scholarly journals Multi-Resolution Supervision Network with an Adaptive Weighted Loss for Desert Segmentation

2021 ◽  
Vol 13 (11) ◽  
pp. 2054
Author(s):  
Lexuan Wang ◽  
Liguo Weng ◽  
Min Xia ◽  
Jia Liu ◽  
Haifeng Lin
Keyword(s):  
Loss Function ◽  
Large Scale ◽  
Convergence Speed ◽  
Learning Ability ◽  
Segmentation Result ◽  
Image Size ◽  
Multi Scale ◽  
Optimization Task ◽  
Large Scale Change ◽  
Segmentation Models

Desert segmentation of remote sensing images is the basis of analysis of desert area. Desert images are usually characterized by large image size, large-scale change, and irregular location distribution of surface objects. The multi-scale fusion method is widely used in the existing deep learning segmentation models to solve the above problems. Based on the idea of multi-scale feature extraction, this paper took the segmentation results of each scale as an independent optimization task and proposed a multi-resolution supervision network (MrsSeg) to further improve the desert segmentation result. Due to the different optimization difficulty of each branch task, we also proposed an auxiliary adaptive weighted loss function (AWL) to automatically optimize the training process. MrsSeg first used a lightweight backbone to extract different-resolution features, then adopted a multi-resolution fusion module to fuse the local information and global information, and finally, a multi-level fusion decoder was used to aggregate and merge the features at different levels to get the desert segmentation result. In this method, each branch loss was treated as an independent task, AWL was proposed to calculate and adjust the weight of each branch. By giving priority to the easy tasks, the improved loss function could effectively improve the convergence speed of the model and the desert segmentation result. The experimental results showed that MrsSeg-AWL effectively improved the learning ability of the model and has faster convergence speed, lower parameter complexity, and more accurate segmentation results.

Multi-Scale Collaborative Network for Human Pose Estimation

2019 ◽  
Vol 16 (04) ◽  
pp. 1941003
Author(s):  
Chunsheng Guo ◽  
Jialuo Zhou ◽  
Wenlong Du ◽  
Xuguang Zhang
Keyword(s):  
Loss Function ◽  
Pose Estimation ◽  
Large Scale ◽  
Human Pose Estimation ◽  
Small Scale ◽  
Feature Maps ◽  
Multi Scale ◽  
Human Pose ◽  
Processing Network ◽  
Weight Coefficients

Human pose estimation is a fundamental but challenging task in computer vision. The estimation of human pose mainly depends on the global information of the keypoint type and the local information of the keypoint location. However, the consistency of the cascading process makes it difficult for each stacking network to form a differentiation and collaboration mechanism. In order to solve these problems, this paper introduces a new human pose estimation framework called Multi-Scale Collaborative (MSC) network. The pre-processing network forms feature maps of different sizes, and dispatches them to various locations of the stack network, with small-scale features reaching the front-end stacking network and large-scale features reaching the back-end stacking network. A new loss function is proposed for MSC network. Different keypoints have different weight coefficients of loss function at different scales, and the keypoint weight coefficients are dynamically adjusted from the top hourglass network to the bottom hourglass network. Experimental results show that the proposed method is competitive in MPII and LSP challenge leaderboard among the state-of-the-art methods.

scholarly journals A New Deep Learning Algorithm for SAR Scene Classification Based on Spatial Statistical Modeling and Features Re-Calibration

Sensors ◽  
2019 ◽  
Vol 19 (11) ◽  
pp. 2479 ◽  
Author(s):  
Lifu Chen ◽  
Xianliang Cui ◽  
Zhenhong Li ◽  
Zhihui Yuan ◽  
Jin Xing ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Learning Algorithm ◽  
High Accuracy ◽  
Learning Ability ◽  
Scene Classification ◽  
Gaussian Derivative ◽  
Multi Scale ◽  
Spatial Features ◽  
The Mean

