An Optimization for Convolutional Network Layers Using the Viola-Jones Framework and Ternary Weight Networks

2021 ◽  
pp. 1-6
Author(s):  
Rhys Agombar ◽  
Christian Bauckhage ◽  
Max Luebbering ◽  
Rafet Sifa
Keyword(s):  
Convolutional Network ◽  
Network Layers

scholarly journals Seeing it all: Convolutional network layers map the function of the human visual system

NeuroImage ◽  
2017 ◽  
Vol 152 ◽  
pp. 184-194 ◽  
Author(s):  
Michael Eickenberg ◽  
Alexandre Gramfort ◽  
Gaël Varoquaux ◽  
Bertrand Thirion
Keyword(s):  
Visual System ◽  
Human Visual System ◽  
Convolutional Network ◽  
Network Layers

DeepGCNs-Att: Point cloud semantic segmentation with contextual point representations

2021 ◽  
pp. 1-10
Author(s):  
Bin Jiang ◽  
Xinyu Wang ◽  
Li Huang ◽  
Jian Xiao
Keyword(s):  
Neural Networks ◽  
Point Cloud ◽  
Semantic Segmentation ◽  
Global Features ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Network Layers ◽  
Speed Up ◽  
Network Backbone ◽  
Context Features

 Graph Convolutional Networks are able to characterize non-Euclidean spaces effectively compared with traditional Convolutional Neural Networks, which can extract the local features of the point cloud using deep neural networks, but it cannot make full use of the global features of the point cloud for semantic segmentation. To solve this problem, this paper proposes a novel network structure called DeepGCNs-Att that enables deep Graph Convolutional Network to aggregate global context features efficiently. Moreover, to speed up the computation, we add an Attention layer after the Graph Convolutional Network Backbone Block to mutually enhance the connection between the distant points of the non-Euclidean space. Our model is tested on the standard benchmark S3DIS. By comparing with other deep Graph Convolutional Networks, our DeepGCNs-Att’s mIoU has at least two percent higher than that of all other models and even shows excellent results in space complexity and computational complexity under the same number of Graph Convolutional Network layers.

Extraverts Have Larger Social Network Layers

2011 ◽  
Vol 32 (3) ◽  
pp. 161-169 ◽  
Author(s):  
Thomas V. Pollet ◽  
Sam G. B. Roberts ◽  
Robin I. M. Dunbar
Keyword(s):  
Social Network ◽  
Social Relationships ◽  
Outer Layer ◽  
Network Size ◽  
Emotional Intensity ◽  
Emotional Closeness ◽  
Network Layer ◽  
Network Layers ◽  
Social Network Size

Previous studies showed that extraversion influences social network size. However, it is unclear how extraversion affects the size of different layers of the network, and how extraversion relates to the emotional intensity of social relationships. We examined the relationships between extraversion, network size, and emotional closeness for 117 individuals. The results demonstrated that extraverts had larger networks at every layer (support clique, sympathy group, outer layer). The results were robust and were not attributable to potential confounds such as sex, though they were modest in size (raw correlations between extraversion and size of network layer, .20 < r < .23). However, extraverts were not emotionally closer to individuals in their network, even after controlling for network size. These results highlight the importance of considering not just social network size in relation to personality, but also the quality of relationships with network members.

Effective Multi-Layer Security for Campus Network

2015 ◽  
Vol 2 ◽  
pp. 6
Author(s):  
Isiaka Ajewale Alimi
Keyword(s):  
Network Architecture ◽  
Communication Systems ◽  
Denial Of Service ◽  
High Rate ◽  
Campus Network ◽  
Security Measures ◽  
Security Breaches ◽  
Security Technologies ◽  
Network Layers ◽  
Firewall System

The development in different communication systems as well as multimedia applications and services leads to high rate of Internet usage. However, transmission of information over such networks can be compromised and security breaches such as virus, denial of service, unauthorized access, and theft of proprietary information which may have devastating impact on the system may occur if adequate security measures are not employed. Consequently, building viable, effective, and safe network is one of the main technical challenges of information transmission in campus networks. Furthermore, it has been observed that, network threats and attacks exist from the lower layers of network traffic to the application layer; therefore, this paper proposes an effective multi-layer firewall system for augmenting the functionalities of other network security technologies due to the fact that, irrespective of the type of access control being employed, attacks are still bound to occur. The effectiveness of the proposed network architecture is demonstrated using Cisco Packet Tracer. The simulation results show that, implementation of the proposed topology is viable and offers reasonable degree of security at different network layers.

scholarly journals Knowledge and Geo-Object Based Graph Convolutional Network for Remote Sensing Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3848
Author(s):  
Wei Cui ◽  
Meng Yao ◽  
Yuanjie Hao ◽  
Ziwei Wang ◽  
Xin He ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Prior Knowledge ◽  
Contextual Information ◽  
Information Aggregation ◽  
Semantic Segmentation ◽  
Spatial Correlations ◽  
Convolutional Network ◽  
Object Based ◽  
Graph Neural Networks ◽  
Salt And Pepper

Pixel-based semantic segmentation models fail to effectively express geographic objects and their topological relationships. Therefore, in semantic segmentation of remote sensing images, these models fail to avoid salt-and-pepper effects and cannot achieve high accuracy either. To solve these problems, object-based models such as graph neural networks (GNNs) are considered. However, traditional GNNs directly use similarity or spatial correlations between nodes to aggregate nodes’ information, which rely too much on the contextual information of the sample. The contextual information of the sample is often distorted, which results in a reduction in the node classification accuracy. To solve this problem, a knowledge and geo-object-based graph convolutional network (KGGCN) is proposed. The KGGCN uses superpixel blocks as nodes of the graph network and combines prior knowledge with spatial correlations during information aggregation. By incorporating the prior knowledge obtained from all samples of the study area, the receptive field of the node is extended from its sample context to the study area. Thus, the distortion of the sample context is overcome effectively. Experiments demonstrate that our model is improved by 3.7% compared with the baseline model named Cluster GCN and 4.1% compared with U-Net.

scholarly journals SACN: A Novel Rotating Face Detector Based on Architecture Search

Electronics ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 558
Author(s):  
Anping Song ◽  
Xiaokang Xu ◽  
Xinyi Zhai
Keyword(s):  
Face Detection ◽  
Human Face ◽  
Angle Error ◽  
Rotation Invariant ◽  
Convolutional Network ◽  
Data Set ◽  
Practical Applications ◽  
Model Size ◽  
Average Angle ◽  
Face Detector

Rotation-Invariant Face Detection (RIPD) has been widely used in practical applications; however, the problem of the adjusting of the rotation-in-plane (RIP) angle of the human face still remains. Recently, several methods based on neural networks have been proposed to solve the RIP angle problem. However, these methods have various limitations, including low detecting speed, model size, and detecting accuracy. To solve the aforementioned problems, we propose a new network, called the Searching Architecture Calibration Network (SACN), which utilizes architecture search, fully convolutional network (FCN) and bounding box center cluster (CC). SACN was tested on the challenging Multi-Oriented Face Detection Data Set and Benchmark (MOFDDB) and achieved a higher detecting accuracy and almost the same speed as existing detectors. Moreover, the average angle error is optimized from the current 12.6° to 10.5°.

Sign in / Sign up

Export Citation Format

Share Document