HDPL: a hybrid descriptor for points and lines based on graph neural networks

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Zirui Guo ◽  
Huimin Lu ◽  
Qinghua Yu ◽  
Ruibin Guo ◽  
Junhao Xiao ◽  
...  
Keyword(s):  
Neural Network ◽  
Feature Matching ◽  
Feature Descriptor ◽  
Graph Structure ◽  
Multiple Features ◽  
Content Type ◽  
Geometric Relation ◽  
Line Features ◽  
Graph Neural Networks ◽  
Geometric Relationship

Purpose This paper aims to design a novel feature descriptor to improve the performance of feature matching in challenge scenes, such as low texture and wide-baseline scenes. Common descriptors are not suitable for low texture scenes and other challenging scenes mainly owing to encoding only one kind of features. The proposed feature descriptor considers multiple features and their locations, which is more expressive. Design/methodology/approach A graph neural network–based descriptors enhancement algorithm for feature matching is proposed. In this paper, point and line features are the primary concerns. In the graph, commonly used descriptors for points and lines constitute the nodes and the edges are determined by the geometric relationship between points and lines. After the graph convolution designed for incomplete join graph, enhanced descriptors are obtained. Findings Experiments are carried out in indoor, outdoor and low texture scenes. The experiments investigate the real-time performance, rotation invariance, scale invariance, viewpoint invariance and noise sensitivity of the descriptors in three types of scenes. The results show that the enhanced descriptors are robust to scene changes and can be used in wide-baseline matching. Originality/value A graph structure is designed to represent multiple features in an image. In the process of building graph structure, the geometric relation between multiple features is used to establish the edges. Furthermore, a novel hybrid descriptor for points and lines is obtained using graph convolutional neural network. This enhanced descriptor has the advantages of both point features and line features in feature matching.

scholarly journals Graph Dilated Network with Rejection Mechanism

2020 ◽  
Vol 10 (7) ◽  
pp. 2421
Author(s):  
Bencheng Yan ◽  
Chaokun Wang ◽  
Gaoyang Guo
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Great Success ◽  
Convolution Kernel ◽  
Graph Structure ◽  
Proposed Model ◽  
Rejection Mechanism ◽  
Laplacian Smoothing ◽  
Graph Neural Networks ◽  
High Level

Recently, graph neural networks (GNNs) have achieved great success in dealing with graph-based data. The basic idea of GNNs is iteratively aggregating the information from neighbors, which is a special form of Laplacian smoothing. However, most of GNNs fall into the over-smoothing problem, i.e., when the model goes deeper, the learned representations become indistinguishable. This reflects the inability of the current GNNs to explore the global graph structure. In this paper, we propose a novel graph neural network to address this problem. A rejection mechanism is designed to address the over-smoothing problem, and a dilated graph convolution kernel is presented to capture the high-level graph structure. A number of experimental results demonstrate that the proposed model outperforms the state-of-the-art GNNs, and can effectively overcome the over-smoothing problem.

scholarly journals Facial Landmark-Based Emotion Recognition via Directed Graph Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 764 ◽  
Author(s):  
Quang Tran Ngoc ◽  
Seunghyun Lee ◽  
Byung Cheol Song
Keyword(s):  
Neural Network ◽  
Emotion Recognition ◽  
Directed Graph ◽  
Stable Form ◽  
Graph Structure ◽  
Emotional Information ◽  
The Past ◽  
Facial Landmark ◽  
Active Research ◽  
Graph Neural Networks

Facial emotion recognition (FER) has been an active research topic in the past several years. One of difficulties in FER is the effective capture of geometrical and temporary information from landmarks. In this paper, we propose a graph convolution neural network that utilizes landmark features for FER, which we called a directed graph neural network (DGNN). Nodes in the graph structure were defined by landmarks, and edges in the directed graph were built by the Delaunay method. By using graph neural networks, we could capture emotional information through faces’ inherent properties, like geometrical and temporary information. Also, in order to prevent the vanishing gradient problem, we further utilized a stable form of a temporal block in the graph framework. Our experimental results proved the effectiveness of the proposed method for datasets such as CK+ (96.02%), MMI (69.4%), and AFEW (32.64%). Also, a fusion network using image information as well as landmarks, is presented and investigated for the CK+ (98.47% performance) and AFEW (50.65% performance) datasets.

scholarly journals A Rotation-Invariant Optical and SAR Image Registration Algorithm Based on Deep and Gaussian Features

2021 ◽  
Vol 13 (13) ◽  
pp. 2628
Author(s):  
Zeyi Li ◽  
Haitao Zhang ◽  
Yihang Huang
Keyword(s):  
Neural Network ◽  
Image Registration ◽  
Feature Matching ◽  
Speckle Noise ◽  
Feature Descriptor ◽  
Sar Images ◽  
Gaussian Pyramid ◽  
Novel Approach ◽  
Image Registration Algorithm ◽  
Deep Learning Neural Network

