LINEX(linear and exponential) loss function is a useful asymmetric loss function. The purpose of using a LINEX loss function in credibility models is to solve the problem of very high premium by suing a symmetric quad...LINEX(linear and exponential) loss function is a useful asymmetric loss function. The purpose of using a LINEX loss function in credibility models is to solve the problem of very high premium by suing a symmetric quadratic loss function in most of classical credibility models. The Bayes premium and the credibility premium are derived under LINEX loss function. The consistency of Bayes premium and credibility premium were also checked. Finally, the simulation was introduced to show the differences between the credibility estimator we derived and the classical one.展开更多
Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss...Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss functions are introduced to measure the degree of similarity between the samples generated by the generator and the real data samples,and the effectiveness of the loss functions in improving the generating ability of GANs.In this paper,we present a detailed survey for the loss functions used in GANs,and provide a critical analysis on the pros and cons of these loss functions.First,the basic theory of GANs along with the training mechanism are introduced.Then,the most commonly used loss functions in GANs are introduced and analyzed.Third,the experimental analyses and comparison of these loss functions are presented in different GAN architectures.Finally,several suggestions on choosing suitable loss functions for image synthesis tasks are given.展开更多
In this paper, MLINEX loss function was considered to solve the problem of high premium in credibility models. The Bayes premium and credibility premium were obtained under MLINEX loss function by using a symmetric qu...In this paper, MLINEX loss function was considered to solve the problem of high premium in credibility models. The Bayes premium and credibility premium were obtained under MLINEX loss function by using a symmetric quadratic loss function. A credibility model with multiple contracts was established and the corresponding credibility estimator was derived under MLINEX loss function. For this model the estimations of the structure parameters and a numerical example were also given.展开更多
针对传统图像处理算法对钢铁表面缺陷检测存在识别效率低、漏检误检率高等问题,提出了YOLOv8-DSG(Deformable Convolution Network Squeeze and Excitation Network Generalized Intersection over Union)钢铁表面缺陷检测算法。在传统Y...针对传统图像处理算法对钢铁表面缺陷检测存在识别效率低、漏检误检率高等问题,提出了YOLOv8-DSG(Deformable Convolution Network Squeeze and Excitation Network Generalized Intersection over Union)钢铁表面缺陷检测算法。在传统YOLOv8算法的基础上,首先在Backbone网络的C2f(Convolution to Feature)模块中嵌入了可变形卷积网络DCN(Deformable Convolution Network),增强了模型在复杂背景条件下的特征提取能力;其次,在Neck网络中引入了SE(Squeeze and Excitation Network)注意力模块,突出钢铁表面重要特征信息,提升了特征融合的丰富性;最后,利用GIOU(Generalized Intersection Over Union)损失函数代替原有的CIOU(Complete Intersection Over Union),相比CIOU,GIOU引入了最小包围框面积比率,可更准确衡量框的重合面积。实验结果表明,YOLOv8-DSG算法在NEU-DET数据集上平均精度mAP达到80%,相较于原YOLOv8算法,提高了3.3%,且误检、漏检率低,具有更高的检测精度和运算效率,可在质量检测方面发挥重要作用。展开更多
基金Supported by the NNSF of China(71001046)Supported by the NSF of Jiangxi Province(20114BAB211004)
文摘LINEX(linear and exponential) loss function is a useful asymmetric loss function. The purpose of using a LINEX loss function in credibility models is to solve the problem of very high premium by suing a symmetric quadratic loss function in most of classical credibility models. The Bayes premium and the credibility premium are derived under LINEX loss function. The consistency of Bayes premium and credibility premium were also checked. Finally, the simulation was introduced to show the differences between the credibility estimator we derived and the classical one.
文摘Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss functions are introduced to measure the degree of similarity between the samples generated by the generator and the real data samples,and the effectiveness of the loss functions in improving the generating ability of GANs.In this paper,we present a detailed survey for the loss functions used in GANs,and provide a critical analysis on the pros and cons of these loss functions.First,the basic theory of GANs along with the training mechanism are introduced.Then,the most commonly used loss functions in GANs are introduced and analyzed.Third,the experimental analyses and comparison of these loss functions are presented in different GAN architectures.Finally,several suggestions on choosing suitable loss functions for image synthesis tasks are given.
基金Supported by the National Natural Science Foundation of China（11271189） Supported by the Scientific Research Innovation Project of Jiangsu Province（KYZZ116_0175）
文摘In this paper, MLINEX loss function was considered to solve the problem of high premium in credibility models. The Bayes premium and credibility premium were obtained under MLINEX loss function by using a symmetric quadratic loss function. A credibility model with multiple contracts was established and the corresponding credibility estimator was derived under MLINEX loss function. For this model the estimations of the structure parameters and a numerical example were also given.
文摘针对传统图像处理算法对钢铁表面缺陷检测存在识别效率低、漏检误检率高等问题,提出了YOLOv8-DSG(Deformable Convolution Network Squeeze and Excitation Network Generalized Intersection over Union)钢铁表面缺陷检测算法。在传统YOLOv8算法的基础上,首先在Backbone网络的C2f(Convolution to Feature)模块中嵌入了可变形卷积网络DCN(Deformable Convolution Network),增强了模型在复杂背景条件下的特征提取能力;其次,在Neck网络中引入了SE(Squeeze and Excitation Network)注意力模块,突出钢铁表面重要特征信息,提升了特征融合的丰富性;最后,利用GIOU(Generalized Intersection Over Union)损失函数代替原有的CIOU(Complete Intersection Over Union),相比CIOU,GIOU引入了最小包围框面积比率,可更准确衡量框的重合面积。实验结果表明,YOLOv8-DSG算法在NEU-DET数据集上平均精度mAP达到80%,相较于原YOLOv8算法,提高了3.3%,且误检、漏检率低,具有更高的检测精度和运算效率,可在质量检测方面发挥重要作用。
