摘要
为了提高卷积神经网络在人体姿势估计任务上的精度,提出了一种基于均方损失函数(Mean Squared Error,MSE)的改进损失函数来处理网络学习中回归热点图的前景(高斯核)和背景之间像素点不均衡问题,根据前景与背景不同像素点值对损失函数赋予不同权重,并将其命名为聚焦均方损失函数(Focus Mean Squared Error,FMSE).与均方损失函数相比,我们提出的聚焦均方损失函数可以有效地减少前景和背景之间像素点不均衡对网络性能的影响,帮助网络定位关键点的空间位置,提升了网络性能,并使得训练阶段中损失函数收敛速度更快.并在公开数据集上进行实验,以验证我们所提出的聚焦均方损失函数的有效性.
In order to improve the accuracy of the human pose estimation task of convolutional neural networks,we propose an improved loss function based on Mean Squared Error(MSE)to deal with the pixel imbalance between foreground(Gaussian kernel)and background in heatmaps,assign different weights to the loss function according to different pixel values in the foreground and background,and named it Focus Mean Squared Error(FMSE).Compared with the mean squared loss function,the proposed focused mean squared loss function can effectively reduce the impact of pixel imbalance between foreground and background on network performance,help the network locate the spatial location of key points,improve network performance,and make the loss function converge faster in the training phase.Experiments are performed on public data sets to verify the effectiveness of the proposed focused mean square loss function.
作者
徐锐
冯瑞
XU Rui;FENG Rui(School of Computer Science,Fudan University,Shanghai 201203,China;Shanghai Engineering Research Center for Video Technology and System,Shanghai 201203,China)
出处
《计算机系统应用》
2020年第10期133-140,共8页
Computer Systems & Applications
基金
国家重点研发计划(2017YFC0803702)
作者简介
通讯作者:冯瑞,E-mail:imvl@fudan.edu.cn