Synthetic Aperture Radar (SAR) scene classification is challenging but widely applied, in which deep learning can play a pivotal role because of its hierarchical feature learning ability. In the paper, we propose a new scene classification framework, named Feature Recalibration Network with Multi-scale Spatial Features (FRN-MSF), to achieve high accuracy in SAR-based scene classification. First, a Multi-Scale Omnidirectional Gaussian Derivative Filter (MSOGDF) is constructed. Then, Multi-scale Spatial Features (MSF) of SAR scenes are generated by weighting MSOGDF, a Gray Level Gradient Co-occurrence Matrix (GLGCM) and Gabor transformation. These features were processed by the Feature Recalibration Network (FRN) to learn high-level features. In the network, the Depthwise Separable Convolution (DSC), Squeeze-and-Excitation (SE) Block and Convolution Neural Network (CNN) are integrated. Finally, these learned features will be classified by the Softmax function. Eleven types of SAR scenes obtained from four systems combining different bands and resolutions were trained and tested, and a mean accuracy of 98.18% was obtained. To validate the generality of FRN-MSF, five types of SAR scenes sampled from two additional large-scale Gaofen-3 and TerraSAR-X images were evaluated for classification. The mean accuracy of the five types reached 94.56%; while the mean accuracy for the same five types of the former tested 11 types of scene was 96%. The high accuracy indicates that the FRN-MSF is promising for SAR scene classification without losing generality.

Partnerships Generate Co-Benefits in Agricultural Stream Restoration (Canterbury, New Zealand)

2020 ◽  
Vol 4 (1) ◽  
Author(s):  
Catherine M. Febria ◽  
Maggie Bayfield ◽  
Kathryn E. Collins ◽  
Hayley S. Devlin ◽  
Brandon C. Goeller ◽  
...  
Keyword(s):  
New Zealand ◽  
Large Scale ◽  
Agricultural Land ◽  
Indigenous Rights ◽  
Freshwater Ecosystem ◽  
Reduced Pressure ◽  
Ecosystem Integrity ◽  
Riparian Management ◽  
Scale Change ◽  
Large Scale Change

In Aotearoa New Zealand, agricultural land-use intensification and decline in freshwater ecosystem integrity pose complex challenges for science and society. Despite riparian management programmes across the country, there is frustration over a lack in widespread uptake, upfront financial costs, possible loss in income, obstructive legislation and delays in ecological recovery. Thus, social, economic and institutional barriers exist when implementing and assessing agricultural freshwater restoration. Partnerships are essential to overcome such barriers by identifying and promoting co-benefits that result in amplifying individual efforts among stakeholder groups into coordinated, large-scale change. Here, we describe how initial progress by a sole farming family at the Silverstream in the Canterbury region, South Island, New Zealand, was used as a catalyst for change by the Canterbury Waterway Rehabilitation Experiment, a university-led restoration research project. Partners included farmers, researchers, government, industry, treaty partners (Indigenous rights-holders) and practitioners. Local capacity and capability was strengthened with practitioner groups, schools and the wider community. With partnerships in place, co-benefits included lowered costs involved with large-scale actions (e.g., earth moving), reduced pressure on individual farmers to undertake large-scale change (e.g., increased participation and engagement), while also legitimising the social contracts for farmers, scientists, government and industry to engage in farming and freshwater management. We describe contributions and benefits generated from the project and describe iterative actions that together built trust, leveraged and aligned opportunities. These actions were scaled from a single farm to multiple catchments nationally.

scholarly journals Public Awareness: What Climate Change Scientists Should Consider

2020 ◽  
Vol 12 (20) ◽  
pp. 8369
Author(s):  
Mohammad Rahimi
Keyword(s):  
Climate Change ◽  
Social Media ◽  
Large Scale ◽  
Public Awareness ◽  
Connected Network ◽  
Multi Scale ◽  
Valuable Addition ◽  
Scientific Approach ◽  
Design Solutions ◽  
Mitigate Climate Change

In this Opinion, the importance of public awareness to design solutions to mitigate climate change issues is highlighted. A large-scale acknowledgment of the climate change consequences has great potential to build social momentum. Momentum, in turn, builds motivation and demand, which can be leveraged to develop a multi-scale strategy to tackle the issue. The pursuit of public awareness is a valuable addition to the scientific approach to addressing climate change issues. The Opinion is concluded by providing strategies on how to effectively raise public awareness on climate change-related topics through an integrated, well-connected network of mavens (e.g., scientists) and connectors (e.g., social media influencers).

scholarly journals The Relevance of Inequality Research in Sociology for Inequality Reduction

