摘要
目标检测作为计算机视觉的一个重要研究方向,近年来在算法性能上有了突破性进展.为了更好的提升两阶段目标检测的精度与速度性能,提出了一种基于迁移学习方法的融合深度扩张卷积网络和轻量化网络的检测模型.首先用扩张卷积网络替换主干网络中部分的卷积残差模块——深度扩张卷积网络D_dNet-65;然后对预训练后的特征图进行压缩操作,并增加一个81类的全连接层以确保正常进行分类和回归操作——轻量化网络结构;最后,引入迁移学习方法并融合D_dNet和轻量化网络结构,通过迁移实现模型的进一步优化.实验在典型的数据集MSCOCO以及VOC07上进行.实验评估表明,本文提出的方法具有良好的有效性和可扩展性.
Object detection is an important research direction in the field of computer vision.In recent years,object detection has made great advances in public datasets,and there are also breakthroughs in algorithmic performance.In order to improve the accuracy and speed performance of two-stage object detection,this paper proposes a detection model based on transfer learning method that fuses the deep dilated convolutions network and the light-weight network.First,the dilated con-volutions network is used to replace the convolutional residual module in the backbone network,namely deep dilated convo-lution network(D_dNet-65).Then,by compressing the pretrained feature map and adding an 81-class fully connected layer to replace the original two layers,namely light-weight network.Finally,the transfer learning method is introduced in the pre-training to optimize the model(D_dNet and light-weight network).The experiment was carried out on a typical data set,MSCOCO and VOC07.And the experiment shows that the method proposed in this paper has good effectiveness and scal-ability.
作者
权宇
李志欣
张灿龙
马慧芳
QUAN Yu;LI Zhi-xin;ZHANG Can-long;MA Hui-fang(Guangxi Key Lab of Multi-source Information Mining and Security,Guangxi Normal University,Guilin,Guangxi 541004,China;College of Computer Science and Engineering,Northwest Normal University,Lanzhou,Gansu 730070,China)
出处
《电子学报》
EI
CAS
CSCD
北大核心
2020年第2期390-397,共8页
Acta Electronica Sinica
基金
国家自然科学基金(No.61966004,No.61663004,No.61762078,No.61866004)
广西自然科学基金(No.2019GXNSFDA245018,No.2016GXNSFAA380146,No.2017 GXNSFAA198365,No.2018GXNSFDA281009)
广西多源信息挖掘与安全重点实验室基金(No.16-A-03-02,No.MIMS18-08)。
关键词
图像目标检测
迁移学习
扩张卷积网络
轻量化网络
卷积神经网络
image object detection
transfer learning
dilated convolution network
light-weight network
convolution neural network
