Selective Multi-Convolutional Region Feature Extraction based Iterative Discrimination CNN for Fine-Grained Vehicle Model Recognition

2018 ◽  
Author(s):  
Yanling Tian ◽  
Weitong Zhang ◽  
Qieshi Zhang ◽  
Gang Lu ◽  
Xiaojun Wu
Keyword(s):  
Feature Extraction ◽  
Vehicle Model ◽  
Fine Grained ◽  
Model Recognition ◽  
Region Feature

Few-Shots Learning for Fine-Grained Vehicle Model Recognition

2021 ◽  
Author(s):  
Landry Kezebou ◽  
Victor Oludare ◽  
Karen Panetta ◽  
Sos Agaian
Keyword(s):  
Vehicle Model ◽  
Fine Grained ◽  
Model Recognition

CAM: A fine-grained vehicle model recognition method based on visual attention model

2020 ◽  
Vol 104 ◽  
pp. 104027
Author(s):  
Ye Yu ◽  
Longdao Xu ◽  
Wei Jia ◽  
Wenjia Zhu ◽  
Yunxiang Fu ◽  
...  
Keyword(s):  
Visual Attention ◽  
Vehicle Model ◽  
Recognition Method ◽  
Visual Attention Model ◽  
Attention Model ◽  
Fine Grained ◽  
Model Recognition

Lightweight detection algorithm for fine-grained surface defects of aerospace seal rings

2021 ◽  
pp. 1-18
Author(s):  
Hui Liu ◽  
Boxia He ◽  
Yong He ◽  
Xiaotian Tao
Keyword(s):  
Feature Extraction ◽  
Defect Detection ◽  
Surface Defect ◽  
Surface Defects ◽  
Detection Algorithm ◽  
Seal Ring ◽  
Fine Grained ◽  
Aerospace Applications ◽  
Surface Defect Detection ◽  
The Mean

The existing seal ring surface defect detection methods for aerospace applications have the problems of low detection efficiency, strong specificity, large fine-grained classification errors, and unstable detection results. Considering these problems, a fine-grained seal ring surface defect detection algorithm for aerospace applications is proposed. Based on analysis of the stacking process of standard convolution, heat maps of original pixels in the receptive field participating in the convolution operation are quantified and generated. According to the generated heat map, the feature extraction optimization method of convolution combinations with different dilation rates is proposed, and an efficient convolution feature extraction network containing three kinds of dilated convolutions is designed. Combined with the O-ring surface defect features, a multiscale defect detection network is designed. Before the head of multiscale classification and position regression, feature fusion tree modules are added to ensure the reuse and compression of the responsive features of different receptive fields on the same scale feature maps. Experimental results show that on the O-rings-3000 testing dataset, the mean condition accuracy of the proposed algorithm reaches 95.10% for 5 types of surface defects of aerospace O-rings. Compared with RefineDet, the mean condition accuracy of the proposed algorithm is only reduced by 1.79%, while the parameters and FLOPs are reduced by 35.29% and 64.90%, respectively. Moreover, the proposed algorithm has good adaptability to image blur and light changes caused by the cutting of imaging hardware, thus saving the cost.

scholarly journals DGANet: A Dilated Graph Attention-Based Network for Local Feature Extraction on 3D Point Clouds

2021 ◽  
Vol 13 (17) ◽  
pp. 3484
Author(s):  
Jie Wan ◽  
Zhong Xie ◽  
Yongyang Xu ◽  
Ziyin Zeng ◽  
Ding Yuan ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Long Range ◽  
Point Clouds ◽  
Feature Representation ◽  
Learning Ability ◽  
Geometric Feature ◽  
Cloud Data ◽  
Fine Grained ◽  
3D Point Clouds ◽  
Benchmark Datasets

Feature extraction on point clouds is an essential task when analyzing and processing point clouds of 3D scenes. However, there still remains a challenge to adequately exploit local fine-grained features on point cloud data due to its irregular and unordered structure in a 3D space. To alleviate this problem, a Dilated Graph Attention-based Network (DGANet) with a certain feature for learning ability is proposed. Specifically, we first build a local dilated graph-like region for each input point to establish the long-range spatial correlation towards its corresponding neighbors, which allows the proposed network to access a wider range of geometric information of local points with their long-range dependencies. Moreover, by integrating the dilated graph attention module (DGAM) implemented by a novel offset–attention mechanism, the proposed network promises to highlight the differing ability of each edge of the constructed local graph to uniquely learn the discrepancy feature of geometric attributes between the connected point pairs. Finally, all the learned edge attention features are further aggregated, allowing the most significant geometric feature representation of local regions by the graph–attention pooling to fully extract local detailed features for each point. The validation experiments using two challenging benchmark datasets demonstrate the effectiveness and powerful generation ability of our proposed DGANet in both 3D object classification and segmentation tasks.

Sign in / Sign up

Export Citation Format

Share Document