Image classification always has open challenges for computer vision research.Nowadays,deep learning has promoted the development of this field,especially in Convolutional Neural Networks(CNNs).This article proposes th...Image classification always has open challenges for computer vision research.Nowadays,deep learning has promoted the development of this field,especially in Convolutional Neural Networks(CNNs).This article proposes the development of efficiently scaled dilation of DropBlock optimization in CNNs for the fungus classification,which there are five species in this experiment.The proposed technique adjusts the convolution size at 35,45,and 60 with the max-polling size 2×2.The CNNs models are also designed in 12 models with the different BlockSizes and KeepProp.The proposed techniques provide maximum accuracy of 98.30%for the training set.Moreover,three accurate models,called Precision,Recall,and F1-score,are employed to measure the testing set.The experiment results expose that the proposed models achieve to classify the fungus and provide an excellent accuracy compared with the previous techniques.Furthermore,the proposed techniques can reduce the CNNs structure layer,directly affecting resource and time computation.展开更多
针对摩托车头盔的传统检测方法准确率低、泛化能力差和目标检测网络参数量大难以在嵌入式设备运行的问题,提出改进的YOLOv2的MNXt-ECA-D-YOLOv2目标检测算法模型。首先引入Mobile Ne Xt网络替换YOLOv2原始骨干网络,其次在Mobile Ne Xt...针对摩托车头盔的传统检测方法准确率低、泛化能力差和目标检测网络参数量大难以在嵌入式设备运行的问题,提出改进的YOLOv2的MNXt-ECA-D-YOLOv2目标检测算法模型。首先引入Mobile Ne Xt网络替换YOLOv2原始骨干网络,其次在Mobile Ne Xt的沙漏块中引入密集连接结构同时在网络中引入有效通道注意力机制,然后在不同深度网络层应用不同的激活函数,最后在网络输出卷积层之前增加Drop Block模块。采用K-means聚类算法重新设计了自制数据集的先验框尺寸。实验结果表明,改进后的模型相比原始YOLOv2,在AP50指标上提高了3.53%,模型大小减少77.44%,检测速度提高了近4倍。通过对比实验可知,改进后的YOLOv2模型在保持较高的精度下模型更小,在CPU中的推理速度更快,具有一定的应用价值。展开更多
Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of int...Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.展开更多
基金This research is supported by the NationalResearch Council of Thailand(NRCT).NRISS No.906919,144276,2589514(FFB65E0712),2589488(FFB65E0713).
文摘Image classification always has open challenges for computer vision research.Nowadays,deep learning has promoted the development of this field,especially in Convolutional Neural Networks(CNNs).This article proposes the development of efficiently scaled dilation of DropBlock optimization in CNNs for the fungus classification,which there are five species in this experiment.The proposed technique adjusts the convolution size at 35,45,and 60 with the max-polling size 2×2.The CNNs models are also designed in 12 models with the different BlockSizes and KeepProp.The proposed techniques provide maximum accuracy of 98.30%for the training set.Moreover,three accurate models,called Precision,Recall,and F1-score,are employed to measure the testing set.The experiment results expose that the proposed models achieve to classify the fungus and provide an excellent accuracy compared with the previous techniques.Furthermore,the proposed techniques can reduce the CNNs structure layer,directly affecting resource and time computation.
文摘针对摩托车头盔的传统检测方法准确率低、泛化能力差和目标检测网络参数量大难以在嵌入式设备运行的问题,提出改进的YOLOv2的MNXt-ECA-D-YOLOv2目标检测算法模型。首先引入Mobile Ne Xt网络替换YOLOv2原始骨干网络,其次在Mobile Ne Xt的沙漏块中引入密集连接结构同时在网络中引入有效通道注意力机制,然后在不同深度网络层应用不同的激活函数,最后在网络输出卷积层之前增加Drop Block模块。采用K-means聚类算法重新设计了自制数据集的先验框尺寸。实验结果表明,改进后的模型相比原始YOLOv2,在AP50指标上提高了3.53%,模型大小减少77.44%,检测速度提高了近4倍。通过对比实验可知,改进后的YOLOv2模型在保持较高的精度下模型更小,在CPU中的推理速度更快,具有一定的应用价值。
基金This work was supported,in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401+1 种基金in part,by the Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant Numbers SJCX21_0363in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.
