Improved Lightweight(改进的轻量级)研究综述
Improved Lightweight 改进的轻量级 - Finally, similar frames are input into the improved lightweight feature matching network based on Transformer to judge whether the current position is loop closure. [1] Since the existing target detection models deployed on embedded devices cannot meet the needs of rapid detection, an improved lightweight network based on Yolov5 was adopted in this paper. [2] Our method contains an improved lightweight deep neural network (DNN) to capture the signal portions damaged by EMA and MA, uses the sample entropy to quantize noisy portions, and discards those portions that exceed a defined threshold. [3] Tested on the constructed peanut detection data set, the improved lightweight peanut detection network based on YOLO v3 reached an average accuracy rate of 99. [4] First, an improved lightweight instance segmentation network is proposed for the segmentation and location of fastener and rail. [5] Experimental results showed that the detection speed of the improved lightweight network could reach up to 40. [6] To solve these problems, an improved lightweight network MobileNetv3 based on YOLO v3 is proposed. [7] HIGHLIGHTSA deep learning algorithm with an improved lightweight network was used to identify apple fruit. [8] In this paper, we have designed an improved lightweight Elliptic Curve Cryptography based anonymous authentication protocol for IoMT, which has lightweight as compared to the He et al. [9] The aim is to process materials with improved lightweight performances, static or fatigue properties, crack resistance, toughness or wear resistance. [10] Specifically, the improved power battery model is combined with the improved lightweight charging load and the online estimation of the state of charge as well as the electromotive force of the battery model are used to adjust charging load parameters in real time to simulate the charging response. [11] Washing also reduced the initial sintering temperature and improved lightweight aggregate properties. [12] In order to resolve the problems, there is a need to develop improved lightweight polymeric composite materials, which can be used in the construction and transportation industries. [13] Finally, we have proposed two improved lightweight proposals based on the broadening mechanisms of the STL bandwidth. [14] First, considering the low contrast characteristics of IR images, we proposed an improved lightweight non-local depth feature method (Light-NLDF) for IR ship target saliency detection. [15] Finally, a series of experiments and tests on the IsoGD and Jester datasets are conducted to demonstrate the effectiveness of our improved lightweight I3D. [16] An improved lightweight convolutional neural network for wear debris image classification named UstbNet is proposed in this paper. [17] In this paper, we proposed an improved lightweight Siamese network, which combine the MobileNetV2 and SiamRPN. [18]最后将相似的帧输入到基于Transformer的改进的轻量级特征匹配网络中，判断当前位置是否是闭环。 [1] 由于现有部署在嵌入式设备上的目标检测模型无法满足快速检测的需求，本文采用基于Yolov5的改进轻量级网络。 [2] 我们的方法包含一个改进的轻量级深度神经网络 (DNN) 来捕获被 EMA 和 MA 损坏的信号部分，使用样本熵来量化噪声部分，并丢弃那些超过定义阈值的部分。 [3] 在构建的花生检测数据集上进行测试，基于YOLO v3改进的轻量级花生检测网络平均准确率达到99。 [4] 首先，提出了一种改进的轻量级实例分割网络，用于紧固件和轨道的分割和定位。 [5] 实验结果表明，改进后的轻量级网络的检测速度可达40。 [6] 针对这些问题，提出了一种基于YOLO v3的改进的轻量级网络MobileNetv3。 [7] HIGHLIGHTSA 具有改进的轻量级网络的深度学习算法用于识别苹果果实。 [8] 在本文中，我们为物联网设计了一种改进的基于椭圆曲线加密的轻量级匿名认证协议，与 He 等人相比具有轻量级的特点。 [9] 目的是加工具有改进的轻质性能、静态或疲劳性能、抗裂性、韧性或耐磨性的材料。 [10] 具体而言，将改进后的动力电池模型与改进后的轻量化充电负载相结合，利用电池模型的荷电状态在线估计和电动势实时调整充电负载参数，模拟充电响应。 [11] 洗涤还降低了初始烧结温度并改善了轻质骨料的性能。 [12] 为了解决这些问题，需要开发可用于建筑和运输行业的改进的轻质聚合物复合材料。 [13] 最后，我们基于 STL 带宽的扩展机制提出了两个改进的轻量级建议。 [14] 首先，考虑到红外图像的低对比度特性，我们提出了一种改进的轻量级非局部深度特征方法（Light-NLDF），用于红外舰船目标显着性检测。 [15] 最后，对 IsoGD 和 Jester 数据集进行了一系列实验和测试，以证明我们改进的轻量级 I3D 的有效性。 [16] 本文提出了一种改进的用于磨损碎片图像分类的轻量级卷积神经网络UstbNet。 [17] 在本文中，我们提出了一种改进的轻量级 Siamese 网络，它结合了 MobileNetV2 和 SiamRPN。 [18]
improved lightweight network 改进的轻量级网络
Since the existing target detection models deployed on embedded devices cannot meet the needs of rapid detection, an improved lightweight network based on Yolov5 was adopted in this paper. [1] Experimental results showed that the detection speed of the improved lightweight network could reach up to 40. [2] To solve these problems, an improved lightweight network MobileNetv3 based on YOLO v3 is proposed. [3] HIGHLIGHTSA deep learning algorithm with an improved lightweight network was used to identify apple fruit. [4]由于现有部署在嵌入式设备上的目标检测模型无法满足快速检测的需求，本文采用基于Yolov5的改进轻量级网络。 [1] 实验结果表明，改进后的轻量级网络的检测速度可达40。 [2] 针对这些问题，提出了一种基于YOLO v3的改进的轻量级网络MobileNetv3。 [3] HIGHLIGHTSA 具有改进的轻量级网络的深度学习算法用于识别苹果果实。 [4]