{"title":"DAMVNet:基于双注意机制和VLAD的三维点云分类网络","authors":"Guodao Zhang, Xiaotian Pan, Li Xiao-nan, Zhang zhi-yong, Wei Wu, Ping-Kuo Chen","doi":"10.1109/ICCEAI52939.2021.00014","DOIUrl":null,"url":null,"abstract":"Aiming at the lack of effective use of contextual fine-grained local features in the existing deep learning-based 3D point cloud classification model, which leads to lower classification accuracy, a three-dimensional point cloud classification network based on dual attention mechanism and VLAD is proposed. Firstly, the local fine-grained features and global information of point cloud are mined by self-attention mechanism, and then the local geometric representation is learned by embedding graph attention mechanism in MLP layer. To take full advantage of the features, a multi-headed mechanism is used to aggregate different features from separate headers, and an effective key point descriptor is introduced to help identify the global geometry. Finally, the high-level semantic features of point clouds are obtained by locally aggregating vector VLAD layers. The experimental results show that the model achieves 92.45% accuracy on Mode1Net40 dataset.","PeriodicalId":331409,"journal":{"name":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DAMVNet: Three-dimensional point cloud classification network based on dual attention mechanism and VLAD\",\"authors\":\"Guodao Zhang, Xiaotian Pan, Li Xiao-nan, Zhang zhi-yong, Wei Wu, Ping-Kuo Chen\",\"doi\":\"10.1109/ICCEAI52939.2021.00014\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Aiming at the lack of effective use of contextual fine-grained local features in the existing deep learning-based 3D point cloud classification model, which leads to lower classification accuracy, a three-dimensional point cloud classification network based on dual attention mechanism and VLAD is proposed. Firstly, the local fine-grained features and global information of point cloud are mined by self-attention mechanism, and then the local geometric representation is learned by embedding graph attention mechanism in MLP layer. To take full advantage of the features, a multi-headed mechanism is used to aggregate different features from separate headers, and an effective key point descriptor is introduced to help identify the global geometry. Finally, the high-level semantic features of point clouds are obtained by locally aggregating vector VLAD layers. The experimental results show that the model achieves 92.45% accuracy on Mode1Net40 dataset.\",\"PeriodicalId\":331409,\"journal\":{\"name\":\"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCEAI52939.2021.00014\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCEAI52939.2021.00014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
DAMVNet: Three-dimensional point cloud classification network based on dual attention mechanism and VLAD
Aiming at the lack of effective use of contextual fine-grained local features in the existing deep learning-based 3D point cloud classification model, which leads to lower classification accuracy, a three-dimensional point cloud classification network based on dual attention mechanism and VLAD is proposed. Firstly, the local fine-grained features and global information of point cloud are mined by self-attention mechanism, and then the local geometric representation is learned by embedding graph attention mechanism in MLP layer. To take full advantage of the features, a multi-headed mechanism is used to aggregate different features from separate headers, and an effective key point descriptor is introduced to help identify the global geometry. Finally, the high-level semantic features of point clouds are obtained by locally aggregating vector VLAD layers. The experimental results show that the model achieves 92.45% accuracy on Mode1Net40 dataset.