四川大学学报（自然科学版）2024，Vol.61Issue(5)：99-107,9.DOI:10.19907/j.0490-6756.2024.053002
基于改进生成对抗网络的半监督语义分割
Semi-supervised semantic segmentation based on improved generative adversarial networks
摘要
Abstract
During the training process,adversarial semi-supervised semantic segmentation networks likely have poor convergence stability and may not model the remote dependence between pixels.In order to solve these problems,a semi-supervised semantic segmentation network is proposed to apply spectral normalization to generative adversarial networks and coordinate attention mechanisms.The spectral normalization is used to make the discriminator of the adversarial network satisfy the Lipsitz continuity,so as to improve the stability of the training process and avoid the problem of gradient disappearance.In addition,the coordinate attention mechanism is integrated into the segmentation network,so as to enable the network to obtain the dependence between distant pixels and enlarge the receptive field.Compared to the benchmark model,when using the 1/50,1/20,and 1/8 labeled datasets in the PASCAL VOC 2012 enhanced dataset,the proposed method im-proves MIoU by 2.2%,1.4%,and 1.8%,respectively.When the 1/8,1/4,and 1/2 labeled datasets in Cityscapes,the proposed method improves MIoU by 1.9%,2.1%,and 1.3%,respectively.The experi-mental results demonstrate that,in comparison with other semi-supervised semantic segmentation networks based on adversarial learning,the proposed algorithm exhibits superior stability and accuracy in semi-supervised semantic segmentation tasks.关键词
语义分割/半监督学习/生成对抗网络/谱归一化/注意力机制Key words
Semantic segmentation/Semi-supervised learning/Generative adversarial network/Spectrum normalization/Attention mechanism分类
信息技术与安全科学引用本文复制引用
王小成,胡亚琦,王一中..基于改进生成对抗网络的半监督语义分割[J].四川大学学报（自然科学版）,2024,61(5):99-107,9.基金项目
国家自然科学基金(62362047) （62362047）
