使用九点双三次卷积插值方法改进的Deep Lab-v3模型  

Improved DeepLab-v3 model using nine-point bicubic convolution interpolation

作　　者：宋国杰[1] 黄佳芳 陈普春[1] 陈亚丽[1] Song Guojie;Huang Jiafang;Chen Puchun;Chen Yali(School of Science,Southwest Petroleum University,Chengdu 610500,China)

机构地区：[1]西南石油大学理学院,成都610500

出　　处：《计算机应用研究》2020年第9期2876-2880,共5页Application Research of Computers

基　　金：国家自然科学基金面上项目(41674141)。

摘　　要：针对Deep Lab-v3模型中双线性插值方法只能从邻近的四个抽样点提取信息,导致图像分割的精确度下降问题,提出两个改进的Deep Lab-v3模型,即IDL-v3-1(improved Deep Lab-v3-1 model)和IDL-v3-2(improved Deep Lab-v3-2 model)。两个改进的模型使用九点双三次卷积插值方法替换Deep Lab-v3模型的双线性插值方法,以获得更精确的分割图像。在PASCAL VOC 2012数据集上检验发现,与Deep Lab-v3模型相比,IDL-v3-1和IDLv3-2的精确度分别提升了0.43%和0.59%,分割每张图像的耗时量分别增加了0.002 s和0.005 s。实验结果表明,改进的Deep Lab-v3模型可以在与Deep Lab-v3模型相近的时间成本内达到更高的图像分割精度。In view of the fact that the bilinear interpolation method in the DeepLab-v3 model can only extract information from four adjacent sampling points,resulting in the degradation of image segmentation accuracy,this paper proposed two improved DeepLab-v3 models: IDL-v3-1 and IDL-v3-2. The two improved models replaced the bilinear interpolation method of the DeepLab-v3 model with a nine-point bicubic convolution interpolation method to get a more accurate segmentation image.It tested model on the PASCAL VOC 2012 dataset,it was found that compared with the DeepLab-v3 model,the accuracy of IDL-v3-1 and IDL-v3-2 were increased by 0. 43% and 0. 59%,respectively,and the time taken to segment each image was increased by 0. 002 s and 0. 005 s,respectively. Experimental results show that the improved DeepLab-v3 model can achieve higher image segmentation accuracy in a similar time cost as the DeepLab-v3 model.

关 键 词：图像语义分割 Deep Lab-v3 双线性插值 双三次卷积插值 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]