Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to est...Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.展开更多
Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmentalmonitoring.Addressing the limitations of conventional convolutional neural networks,we propose ...Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmentalmonitoring.Addressing the limitations of conventional convolutional neural networks,we propose an innovative transformer-based method.This method leverages transformers,which are adept at processing data sequences,to enhance cloud detection accuracy.Additionally,we introduce a Cyclic Refinement Architecture that improves the resolution and quality of feature extraction,thereby aiding in the retention of critical details often lost during cloud detection.Our extensive experimental validation shows that our approach significantly outperforms established models,excelling in high-resolution feature extraction and precise cloud segmentation.By integrating Positional Visual Transformers(PVT)with this architecture,our method advances high-resolution feature delineation and segmentation accuracy.Ultimately,our research offers a novel perspective for surmounting traditional challenges in cloud detection and contributes to the advancement of precise and dependable image analysis across various domains.展开更多
The increasing use of cloud-based devices has reached the critical point of cybersecurity and unwanted network traffic.Cloud environments pose significant challenges in maintaining privacy and security.Global approach...The increasing use of cloud-based devices has reached the critical point of cybersecurity and unwanted network traffic.Cloud environments pose significant challenges in maintaining privacy and security.Global approaches,such as IDS,have been developed to tackle these issues.However,most conventional Intrusion Detection System(IDS)models struggle with unseen cyberattacks and complex high-dimensional data.In fact,this paper introduces the idea of a novel distributed explainable and heterogeneous transformer-based intrusion detection system,named INTRUMER,which offers balanced accuracy,reliability,and security in cloud settings bymultiplemodulesworking together within it.The traffic captured from cloud devices is first passed to the TC&TM module in which the Falcon Optimization Algorithm optimizes the feature selection process,and Naie Bayes algorithm performs the classification of features.The selected features are classified further and are forwarded to the Heterogeneous Attention Transformer(HAT)module.In this module,the contextual interactions of the network traffic are taken into account to classify them as normal or malicious traffic.The classified results are further analyzed by the Explainable Prevention Module(XPM)to ensure trustworthiness by providing interpretable decisions.With the explanations fromthe classifier,emergency alarms are transmitted to nearby IDSmodules,servers,and underlying cloud devices for the enhancement of preventive measures.Extensive experiments on benchmark IDS datasets CICIDS 2017,Honeypots,and NSL-KDD were conducted to demonstrate the efficiency of the INTRUMER model in detecting network trafficwith high accuracy for different types.Theproposedmodel outperforms state-of-the-art approaches,obtaining better performance metrics:98.7%accuracy,97.5%precision,96.3%recall,and 97.8%F1-score.Such results validate the robustness and effectiveness of INTRUMER in securing diverse cloud environments against sophisticated cyber threats.展开更多
【背景】传统方法因静态感受野设计较难适配城市自动驾驶场景中汽车、行人及骑行者等目标的显著尺度差异,且跨尺度特征融合易引发层级干扰。【方法】针对自动驾驶场景中多类别、多尺寸目标的3D检测中跨尺度表征一致性的关键挑战,本研究...【背景】传统方法因静态感受野设计较难适配城市自动驾驶场景中汽车、行人及骑行者等目标的显著尺度差异,且跨尺度特征融合易引发层级干扰。【方法】针对自动驾驶场景中多类别、多尺寸目标的3D检测中跨尺度表征一致性的关键挑战,本研究提出基于均衡化感受野的3D目标检测方法VoxTNT,通过局部-全局协同注意力机制提升检测性能。在局部层面,设计了PointSetFormer模块,引入诱导集注意力模块(Induced Set Attention Block,ISAB),通过约简的交叉注意力聚合高密度点云的细粒度几何特征,突破传统体素均值池化的信息损失瓶颈;在全局层面,设计了VoxelFormerFFN模块,将非空体素抽象为超点集并实施跨体素ISAB交互,建立长程上下文依赖关系,并将全局特征学习计算负载从O(N^(2))压缩至O(M^(2))(M<<N,M为非空体素数量),规避了复杂的Transformer直接使用在原始点云造成的高计算复杂度。该双域耦合架构实现了局部细粒度感知与全局语义关联的动态平衡,有效缓解固定感受野和多尺度融合导致的特征建模偏差。【结果】实验表明,该方法在KITTI数据集单阶段检测下,中等难度级别的行人检测精度AP(Average Precision)值达到59.56%,较SECOND基线提高约12.4%,两阶段检测下以66.54%的综合指标mAP(mean Average Precision)领先次优方法BSAODet的66.10%。同时,在WOD数据集中验证了方法的有效性,综合指标mAP达到66.09%分别超越SECOND和PointPillars基线7.7%和8.5%。消融实验进一步表明,均衡化局部和全局感受野的3D特征学习机制能显著提升小目标检测精度(如在KITTI数据集中全组件消融的情况下,中等难度级别的行人和骑行者检测精度分别下降10.8%和10.0%),同时保持大目标检测的稳定性。【结论】本研究为解决自动驾驶多尺度目标检测难题提供了新思路,未来将优化模型结构以进一步提升效能。展开更多
Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning b...Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning based model,for the types identification.However,traditional approaches such as convolutional neural networks(CNNs)encounter difficulties in capturing global contextual information.In addition,they are computationally expensive,which restricts their usability in resource-limited environments.To tackle these issues,we present the Cloud Vision Transformer(CloudViT),a lightweight model that integrates CNNs with Transformers.The integration enables an effective balance between local and global feature extraction.To be specific,CloudViT comprises two innovative modules:Feature Extraction(E_Module)and Downsampling(D_Module).These modules are able to significantly reduce the number of model parameters and computational complexity while maintaining translation invariance and enhancing contextual comprehension.Overall,the CloudViT includes 0.93×10^(6)parameters,which decreases more than ten times compared to the SOTA(State-of-the-Art)model CloudNet.Comprehensive evaluations conducted on the HBMCD and SWIMCAT datasets showcase the outstanding performance of CloudViT.It achieves classification accuracies of 98.45%and 100%,respectively.Moreover,the efficiency and scalability of CloudViT make it an ideal candidate for deployment inmobile cloud observation systems,enabling real-time cloud image classification.The proposed hybrid architecture of CloudViT offers a promising approach for advancing ground-based cloud image classification.It holds significant potential for both optimizing performance and facilitating practical deployment scenarios.展开更多
针对多目标识别过程中点云分类和分割精度不高的问题,提出了一种基于改进Transformer模型的点云分类与分割方法DRPT(Double randomness Point Transformer),该方法在Transformer模型卷积投影层创建新的点嵌入,利用局部邻域的动态处理在...针对多目标识别过程中点云分类和分割精度不高的问题,提出了一种基于改进Transformer模型的点云分类与分割方法DRPT(Double randomness Point Transformer),该方法在Transformer模型卷积投影层创建新的点嵌入,利用局部邻域的动态处理在数据特征向量中持续增加全局特征属性,从而提高多目标识别中点云分类和分割的精度。实验中采用了标准基准数据集(ModelNet40、ShapeNet部分分割和SemanticKITTI场景语义分割数据集)以验证模型的性能,实验结果表明:DRPT模型的pIoU值为85.9%,比其他模型平均高出3.5%,有效提高了多目标识别检测时点云分类与分割精度,是对智能网联技术发展的有效支撑。展开更多
基金supported in part by the Nationa Natural Science Foundation of China (61876011)the National Key Research and Development Program of China (2022YFB4703700)+1 种基金the Key Research and Development Program 2020 of Guangzhou (202007050002)the Key-Area Research and Development Program of Guangdong Province (2020B090921003)。
文摘Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.
基金funded by the Chongqing Normal University Startup Foundation for PhD(22XLB021)supported by the Open Research Project of the State Key Laboratory of Industrial Control Technology,Zhejiang University,China(No.ICT2023B40).
文摘Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmentalmonitoring.Addressing the limitations of conventional convolutional neural networks,we propose an innovative transformer-based method.This method leverages transformers,which are adept at processing data sequences,to enhance cloud detection accuracy.Additionally,we introduce a Cyclic Refinement Architecture that improves the resolution and quality of feature extraction,thereby aiding in the retention of critical details often lost during cloud detection.Our extensive experimental validation shows that our approach significantly outperforms established models,excelling in high-resolution feature extraction and precise cloud segmentation.By integrating Positional Visual Transformers(PVT)with this architecture,our method advances high-resolution feature delineation and segmentation accuracy.Ultimately,our research offers a novel perspective for surmounting traditional challenges in cloud detection and contributes to the advancement of precise and dependable image analysis across various domains.
文摘The increasing use of cloud-based devices has reached the critical point of cybersecurity and unwanted network traffic.Cloud environments pose significant challenges in maintaining privacy and security.Global approaches,such as IDS,have been developed to tackle these issues.However,most conventional Intrusion Detection System(IDS)models struggle with unseen cyberattacks and complex high-dimensional data.In fact,this paper introduces the idea of a novel distributed explainable and heterogeneous transformer-based intrusion detection system,named INTRUMER,which offers balanced accuracy,reliability,and security in cloud settings bymultiplemodulesworking together within it.The traffic captured from cloud devices is first passed to the TC&TM module in which the Falcon Optimization Algorithm optimizes the feature selection process,and Naie Bayes algorithm performs the classification of features.The selected features are classified further and are forwarded to the Heterogeneous Attention Transformer(HAT)module.In this module,the contextual interactions of the network traffic are taken into account to classify them as normal or malicious traffic.The classified results are further analyzed by the Explainable Prevention Module(XPM)to ensure trustworthiness by providing interpretable decisions.With the explanations fromthe classifier,emergency alarms are transmitted to nearby IDSmodules,servers,and underlying cloud devices for the enhancement of preventive measures.Extensive experiments on benchmark IDS datasets CICIDS 2017,Honeypots,and NSL-KDD were conducted to demonstrate the efficiency of the INTRUMER model in detecting network trafficwith high accuracy for different types.Theproposedmodel outperforms state-of-the-art approaches,obtaining better performance metrics:98.7%accuracy,97.5%precision,96.3%recall,and 97.8%F1-score.Such results validate the robustness and effectiveness of INTRUMER in securing diverse cloud environments against sophisticated cyber threats.