2021 ◽  
Vol 7 ◽  
pp. 237802312110201
Author(s):  
Thomas A. DiPrete ◽  
Brittany N. Fox-Williams
Keyword(s):  
Social Sciences ◽  
Social Policy ◽  
Social Inequality ◽  
Large Scale ◽  
Sociological Research ◽  
Life Chances ◽  
The Past ◽  
The Social ◽  
Large Scale Change ◽  
The Subject

Social inequality is a central topic of research in the social sciences. Decades of research have deepened our understanding of the characteristics and causes of social inequality. At the same time, social inequality has markedly increased during the past 40 years, and progress on reducing poverty and improving the life chances of Americans in the bottom half of the distribution has been frustratingly slow. How useful has sociological research been to the task of reducing inequality? The authors analyze the stance taken by sociological research on the subject of reducing inequality. They identify an imbalance in the literature between the discipline’s continual efforts to motivate the plausibility of large-scale change and its lesser efforts to identify feasible strategies of change either through social policy or by enhancing individual and local agency with the potential to cumulate into meaningful progress on inequality reduction.

scholarly journals Multi-Scale Ionospheric Anomalies Monitoring and Spatio-Temporal Analysis during Intense Storm

Atmosphere ◽  
2021 ◽  
Vol 12 (2) ◽  
pp. 215
Author(s):  
Na Cheng ◽  
Shuli Song ◽  
Wei Li
Keyword(s):  
Magnetic Storm ◽  
Large Scale ◽  
Temporal Dynamics ◽  
Ionospheric Disturbance ◽  
Ionospheric Scintillation ◽  
Small Scale ◽  
Electron Content ◽  
Total Electron ◽  
Multi Scale ◽  
Intense Storm

The ionosphere is a significant component of the geospace environment. Storm-induced ionospheric anomalies severely affect the performance of Global Navigation Satellite System (GNSS) Positioning, Navigation, and Timing (PNT) and human space activities, e.g., the Earth observation, deep space exploration, and space weather monitoring and prediction. In this study, we present and discuss the multi-scale ionospheric anomalies monitoring over China using the GNSS observations from the Crustal Movement Observation Network of China (CMONOC) during the 2015 St. Patrick’s Day storm. Total Electron Content (TEC), Ionospheric Electron Density (IED), and the ionospheric disturbance index are used to monitor the storm-induced ionospheric anomalies. This study finally reveals the occurrence of the large-scale ionospheric storms and small-scale ionospheric scintillation during the storm. The results show that this magnetic storm was accompanied by a positive phase and a negative phase ionospheric storm. At the beginning of the main phase of the magnetic storm, both TEC and IED were significantly enhanced. There was long-duration depletion in the topside ionospheric TEC during the recovery phase of the storm. This study also reveals the response and variations in regional ionosphere scintillation. The Rate of the TEC Index (ROTI) was exploited to investigate the ionospheric scintillation and compared with the temporal dynamics of vertical TEC. The analysis of the ROTI proved these storm-induced TEC depletions, which suppressed the occurrence of the ionospheric scintillation. To improve the spatial resolution for ionospheric anomalies monitoring, the regional Three-Dimensional (3D) ionospheric model is reconstructed by the Computerized Ionospheric Tomography (CIT) technique. The spatial-temporal dynamics of ionospheric anomalies during the severe geomagnetic storm was reflected in detail. The IED varied with latitude and altitude dramatically; the maximum IED decreased, and the area where IEDs were maximum moved southward.

scholarly journals Non-Intrusive Load Disaggregation Based on a Multi-Scale Attention Residual Network

2020 ◽  
Vol 10 (24) ◽  
pp. 9132
Author(s):  
Liguo Weng ◽  
Xiaodong Zhang ◽  
Junhao Qian ◽  
Min Xia ◽  
Yiqing Xu ◽  
...  
Keyword(s):  
Smart Grids ◽  
Recognition Rate ◽  
Low Frequency ◽  
Attention Mechanism ◽  
Learning Ability ◽  
Residual Network ◽  
Multi Scale ◽  
Energy Disaggregation ◽  
Benchmark Datasets ◽  
Load Disaggregation

