Multi-feature fusion gaze estimation based on attention mechanism

2021 ◽  
Author(s):  
Zhangfang Hu ◽  
Yanling Xia ◽  
Yuan Luo ◽  
Lan Wang
Keyword(s):  
Feature Fusion ◽  
Attention Mechanism ◽  
Gaze Estimation

scholarly journals A Multi-Branch Feature Fusion Strategy Based on an Attention Mechanism for Remote Sensing Image Scene Classification

2021 ◽  
Vol 13 (10) ◽  
pp. 1950
Author(s):  
Cuiping Shi ◽  
Xin Zhao ◽  
Liguo Wang
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
Classification Accuracy ◽  
Feature Fusion ◽  
State Of The Art ◽  
Rapid Development ◽  
Remote Sensing Image ◽  
Classification Performance ◽  
Attention Mechanism ◽  
Scene Classification

In recent years, with the rapid development of computer vision, increasing attention has been paid to remote sensing image scene classification. To improve the classification performance, many studies have increased the depth of convolutional neural networks (CNNs) and expanded the width of the network to extract more deep features, thereby increasing the complexity of the model. To solve this problem, in this paper, we propose a lightweight convolutional neural network based on attention-oriented multi-branch feature fusion (AMB-CNN) for remote sensing image scene classification. Firstly, we propose two convolution combination modules for feature extraction, through which the deep features of images can be fully extracted with multi convolution cooperation. Then, the weights of the feature are calculated, and the extracted deep features are sent to the attention mechanism for further feature extraction. Next, all of the extracted features are fused by multiple branches. Finally, depth separable convolution and asymmetric convolution are implemented to greatly reduce the number of parameters. The experimental results show that, compared with some state-of-the-art methods, the proposed method still has a great advantage in classification accuracy with very few parameters.

Feature fusion network based on attention mechanism for 3D semantic segmentation of point clouds

2020 ◽  
Vol 133 ◽  
pp. 327-333 ◽  
Author(s):  
Heng Zhou ◽  
Zhijun Fang ◽  
Yongbin Gao ◽  
Bo Huang ◽  
Cengsi Zhong ◽  
...  
Keyword(s):  
Feature Fusion ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Attention Mechanism

scholarly journals A New Time-Space Attention Mechanism Driven Multi-Feature Fusion Method for Tool Wear Monitoring

2021 ◽  
Author(s):  
Tingting Feng ◽  
Liang Guo ◽  
Hongli Gao ◽  
Tao Chen ◽  
Yaoxiang Yu ◽  
...  
Keyword(s):  
Tool Wear ◽  
Feature Fusion ◽  
Attention Mechanism ◽  
Fusion Method ◽  
Tool Wear Monitoring ◽  
Time And Space ◽  
Time Space ◽  
Sensor Signals ◽  
Wear Monitoring ◽  
New Time

Abstract In order to accurately monitor the tool wear process, it is usually necessary to collect a variety of sensor signals during the cutting process. Different sensor signals in the feature space can provide complementary information. In addition, the monitoring signal is time series data, which also contains a wealth of tool degradation information in the time dimension. However, how to fuse multi-sensor information in time and space dimensions is a key issue that needs to be solved. This paper proposes a new time-space attention mechanism driven multi-feature fusion method to realize the tool wear monitoring. Firstly, lots of features are established from different sensor signals and selected preliminarily. Then, a new feature fusion model with time-space attention mechanism is constructed to fuse features in time and space dimensions. Finally, the tool degradation model is established according to the predicted wear, and the tool remaining useful life is predicted by particle filter. The effectiveness of this method is verified by a tool life cycle wear experiment. Through comparing with other feature fusion models, it is demonstrated that the proposed method realizes the tool wear monitoring more accurately and has better stability.

scholarly journals Small-scale Pedestrian Detection Method based on Attention Mechanism and Adaptive Feature Fusion

2021 ◽  
Vol 2035 (1) ◽  
pp. 012023
Author(s):  
Yuhao You ◽  
Houjin Chen ◽  
Yanfeng Li ◽  
Minjun Wang ◽  
Jinlei Zhu
Keyword(s):  
Detection Method ◽  
Feature Fusion ◽  
Pedestrian Detection ◽  
Attention Mechanism ◽  
Small Scale

scholarly journals A new end-to-end image dehazing algorithm based on residual attention mechanism

2021 ◽  
Vol 39 (4) ◽  
pp. 901-908
Author(s):  
Zhenjian Yang ◽  
Jiamei Shang ◽  
Zhongwei Zhang ◽  
Yan Zhang ◽  
Shudong Liu
Keyword(s):  
Feature Extraction ◽  
Feature Fusion ◽  
Attention Mechanism ◽  
Image Dehazing ◽  
Atmospheric Scattering ◽  
Scale Feature ◽  
Multi Scale ◽  
Color Distortion ◽  
End To End ◽  
Density Image

