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

Zhu, Hongyu; Xie, Chao; Fei, Yeqi; Tao, Huanjie

doi:10.3390/electronics10101187

Cited by 38 publications

(17 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

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%

Calibrating a Three-Viewpoints Thermal Camera with Few Correspondences

Kim

Lee

2023

J Sign Process Syst

View full text Add to dashboard Cite

This paper proposes the approach to calibration of a thermal camera that has three viewpoints. This work estimates the intrinsic parameters of the camera by establishing geometric relationship between real-world scene points and image points. This work estimates the extrinsic parameters, i.e., rotation and translation of the camera using vanishing points. The present work is different from the existed work on the calibration from three perspectives. The first one is that this work calibrates thermal camera with three viewpoints whose relative rotation is greater than 180-degree. The second one is that the viewpoints shares few overlapped areas due to the structure of the camera, so the proposed work is more challenging and difficult than the previous work on the calibration. The third one is that projected image of a scene requires quality enhancement for the calibration. Since few overlapped images are given a priori, feature matching cannot be used for the calibration. Instead of using correspondence matching, vanishing points are exploited to estimate relative rotations of cameras. The intrinsic parameters are estimated by capturing thermal-checkerboard followed by image processing. Experimental results show the accuracy and stability of the proposed approach for estimation of the intrinsic and the extrinsic parameters.

show abstract

Section: Intrinsic Parametersmentioning

confidence: 99%

Calibrating a Three-Viewpoints Thermal Camera with Few Correspondences

Kim

Lee

2023

J Sign Process Syst

View full text Add to dashboard Cite

show abstract

“…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%

Landslide Detection from Open Satellite Imagery Using Distant Domain Transfer Learning

et al. 2021

View full text Add to dashboard Cite

Using convolutional neural network (CNN) methods and satellite images for landslide identification and classification is a very efficient and popular task in geological hazard investigations. However, traditional CNNs have two disadvantages: (1) insufficient training images from the study area and (2) uneven distribution of the training set and validation set. In this paper, we introduced distant domain transfer learning (DDTL) methods for landslide detection and classification. We first introduce scene classification satellite imagery into the landslide detection task. In addition, in order to more effectively extract information from satellite images, we innovatively add an attention mechanism to DDTL (AM-DDTL). In this paper, the Longgang study area, a district in Shenzhen City, Guangdong Province, has only 177 samples as the landslide target domain. We examine the effect of DDTL by comparing three methods: the convolutional CNN, pretrained model and DDTL. We compare different attention mechanisms based on the DDTL. The experimental results show that the DDTL method has better detection performance than the normal CNN, and the AM-DDTL models achieve 94% classification accuracy, which is 7% higher than the conventional DDTL method. The requirements for the detection and classification of potential landslides at different disaster zones can be met by applying the AM-DDTL algorithm, which outperforms traditional CNN methods.

show abstract

“…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%

Deep coordinate attention network for single image super‐resolution

Xie

Zhu

Fei

2021

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Deep learning techniques and deep networks have recently been extensively studied and widely applied to single image super-resolution (SR). Among them, channel attention has garnered the most focus owing to its significant boost in the presentational power of a convolutional neural network. However, the original channel attention neglects the critical importance of the positional information, thus imposing performance limitations. Here, a novel perspective, namely, a coordinate attention mechanism, is explored to alleviate the aforementioned problem, and accordingly result in an enhanced SR performance. Specifically, a deep residual coordinate attention SR network (COSR) is proposed, which mainly incorporates the presented coordinate attention blocks into a deep nested residual structure. The coordinate attention captures the positional information by computing the average value vector from the two spatial directions, thus aggregating the features in different coordinates. The nested residual blocks pass low-frequency information from the top to the end through the skip connection lines, allowing convolution filters to concentrate more on high-frequency textures and edges, thereby reducing the difficulty of reconstruction. Extensive experiments demonstrate that our proposed COSR achieves a better performance and exceeds many state-of-the-art SR methods in terms of both quantitative metrics and visual quality.

show abstract

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

Cited by 38 publications

References 69 publications

Calibrating a Three-Viewpoints Thermal Camera with Few Correspondences

Calibrating a Three-Viewpoints Thermal Camera with Few Correspondences

Landslide Detection from Open Satellite Imagery Using Distant Domain Transfer Learning

Deep coordinate attention network for single image super‐resolution

Contact Info

Product

Resources

About