Super-resolution Reconstruction Using Multiconnection Deep Residual Network Combined an Improved Loss Function for Single-frame Image

Peng, Yungui

doi:10.1007/s11042-019-7544-1

Cited by 8 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LSTM units in the hidden layer are fully connected through circular connection, as shown in Figure 3. Since curve fitting is a regression problem, MSE is used in the loss function [18].…”

Section: Analysis Of Normal Power Consumption Prediction Effectmentioning

confidence: 99%

Integrated Energy Security Defense Monitoring Software Based on Cloud Computing

Shang

2022

Security and Communication Networks

View full text Add to dashboard Cite

In order to solve the problem of outlier detection of integrated energy security defense monitoring software, an automatic detection algorithm of virtual machine power anomaly in a cloud computing environment is proposed. The method is implemented through three main steps: data preprocessing, pattern recognition, and prediction of virtual machine power anomaly detection model. It is found through experiments that with the increase of node number, the convergent iterations of the model are less and RMSE is lower, but the increase of node number of the hidden layer will lead to a longer model running time. When the number of nodes reaches 100, the test results of the validation set are significantly improved, and the loss function of the validation set is minimal when the number of nodes is less than 30 iterations. Finally, the hidden layer of the model consists of 100 LSTM units, followed by a dense output layer with 1 neuron, and 0.2 loss, retrospection, and foresight equal to 1. Adam optimizer was used to train LSTM and stop it in advance after 50 iteration steps. Its parameters remained default, with a learning rate of 0.001 and attenuation of 0.9. It can be seen that this model can well predict the virtual machine power consumption data and effectively solve the problem of outlier detection of integrated energy security defense monitoring software.

show abstract

“…LSTM units in the hidden layer are fully connected through circular connection, as shown in Figure 3. Since curve fitting is a regression problem, MSE is used in the loss function [18].…”

Section: Analysis Of Normal Power Consumption Prediction Effectmentioning

confidence: 99%

Integrated Energy Security Defense Monitoring Software Based on Cloud Computing

Shang

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Various network structures have been developed, such as deep network with residual learning [14], Laplace pyramid structure [15], residual block [21], and residual dense network [22]. Besides supervised learning and unsupervised learning [23][24][25][26], reinforcement learning [27][28][29] are also introduced to solve the problem of image super-resolution in recent years. Specifically, the literature [30] has a systematic description of image super resolution.…”

Section: Deep Learning For Image Super-resolutionmentioning

confidence: 99%

Design of Network Cascade Structure for Image Super-Resolution

Zhang¹,

Wang²,

Zheng³

et al. 2021

Journal of New Media

View full text Add to dashboard Cite

Image super resolution is an important field of computer research. The current mainstream image super-resolution technology is to use deep learning to mine the deeper features of the image, and then use it for image restoration. However, most of these models mentioned above only trained the images in a specific scale and do not consider the relationships between different scales of images. In order to utilize the information of images at different scales, we design a cascade network structure and cascaded super-resolution convolutional neural networks. This network contains three cascaded FSRCNNs. Due to each sub FSRCNN can process a specific scale image, our network can simultaneously exploit three scale images, and can also use the information of three different scales of images. Experiments on multiple datasets confirmed that the proposed network can achieve better performance for image SR.

show abstract

“…Compared with many traditional SISR methods based on machine learning, the simple structure of the SRCNN model shows remarkable performance in image super-resolution problems. Then, a large number of CNN-based models were proposed to obtain more accurate SISR results using different techniques to improve the quality of the reconstructed image: the design of the network structure with residuals [18][19][20][21][22]; generative adversarial networks [23]; neural architecture search [24,25]; various attention mechanisms [26], and other technologies [27,28]. With the improvement of architecture, this field has indeed made rich progress.…”

Section: Introductionmentioning

confidence: 99%

GRAN: Ghost Residual Attention Network for Single Image Super Resolution

Niu¹,

Wang²,

Zhu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recently, many works have designed wider and deeper networks to achieve higher image super-resolution performance. Despite their outstanding performance, they still suffer from high computational resources, preventing them from directly applying to embedded devices. To reduce the computation resources and maintain performance, we propose a novel Ghost Residual Attention Network (GRAN) for efficient super-resolution. This paper introduces Ghost Residual Attention Block (GRAB) groups to overcome the drawbacks of the standard convolutional operation, i.e., redundancy of the intermediate feature. GRAB consists of the Ghost Module and Channel and Spatial Attention Module (CSAM) to alleviate the generation of redundant features. Specifically, Ghost Module can reveal information underlying intrinsic features by employing linear operations to replace the standard convolutions. Reducing redundant features by the Ghost Module, our model decreases memory and computing resource requirements in the network. The CSAM pays more comprehensive attention to where and what the feature extraction is, which is critical to recovering the image details. Experiments conducted on the benchmark datasets demonstrate the superior performance of our method in both qualitative and quantitative. Compared to the baseline models,

show abstract

Super-resolution Reconstruction Using Multiconnection Deep Residual Network Combined an Improved Loss Function for Single-frame Image

Cited by 8 publications

References 11 publications

Integrated Energy Security Defense Monitoring Software Based on Cloud Computing

Integrated Energy Security Defense Monitoring Software Based on Cloud Computing

Design of Network Cascade Structure for Image Super-Resolution

GRAN: Ghost Residual Attention Network for Single Image Super Resolution

Contact Info

Product

Resources

About