Learning stacking regressors for single image super-resolution

Zhang, Kaibing; Luo, Shuang; Li, Minqi; Jing, Junfeng; Lü, Jian; Xiong, Zenggang

doi:10.1007/s10489-020-01787-0

Cited by 15 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stacked regressor is used to combine multiple predictors which has been applied since a set of models performs better at burning areas at different places [40]. The principal concept of this technique is to assemble the complementary merits of multiple models to boost the total performance of the ensemble model [41]. Ensemble is one of the machine learning methods that combines the prediction results of more than one base model in order to obtain more powerful and generalizable results compared to a single model.…”

Section: Stacked Regressormentioning

confidence: 99%

Comparison of the Machine Learning Methods to Predict Wildfire Areas

BAYAT

Yildiz

2022

Turkish Journal of Science and Technology

View full text Add to dashboard Cite

In the last decades, global warming has changed the temperature. It caused an increasing the wildfire in everywhere. Wildfires affect people's social lives, animal lives, and countries' economies. Therefore new prevention and control mechanisms are required for forest fires. Artificial intelligence and neural networks have been benefited from in the management of forest fires since the 1990s. Since that time, machine learning (ML) methods have been used in environmental science in various subjects. This study aims to present a performance comparison of ML algorithms applied in fire management. In this paper, different ML models were used to forecast fire size based on various characteristics such as temperature, wind, humidity and precipitation, using records of 512 wildfires that took place in a national park in Northern Portugal.

show abstract

Section: Stacked Regressormentioning

confidence: 99%

Comparison of the Machine Learning Methods to Predict Wildfire Areas

BAYAT

Yildiz

2022

Turkish Journal of Science and Technology

View full text Add to dashboard Cite

show abstract

“…In the SR process, it is of great importance to evaluate the quality of resultant SR images and compare the performance of SR algorithms for further improvement [4]. Currently, existing SR image quality assessment [5][6][7][8][9] (SRIQA) approaches can be divided into two major types, i.e., subjective quality assessment [10] and objective quality assessment. The subjective quality assessment achieves SRIQA by the subjective test of human beings and employs the mean opinion score (MOS) or the differential mean opinion score (DMOS) as indicators to measure image quality.…”

Section: Introductionmentioning

confidence: 99%

FDANet: A frequency-domain attention network for super-resolution image quality assessment

Fan,

Li,

Zhang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

No-reference super-resolution image quality assessment (NR-SRIQA) is still a challenging task due to complicated degradation factors and the lack of reference high-resolution (HR) images. In this paper, we propose a novel NR-SRIQA framework that elaborately designs a frequency domain attention lightweight network called FDANet to predict the quality of SR images. Firstly the frequency domain attention module is used to extract the frequency domain salient map from the divided image patches, and then a frequency domain attention lightweight network is used as the backbone to learn the features in SR images to improve the performance of the network. Compared with the spatial domain attention module, the proposed frequency domain attention module is conducive to learn quality-aware features to quantify the quality of SR images. By integrating the deep learning-based features, the proposed NR-SRIQA model facilitates more compelling quality prediction but requires obviously less computational cost in contrast to compared deep networks for NR-SRIQA. Experimental results verify the superior performance of our method on two benchmark data-bases in terms of both quantitative evaluations and thorough analysis on the model deployment.

show abstract