes to significant improvement [44]. This work employs VDSR that shows superior performance compared to super-resolution CNN [45] in that VDSR has larger number of hidden layers and uses larger receptive field to utilize more image information.…”
Section: Intrinsic Parametersmentioning
confidence: 99%
“…The attention mechanisms have been gradually introduced into the structure of CNN. They include channel attention, spatial attention and non-local attention; these three kinds of attention mechanisms perform better on super-resolution single images [26]. Moreover, a deep neural network equipped with a control gate and feedback attention mechanism can perform pixel-wise classification for very-high-resolution remote sensing images [27].…”
Section: Introductionmentioning
confidence: 99%
“…For instance, the ResNet and DenseNet [23][24][25] structures help neural networks to learn more efficient features. Attention mechanisms [26], which have gained increasing attention from researchers [27], have been introduced into SR architectures. The channel attention proposed by Hu et al [28], which is designed for image classification CNNs, has been utilized to design the RCAN network, achieving a state-of-the-art performance.…”
Section: Introductionmentioning
confidence: 99%
“…For instance, the ResNet and DenseNet [23–25] structures help neural networks to learn more efficient features. Attention mechanisms [26], which have gained increasing attention from researchers [27], have been introduced into SR architectures. The channel attention proposed by Hu et al.…”
Section: Introductionmentioning
confidence: 99%