摘要
在图像的语义分割任务中,不同对象之间像素值存在差异,导致现有的网络模型在图像语义分割过程中丢失图像局部细节信息。针对上述问题,提出一种图像语义分割方法(DECANet)。首先,引入通道注意力网络模块,通过对所有通道的依赖关系进行建模提高网络的表达能力,选择性地学习并强化通道特征,提取有用信息,抑制无用信息。其次,利用改进的空洞空间金字塔池化(ASPP)结构,对提取到的图像卷积特征进行多尺度融合,减少图像细节信息丢失,且在权重参数不改变的情况下提取语义像素位置信息,加快模型的收敛速度。最后,DECANet在PASCAL VOC2012和Cityscapes数据集上的平均交并比分别达81.08%和76%,与现有的先进网络模型相比,检测性能更优,可以有效地捕获局部细节信息,减少图像语义像素分类错误。
The variation in pixel values between different objects during semantic segmentation of images leads to the loss of local image details in existing network models.An image semantic segmentation method(DECANet)is proposed to solve this problem.First,a channel attention network module is introduced to improve network clarity by modeling the dependencies of all channels,selectively learning and reinforcing channel features,and extracting useful information to suppress useless data.Second,using an improved atrous space pyramidal pooling(ASPP)structure,the extracted image convolutional features are multiscale fused to reduce the loss of image detail information,and the semantic pixel location information is extracted without increasing the weight parameters to speed up the model’s convergence.Finally,the mean intersection over union of the proposed method reaches 81.08%and 76%on PASCAL VOC2012 and Cityscapes datasets,respectively.The detection performance of the DECANet is superior to the existing stateoftheart network models,which can effectively capture local detail information and reduce image semantic pixel classification errors.
作者
唐璐
万良
王婷婷
李树胜
Tang Lu;Wan Liang;Wang Tingting;Li Shusheng(College of Computer Science and Technology,Guizhou University,Guiyang 550025,Guizhou,China;Institute of Computer Software and Theory,Guizhou University,Guiyang 550025,Guizhou,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2023年第4期82-90,共9页
Laser & Optoelectronics Progress
基金
国家自然科学基金(62062020)。
关键词
图像语义分割
注意力机制
空洞空间金字塔池化
多尺度融合
image semantic segmentation
attention mechanism
atrous space pyramidal pooling(ASPP)
multiscale fusion