文摘【背景】传统方法因静态感受野设计较难适配城市自动驾驶场景中汽车、行人及骑行者等目标的显著尺度差异,且跨尺度特征融合易引发层级干扰。【方法】针对自动驾驶场景中多类别、多尺寸目标的3D检测中跨尺度表征一致性的关键挑战,本研究提出基于均衡化感受野的3D目标检测方法VoxTNT,通过局部-全局协同注意力机制提升检测性能。在局部层面,设计了PointSetFormer模块,引入诱导集注意力模块(Induced Set Attention Block,ISAB),通过约简的交叉注意力聚合高密度点云的细粒度几何特征,突破传统体素均值池化的信息损失瓶颈;在全局层面,设计了VoxelFormerFFN模块,将非空体素抽象为超点集并实施跨体素ISAB交互,建立长程上下文依赖关系,并将全局特征学习计算负载从O(N^(2))压缩至O(M^(2))(M<<N,M为非空体素数量),规避了复杂的Transformer直接使用在原始点云造成的高计算复杂度。该双域耦合架构实现了局部细粒度感知与全局语义关联的动态平衡,有效缓解固定感受野和多尺度融合导致的特征建模偏差。【结果】实验表明,该方法在KITTI数据集单阶段检测下,中等难度级别的行人检测精度AP(Average Precision)值达到59.56%,较SECOND基线提高约12.4%,两阶段检测下以66.54%的综合指标mAP(mean Average Precision)领先次优方法BSAODet的66.10%。同时,在WOD数据集中验证了方法的有效性,综合指标mAP达到66.09%分别超越SECOND和PointPillars基线7.7%和8.5%。消融实验进一步表明,均衡化局部和全局感受野的3D特征学习机制能显著提升小目标检测精度(如在KITTI数据集中全组件消融的情况下,中等难度级别的行人和骑行者检测精度分别下降10.8%和10.0%),同时保持大目标检测的稳定性。【结论】本研究为解决自动驾驶多尺度目标检测难题提供了新思路,未来将优化模型结构以进一步提升效能。
基金funded by Innovation and Development Special Project of China Meteorological Administration(CXFZ2022J038,CXFZ2024J035)Sichuan Science and Technology Program(No.2023YFQ0072)+1 种基金Key Laboratory of Smart Earth(No.KF2023YB03-07)Automatic Software Generation and Intelligent Service Key Laboratory of Sichuan Province(CUIT-SAG202210).
文摘Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning based model,for the types identification.However,traditional approaches such as convolutional neural networks(CNNs)encounter difficulties in capturing global contextual information.In addition,they are computationally expensive,which restricts their usability in resource-limited environments.To tackle these issues,we present the Cloud Vision Transformer(CloudViT),a lightweight model that integrates CNNs with Transformers.The integration enables an effective balance between local and global feature extraction.To be specific,CloudViT comprises two innovative modules:Feature Extraction(E_Module)and Downsampling(D_Module).These modules are able to significantly reduce the number of model parameters and computational complexity while maintaining translation invariance and enhancing contextual comprehension.Overall,the CloudViT includes 0.93×10^(6)parameters,which decreases more than ten times compared to the SOTA(State-of-the-Art)model CloudNet.Comprehensive evaluations conducted on the HBMCD and SWIMCAT datasets showcase the outstanding performance of CloudViT.It achieves classification accuracies of 98.45%and 100%,respectively.Moreover,the efficiency and scalability of CloudViT make it an ideal candidate for deployment inmobile cloud observation systems,enabling real-time cloud image classification.The proposed hybrid architecture of CloudViT offers a promising approach for advancing ground-based cloud image classification.It holds significant potential for both optimizing performance and facilitating practical deployment scenarios.
文摘针对多目标识别过程中点云分类和分割精度不高的问题,提出了一种基于改进Transformer模型的点云分类与分割方法DRPT(Double randomness Point Transformer),该方法在Transformer模型卷积投影层创建新的点嵌入,利用局部邻域的动态处理在数据特征向量中持续增加全局特征属性,从而提高多目标识别中点云分类和分割的精度。实验中采用了标准基准数据集(ModelNet40、ShapeNet部分分割和SemanticKITTI场景语义分割数据集)以验证模型的性能,实验结果表明:DRPT模型的pIoU值为85.9%,比其他模型平均高出3.5%,有效提高了多目标识别检测时点云分类与分割精度,是对智能网联技术发展的有效支撑。
