本文已被：浏览 4390次 下载 5181次
Received:August 12, 2018 Revised:September 05, 2018
Received:August 12, 2018 Revised:September 05, 2018
中文摘要: 为了提高卷积神经网络在目标检测的精度，本文提出了一种基于改进损失函数的YOLOv3网络.该网络模型应用一种新的损失函数Tan-Squared Error （TSE），将原有的平方和损失（Sum Squared Error，SSE）函数进行转化，能更好地计算连续变量的损失；TSE能有效减低Sigmoid函数梯度消失的影响，使模型收敛更加快速.在VOC数据集上的实验结果表明，与原网络模型的表现相比，利用TSE有效提高了检测精度，且收敛更加快速.
Abstract:To improve the object detect precision of Convolutional Neural Network (CNN), we present a YOLOv3 network which based on improved loss function. This network model uses a new loss function Tan-Squared Error (TSE) which transferred from primary Sum Squared Error(SSE), and works better on continuous variable error computing. Meanwhile, the properties of TSE could decrease the impact of vanishing gradient problem in sigmoid function, and speed up model converging. The experiment results in Pascal VOC dataset show that TSE improves the detect precision effectively compared with the performance of primary network model, and the convergence is accelerated.
文章编号： 中图分类号： 文献标志码：
基金项目:国家重点研发计划（2017YFC0803700）；上海市科委项目（17511101702）；复旦大学工程与应用技术研究院先导项目（gyy2917-003）
引用文本：
吕铄,蔡烜,冯瑞.基于改进损失函数的YOLOv3网络.计算机系统应用,2019,28(2):1-7
LYU Shuo,CAI Xuan,FENG Rui.YOLOv3 Network Based on Improved Loss Function.COMPUTER SYSTEMS APPLICATIONS,2019,28(2):1-7
吕铄,蔡烜,冯瑞.基于改进损失函数的YOLOv3网络.计算机系统应用,2019,28(2):1-7
LYU Shuo,CAI Xuan,FENG Rui.YOLOv3 Network Based on Improved Loss Function.COMPUTER SYSTEMS APPLICATIONS,2019,28(2):1-7