Non-intrusive load disaggregation (NILD) is of great significance to the development of smart grids. Current energy disaggregation methods extract features from sequences, and this process easily leads to a loss of load features and difficulties in detecting, resulting in a low recognition rate of low-use electrical appliances. To solve this problem, a non-intrusive sequential energy disaggregation method based on a multi-scale attention residual network is proposed. Multi-scale convolutions are used to learn features, and the attention mechanism is used to enhance the learning ability of load features. The residual learning further improves the performance of the algorithm, avoids network degradation, and improves the precision of load decomposition. The experimental results on two benchmark datasets show that the proposed algorithm has more advantages than the existing algorithms in terms of load disaggregation accuracy and judgments of the on/off state, and the attention mechanism can further improve the disaggregation accuracy of low-frequency electrical appliances.

scholarly journals Assessing the Impact of the Loss Function, Architecture and Image Type for Deep Learning-Based Wildfire Segmentation

2021 ◽  
Vol 11 (15) ◽  
pp. 7046
Author(s):  
Jorge Francisco Ciprián-Sánchez ◽  
Gilberto Ochoa-Ruiz ◽  
Lucile Rossi ◽  
Frédéric Morandini
Keyword(s):  
Deep Learning ◽  
Loss Function ◽  
State Of The Art ◽  
Fire Detection ◽  
Loss Functions ◽  
Wildfire Spread ◽  
Combine Information ◽  
The Impact ◽  
Image Type ◽  
Segmentation Models

Wildfires stand as one of the most relevant natural disasters worldwide, particularly more so due to the effect of climate change and its impact on various societal and environmental levels. In this regard, a significant amount of research has been done in order to address this issue, deploying a wide variety of technologies and following a multi-disciplinary approach. Notably, computer vision has played a fundamental role in this regard. It can be used to extract and combine information from several imaging modalities in regard to fire detection, characterization and wildfire spread forecasting. In recent years, there has been work pertaining to Deep Learning (DL)-based fire segmentation, showing very promising results. However, it is currently unclear whether the architecture of a model, its loss function, or the image type employed (visible, infrared, or fused) has the most impact on the fire segmentation results. In the present work, we evaluate different combinations of state-of-the-art (SOTA) DL architectures, loss functions, and types of images to identify the parameters most relevant to improve the segmentation results. We benchmark them to identify the top-performing ones and compare them to traditional fire segmentation techniques. Finally, we evaluate if the addition of attention modules on the best performing architecture can further improve the segmentation results. To the best of our knowledge, this is the first work that evaluates the impact of the architecture, loss function, and image type in the performance of DL-based wildfire segmentation models.

scholarly journals Multi-scale modelling of a large scale shell-and-tube latent heat storage system for direct steam generation power plants

2020 ◽  
Author(s):  
Clément Beust ◽  
Erwin Franquet ◽  
Jean-Pierre Bédécarrats ◽  
Pierre Garcia ◽  
Jérôme Pouvreau ◽  
...  
Keyword(s):  
Power Plants ◽  
Large Scale ◽  
Storage System ◽  
Steam Generation ◽  
Latent Heat Storage ◽  
Multi Scale ◽  
Direct Steam ◽  
Scale Modelling ◽  
Shell And Tube ◽  
Generation Power

scholarly journals EyeHealer: A large-scale anterior eye segment dataset with eye structure and lesion annotations

2021 ◽  
Author(s):  
Wenjia Cai ◽  
Jie Xu ◽  
Ke Wang ◽  
Xiaohong Liu ◽  
Wenqin Xu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Image Annotation ◽  
Clinical Care ◽  
Significant Proportion ◽  
Anterior Segment ◽  
Future Research ◽  
Learning Models ◽  
Anterior Eye Segment ◽  
Segmentation Models

Abstract Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide, including diseases associated with corneal pathologies, anterior chamber abnormalities (e.g. blood or inflammation) and lens diseases. The construction of an automatic tool for the segmentation of anterior segment eye lesions will greatly improve the efficiency of clinical care. With research on artificial intelligence progressing in recent years, deep learning models have shown their superiority in image classification and segmentation. The training and evaluation of deep learning models should be based on a large amount of data annotated with expertise, however, such data are relatively scarce in the domain of medicine. Herein, the authors developed a new medical image annotation system, called EyeHealer. It is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel level. Comprehensive experiments were conducted to verify its performance in disease classification and eye lesion segmentation. The results showed that semantic segmentation models outperformed medical segmentation models. This paper describes the establishment of the system for automated classification and segmentation tasks. The dataset will be made publicly available to encourage future research in this area.

Sign in / Sign up

Export Citation Format

Share Document