Traditional feature matching methods of optical and synthetic aperture radar (SAR) used gradient are sensitive to non-linear radiation distortions (NRD) and the rotation between two images. To address this problem, this study presents a novel approach to solving the rigid body rotation problem by a two-step process. The first step proposes a deep learning neural network named RotNET to predict the rotation relationship between two images. The second step uses a local feature descriptor based on the Gaussian pyramid named Gaussian pyramid features of oriented gradients (GPOG) to match two images. The RotNET uses a neural network to analyze the gradient histogram of the two images to derive the rotation relationship between optical and SAR images. Subsequently, GPOG is depicted a keypoint by using the histogram of Gaussian pyramid to make one-cell block structure which is simpler and more stable than HOG structure-based descriptors. Finally, this paper designs experiments to prove that the gradient histogram of the optical and SAR images can reflect the rotation relationship and the RotNET can correctly predict them. The similarity map test and the image registration results obtained on experiments show that GPOG descriptor is robust to SAR speckle noise and NRD.

scholarly journals Multi-Scale Aggregation Graph Neural Networks Based on Feature Similarity for Semi-Supervised Learning

Entropy ◽  
2021 ◽  
Vol 23 (4) ◽  
pp. 403
Author(s):  
Xun Zhang ◽  
Lanyan Yang ◽  
Bin Zhang ◽  
Ying Liu ◽  
Dong Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Structured Data ◽  
Similarity Matrix ◽  
Scale Feature ◽  
Multi Scale ◽  
Adjacent Node ◽  
Feature Similarity ◽  
The Mean ◽  
Graph Neural Networks

The problem of extracting meaningful data through graph analysis spans a range of different fields, such as social networks, knowledge graphs, citation networks, the World Wide Web, and so on. As increasingly structured data become available, the importance of being able to effectively mine and learn from such data continues to grow. In this paper, we propose the multi-scale aggregation graph neural network based on feature similarity (MAGN), a novel graph neural network defined in the vertex domain. Our model provides a simple and general semi-supervised learning method for graph-structured data, in which only a very small part of the data is labeled as the training set. We first construct a similarity matrix by calculating the similarity of original features between all adjacent node pairs, and then generate a set of feature extractors utilizing the similarity matrix to perform multi-scale feature propagation on graphs. The output of multi-scale feature propagation is finally aggregated by using the mean-pooling operation. Our method aims to improve the model representation ability via multi-scale neighborhood aggregation based on feature similarity. Extensive experimental evaluation on various open benchmarks shows the competitive performance of our method compared to a variety of popular architectures.

scholarly journals Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Minyi Dai ◽  
Mehmet F. Demirel ◽  
Yingyu Liang ◽  
Jia-Mian Hu
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Polycrystalline Materials ◽  
Feed Forward Neural Network ◽  
Microscopic Interactions ◽  
Physical Interactions ◽  
Graph Neural Networks ◽  
Individual Grains ◽  
Physical Features ◽  
Machine Learning Models

AbstractVarious machine learning models have been used to predict the properties of polycrystalline materials, but none of them directly consider the physical interactions among neighboring grains despite such microscopic interactions critically determining macroscopic material properties. Here, we develop a graph neural network (GNN) model for obtaining an embedding of polycrystalline microstructure which incorporates not only the physical features of individual grains but also their interactions. The embedding is then linked to the target property using a feed-forward neural network. Using the magnetostriction of polycrystalline Tb0.3Dy0.7Fe2 alloys as an example, we show that a single GNN model with fixed network architecture and hyperparameters allows for a low prediction error of ~10% over a group of remarkably different microstructures as well as quantifying the importance of each feature in each grain of a microstructure to its magnetostriction. Such a microstructure-graph-based GNN model, therefore, enables an accurate and interpretable prediction of the properties of polycrystalline materials.