Traditional image dehazing algorithms based on prior knowledge and deep learning rely on the atmospheric scattering model and are easy to cause color distortion and incomplete dehazing. To solve these problems, an end-to-end image dehazing algorithm based on residual attention mechanism is proposed in this paper. The network includes four modules: encoder, multi-scale feature extraction, feature fusion and decoder. The encoder module encodes the input haze image into feature map, which is convenient for subsequent feature extraction and reduces memory consumption; the multi-scale feature extraction module includes residual smoothed dilated convolution module, residual block and efficient channel attention, which can expand the receptive field and extract different scale features by filtering and weighting; the feature fusion module with efficient channel attention adjusts the channel weight dynamically, acquires rich context information and suppresses redundant information so as to enhance the ability to extract haze density image of the network; finally, the encoder module maps the fused feature nonlinearly to obtain the haze density image and then restores the haze free image. The qualitative and quantitative tests based on SOTS test set and natural haze images show good objective and subjective evaluation results. This algorithm improves the problems of color distortion and incomplete dehazing effectively.

scholarly journals Feature fusion network based on strip pooling

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Gaihua Wang ◽  
Qianyu Zhai
Keyword(s):  
Feature Fusion ◽  
Contextual Information ◽  
Region Of Interest ◽  
Semantic Segmentation ◽  
Attention Mechanism ◽  
Affinity Matrix ◽  
The Public ◽  
Key Factor ◽  
Public Datasets ◽  
The Relationship

AbstractContextual information is a key factor affecting semantic segmentation. Recently, many methods have tried to use the self-attention mechanism to capture more contextual information. However, these methods with self-attention mechanism need a huge computation. In order to solve this problem, a novel self-attention network, called FFANet, is designed to efficiently capture contextual information, which reduces the amount of calculation through strip pooling and linear layers. It proposes the feature fusion (FF) module to calculate the affinity matrix. The affinity matrix can capture the relationship between pixels. Then we multiply the affinity matrix with the feature map, which can selectively increase the weight of the region of interest. Extensive experiments on the public datasets (PASCAL VOC2012, CityScapes) and remote sensing dataset (DLRSD) have been conducted and achieved Mean Iou score 74.5%, 70.3%, and 63.9% respectively. Compared with the current typical algorithms, the proposed method has achieved excellent performance.

scholarly journals HCNET: A Point Cloud Object Detection Network Based on Height and Channel Attention

2021 ◽  
Vol 13 (24) ◽  
pp. 5071
Author(s):  
Jing Zhang ◽  
Jiajun Wang ◽  
Da Xu ◽  
Yunsong Li
Keyword(s):  
Object Detection ◽  
Point Cloud ◽  
Feature Fusion ◽  
Three Dimensional ◽  
Point Clouds ◽  
Autonomous Driving ◽  
Attention Mechanism ◽  
Uneven Distribution ◽  
Adaptive Adjustment ◽  
High Level

The use of LiDAR point clouds for accurate three-dimensional perception is crucial for realizing high-level autonomous driving systems. Upon considering the drawbacks of the current point cloud object-detection algorithms, this paper proposes HCNet, an algorithm that combines an attention mechanism with adaptive adjustment, starting from feature fusion and overcoming the sparse and uneven distribution of point clouds. Inspired by the basic idea of an attention mechanism, a feature-fusion structure HC module with height attention and channel attention, weighted in parallel, is proposed to perform feature-fusion on multiple pseudo images. The use of several weighting mechanisms enhances the ability of feature-information expression. Additionally, we designed an adaptively adjusted detection head that also overcomes the sparsity of the point cloud from the perspective of original information fusion. It reduces the interference caused by the uneven distribution of the point cloud from the perspective of adaptive adjustment. The results show that our HCNet has better accuracy than other one-stage-network or even two-stage-network RCNNs under some evaluation detection metrics. Additionally, it has a detection rate of 30FPS. Especially for hard samples, the algorithm in this paper has better detection performance than many existing algorithms.

scholarly journals Object Detection Network Based on Feature Fusion and Attention Mechanism

2019 ◽  
Vol 11 (1) ◽  
pp. 9 ◽  
Author(s):  
Ying Zhang ◽  
Yimin Chen ◽  
Chen Huang ◽  
Mingke Gao
Keyword(s):  
Object Detection ◽  
Feature Fusion ◽  
Empirical Evaluation ◽  
Attention Mechanism ◽  
Detection Accuracy ◽  
Small Object ◽  
Art Object ◽  
Pascal Voc ◽  
Almost All ◽  
The Impact

In recent years, almost all of the current top-performing object detection networks use CNN (convolutional neural networks) features. State-of-the-art object detection networks depend on CNN features. In this work, we add feature fusion in the object detection network to obtain a better CNN feature, which incorporates well deep, but semantic, and shallow, but high-resolution, CNN features, thus improving the performance of a small object. Also, the attention mechanism was applied to our object detection network, AF R-CNN (attention mechanism and convolution feature fusion based object detection), to enhance the impact of significant features and weaken background interference. Our AF R-CNN is a single end to end network. We choose the pre-trained network, VGG-16, to extract CNN features. Our detection network is trained on the dataset, PASCAL VOC 2007 and 2012. Empirical evaluation of the PASCAL VOC 2007 dataset demonstrates the effectiveness and improvement of our approach. Our AF R-CNN achieves an object detection accuracy of 75.9% on PASCAL VOC 2007, six points higher than Faster R-CNN.

Sign in / Sign up

Export Citation Format

Share Document