Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of...Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.展开更多
Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we ...Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.展开更多
光伏电池的高效发电在推动绿色低碳循环发展中发挥着重要作用,针对光伏电池缺陷图像中存在背景复杂与目标尺寸较小等问题,提出一种改进YOLO11n的缺陷检测模型———CCMW-YOLO11n。首先,在YOLO11n的骨干网络中提出跨阶段部分改进模块(cro...光伏电池的高效发电在推动绿色低碳循环发展中发挥着重要作用,针对光伏电池缺陷图像中存在背景复杂与目标尺寸较小等问题,提出一种改进YOLO11n的缺陷检测模型———CCMW-YOLO11n。首先,在YOLO11n的骨干网络中提出跨阶段部分改进模块(cross stage partial improvement,CSP-I),该模块通过设计多头自注意力机制(multi-head self attention,MHSA)、卷积门控线性单元(convolutional gated linear uint,CGLU)与传统卷积(convolution,Conv)相结合,兼顾全局信息感知与局部特征提取,增强了多尺度特征的提取效果;其次,在特征融合阶段采用内容感知特征重组上采用技术(content-aware reassembly of features,CARAFE),该方法实现了对特征图自适应重组和细节增强,有效保留了细节特征,提升了模型对复杂目标的感知能力;然后,在颈部网络中融入混合聚合网络改进模块(mixed aggregation net enhancement,MAN-E),进一步增强了特征表达能力;最后,针对基础模型中CIoU损失函数的不足,结合WIoUv3、Inner-IoU和SIoU,提出一种新的边界框回归损失函数Wise-Inner-SIoU,以优化模型的回归效果。实验结果表明,改进后的CCMW-YOLO11n模型召回率提升了9.6%,mAP@0.5和mAP@0.5:0.95分别达到91.0%和61.1%,较基础模型分别提高了3.1%和2.0%,实现了对光伏电池缺陷的高效检测。展开更多
基金The authors received Sichuan Science and Technology Program(No.18YYJC1917)funding for this study.
文摘Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.
基金Supported by the National Natural Science Foundation of China (61901308)。
文摘Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.
文摘受货车侧架去除区域复杂结构影响,针对在铸造清理视觉拍摄过程中二维图像存在颜色特征模糊等问题,提出一种基于改进YOLOv10n的侧架铸造残余检测算法。引入轻量级通用上采样算子——内容感知特征重组上采样算子(content aware reassembly of features,CARAFE)模块,有效增加了网络模型的整体感知范围以及对有效语义信息的利用,在不影响网络复杂度的同时提升了检测模型对残余特征的识别能力。提出一种轻量级Mobile_CA模块替换原主干网络,显著降低网络的复杂度。实验结果表明:改进后的网络在铸造残余检测任务中平均检测精度mAP@0.5为93.8%,平均检测速度为65.6帧/s,相较于原网络,mAP@0.5提高了1.1%,检测速度显著提升,能够满足工况对于检测精度和效率的要求。
文摘光伏电池的高效发电在推动绿色低碳循环发展中发挥着重要作用,针对光伏电池缺陷图像中存在背景复杂与目标尺寸较小等问题,提出一种改进YOLO11n的缺陷检测模型———CCMW-YOLO11n。首先,在YOLO11n的骨干网络中提出跨阶段部分改进模块(cross stage partial improvement,CSP-I),该模块通过设计多头自注意力机制(multi-head self attention,MHSA)、卷积门控线性单元(convolutional gated linear uint,CGLU)与传统卷积(convolution,Conv)相结合,兼顾全局信息感知与局部特征提取,增强了多尺度特征的提取效果;其次,在特征融合阶段采用内容感知特征重组上采用技术(content-aware reassembly of features,CARAFE),该方法实现了对特征图自适应重组和细节增强,有效保留了细节特征,提升了模型对复杂目标的感知能力;然后,在颈部网络中融入混合聚合网络改进模块(mixed aggregation net enhancement,MAN-E),进一步增强了特征表达能力;最后,针对基础模型中CIoU损失函数的不足,结合WIoUv3、Inner-IoU和SIoU,提出一种新的边界框回归损失函数Wise-Inner-SIoU,以优化模型的回归效果。实验结果表明,改进后的CCMW-YOLO11n模型召回率提升了9.6%,mAP@0.5和mAP@0.5:0.95分别达到91.0%和61.1%,较基础模型分别提高了3.1%和2.0%,实现了对光伏电池缺陷的高效检测。
