受到移动设备计算能力和存储资源受限的局限,设计高效、高精度的人脸检测器是一个开放性的挑战.因此,文中提出融合多尺度特征的轻量级人脸检测算法(Lightweight Face Detection Algorithm with Multi-scale Feature Fusion,LFDMF),摒弃...受到移动设备计算能力和存储资源受限的局限,设计高效、高精度的人脸检测器是一个开放性的挑战.因此,文中提出融合多尺度特征的轻量级人脸检测算法(Lightweight Face Detection Algorithm with Multi-scale Feature Fusion,LFDMF),摒弃被视为人脸检测核心组件的多级检测结构.首先,利用现有的轻量级主干特征提取网络编码输入图像.然后,利用提出的颈部网络扩张特征图感受野,并将含有不同感受野的多尺度信息融至单级特征图中.最后,利用提出的多任务敏感检测头对该单级特征图进行人脸分类、回归和关键点检测.相比分而治之的人脸检测器,LFDMF精度更高、计算量更少.LFDMF按模型计算量高低可构建3个不同大小的网络,大模型LFDMF-L在Wider Face数据集上性能较优,中等模型LFDMF-M和小模型LFDMF-S以极低的模型参数量和计算量实现可观性能.展开更多
Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportati...Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic fields.The introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network security.Insufficient feature extraction leads to less accurate classification results.In abnormal traffic detection,the data of network traffic is high-dimensional and complex.This data not only increases the computational burden of model training but also makes information extraction more difficult.To address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic detection.To fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is introduced.This module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive field.The proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual block.This module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information redundancy.Experimental results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.展开更多
场景图为描述图像内容的结构图(Graph),其在生成过程中存在两个问题:1)二步式场景图生成方法造成有益信息流失,使得任务难度提高;2)视觉关系长尾分布使得模型发生过拟合、关系推理错误率上升。针对这两个问题,文中提出结合多尺度特征图...场景图为描述图像内容的结构图(Graph),其在生成过程中存在两个问题:1)二步式场景图生成方法造成有益信息流失,使得任务难度提高;2)视觉关系长尾分布使得模型发生过拟合、关系推理错误率上升。针对这两个问题,文中提出结合多尺度特征图和环型关系推理的场景图生成模型SGiF(Scene Graph in Features)。首先,计算多尺度特征图上的每一特征点存在视觉关系的可能性,并将存在可能性高的特征点特征提取出来;然后,从被提取出的特征中解码得到主宾组合,根据解码结果的类别差异,对结果进行去重,以此得到场景图结构;最后,根据场景图结构检测包含目标关系边在内的环路,将环路上的其他边作为计算调整因子的输入,以该因子调整原关系推理结果,并最终完成场景图的生成。实验设置SGGen和PredCls作为验证项,在大型场景图生成数据集VG(Visual Genome)子集上的实验结果表明,通过使用多尺度特征图,相比二步式基线,SGiF的视觉关系检测命中率提升了7.1%,且通过使用环型关系推理,相比非环型关系推理基线,SGiF的关系推理命中率提升了2.18%,从而证明了SGiF的有效性。展开更多
文摘受到移动设备计算能力和存储资源受限的局限,设计高效、高精度的人脸检测器是一个开放性的挑战.因此,文中提出融合多尺度特征的轻量级人脸检测算法(Lightweight Face Detection Algorithm with Multi-scale Feature Fusion,LFDMF),摒弃被视为人脸检测核心组件的多级检测结构.首先,利用现有的轻量级主干特征提取网络编码输入图像.然后,利用提出的颈部网络扩张特征图感受野,并将含有不同感受野的多尺度信息融至单级特征图中.最后,利用提出的多任务敏感检测头对该单级特征图进行人脸分类、回归和关键点检测.相比分而治之的人脸检测器,LFDMF精度更高、计算量更少.LFDMF按模型计算量高低可构建3个不同大小的网络,大模型LFDMF-L在Wider Face数据集上性能较优,中等模型LFDMF-M和小模型LFDMF-S以极低的模型参数量和计算量实现可观性能.
基金supported by the Key Research and Development Program of Xinjiang Uygur Autonomous Region(No.2022B01008)the National Natural Science Foundation of China(No.62363032)+4 种基金the Natural Science Foundation of Xinjiang Uygur Autonomous Region(No.2023D01C20)the Scientific Research Foundation of Higher Education(No.XJEDU2022P011)National Science and Technology Major Project(No.2022ZD0115803)Tianshan Innovation Team Program of Xinjiang Uygur Autonomous Region(No.2023D14012)the“Heaven Lake Doctor”Project(No.202104120018).
文摘Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more intelligent.IoT has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic fields.The introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network security.Insufficient feature extraction leads to less accurate classification results.In abnormal traffic detection,the data of network traffic is high-dimensional and complex.This data not only increases the computational burden of model training but also makes information extraction more difficult.To address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic detection.To fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is introduced.This module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive field.The proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual block.This module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information redundancy.Experimental results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.
文摘场景图为描述图像内容的结构图(Graph),其在生成过程中存在两个问题:1)二步式场景图生成方法造成有益信息流失,使得任务难度提高;2)视觉关系长尾分布使得模型发生过拟合、关系推理错误率上升。针对这两个问题,文中提出结合多尺度特征图和环型关系推理的场景图生成模型SGiF(Scene Graph in Features)。首先,计算多尺度特征图上的每一特征点存在视觉关系的可能性,并将存在可能性高的特征点特征提取出来;然后,从被提取出的特征中解码得到主宾组合,根据解码结果的类别差异,对结果进行去重,以此得到场景图结构;最后,根据场景图结构检测包含目标关系边在内的环路,将环路上的其他边作为计算调整因子的输入,以该因子调整原关系推理结果,并最终完成场景图的生成。实验设置SGGen和PredCls作为验证项,在大型场景图生成数据集VG(Visual Genome)子集上的实验结果表明,通过使用多尺度特征图,相比二步式基线,SGiF的视觉关系检测命中率提升了7.1%,且通过使用环型关系推理,相比非环型关系推理基线,SGiF的关系推理命中率提升了2.18%,从而证明了SGiF的有效性。