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

scholarly journals k-Nearest Neighbor Learning with Graph Neural Networks

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 830
Author(s):  
Seokho Kang
Keyword(s):  
Neural Network ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Weighting Function ◽  
High Sensitivity ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Main Challenge ◽  
Benchmark Datasets ◽  
Graph Neural Networks

k-nearest neighbor (kNN) is a widely used learning algorithm for supervised learning tasks. In practice, the main challenge when using kNN is its high sensitivity to its hyperparameter setting, including the number of nearest neighbors k, the distance function, and the weighting function. To improve the robustness to hyperparameters, this study presents a novel kNN learning method based on a graph neural network, named kNNGNN. Given training data, the method learns a task-specific kNN rule in an end-to-end fashion by means of a graph neural network that takes the kNN graph of an instance to predict the label of the instance. The distance and weighting functions are implicitly embedded within the graph neural network. For a query instance, the prediction is obtained by performing a kNN search from the training data to create a kNN graph and passing it through the graph neural network. The effectiveness of the proposed method is demonstrated using various benchmark datasets for classification and regression tasks.

scholarly journals A Multi-Feature Fusion Slam System Attaching Semantic Invariant to Points and Lines

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1196
Author(s):  
Gang Li ◽  
Yawen Zeng ◽  
Huilan Huang ◽  
Shaojian Song ◽  
Bin Liu ◽  
...  
Keyword(s):  
Feature Matching ◽  
Feature Fusion ◽  
Error Function ◽  
Line Segments ◽  
Cumulative Error ◽  
Localization And Mapping ◽  
Tracking Process ◽  
Line Features ◽  
Point Line ◽  
Segment Data

The traditional simultaneous localization and mapping (SLAM) system uses static points of the environment as features for real-time localization and mapping. When there are few available point features, the system is difficult to implement. A feasible solution is to introduce line features. In complex scenarios containing rich line segments, the description of line segments is not strongly differentiated, which can lead to incorrect association of line segment data, thus introducing errors into the system and aggravating the cumulative error of the system. To address this problem, a point-line stereo visual SLAM system incorporating semantic invariants is proposed in this paper. This system improves the accuracy of line feature matching by fusing line features with image semantic invariant information. When defining the error function, the semantic invariant is fused with the reprojection error function, and the semantic constraint is applied to reduce the cumulative error of the poses in the long-term tracking process. Experiments on the Office sequence of the TartanAir dataset and the KITTI dataset show that this system improves the matching accuracy of line features and suppresses the cumulative error of the SLAM system to some extent, and the mean relative pose error (RPE) is 1.38 and 0.0593 m, respectively.

Dynamic prediction of Indian stock market: an artificial neural network approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Himanshu Goel ◽  
Narinder Pal Singh
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Stock Market ◽  
Institutional Investors ◽  
Time Series Data ◽  
Gradient Algorithm ◽  
Series Data ◽  
Content Type ◽  
Artificial Neural ◽  
Indian Stock Market

Purpose Artificial neural network (ANN) is a powerful technique to forecast the time series data such as the stock market. Therefore, this study aims to predict the Indian stock market closing price using ANNs. Design/methodology/approach The input variables identified from the literature are some macroeconomic variables and a global stock market factor. The study uses an ANN with Scaled Conjugate Gradient Algorithm (SCG) to forecast the Bombay Stock Exchange (BSE) Sensex. Findings The empirical findings reveal that the ANN model is able to achieve 93% accuracy in predicting the BSE Sensex closing prices. Moreover, the results indicate that the Morgan Stanley Capital International world index is the most important variable and the index of industrial production is the least important in predicting Sensex. Research limitations/implications The findings of the study have implications for the investors of all categories such as foreign institutional investors, domestic institutional investors and investment houses. Originality/value The novelty of this study lies in the fact that there are hardly any studies that use ANN to forecast the Indian stock market using macroeconomic indicators.

Graph-based knowledge tracing: Modeling student proficiency using graph neural networks

2021 ◽  
pp. 1-16
Author(s):  
Hiromi Nakagawa ◽  
Yusuke Iwasawa ◽  
Yutaka Matsuo
Keyword(s):  
Neural Networks ◽  
Student Performance ◽  
Classification Problem ◽  
Computer Assisted ◽  
Graph Structure ◽  
Inductive Bias ◽  
Additional Information ◽  
Knowledge Tracing ◽  
Open Datasets ◽  
Graph Neural Networks

Recent advancements in computer-assisted learning systems have caused an increase in the research in knowledge tracing, wherein student performance is predicted over time. Student coursework can potentially be structured as a graph. Incorporating this graph-structured nature into a knowledge tracing model as a relational inductive bias can improve its performance; however, previous methods, such as deep knowledge tracing, did not consider such a latent graph structure. Inspired by the recent successes of graph neural networks (GNNs), we herein propose a GNN-based knowledge tracing method, i.e., graph-based knowledge tracing. Casting the knowledge structure as a graph enabled us to reformulate the knowledge tracing task as a time-series node-level classification problem in the GNN. As the knowledge graph structure is not explicitly provided in most cases, we propose various implementations of the graph structure. Empirical validations on two open datasets indicated that our method could potentially improve the prediction of student performance and demonstrated more interpretable predictions compared to those of the previous methods, without the requirement of any additional information.

Sign in / Sign up

Export Citation Format

Share Document