集间两级语义互补的小样本语义分割
Few-shot semantic segmentation based on inter-set semantic complementarity of two levels
投稿时间:2022-03-12  修订日期:2022-03-12
DOI:
中文关键词: 小样本语义分割  原型学习  集间两级语义特征  多尺度  
英文关键词: few-shot semantic segmentation  prototype learning  inter-set semantic features of two levels  multi-scale
基金项目:中央高校基本科研业务费专项资金资助项目(CZY18002)
作者单位
陈少波 中南民族大学 电子与信息工程学院 
文婧 中南民族大学 电子与信息工程学院 
摘要点击次数: 218
全文下载次数: 0
中文摘要:
      现有的小样本语义分割模型通常只提取单一级别的语义特征,然而由于小样本数据的样本量少、各级语义特征具有不同属性等原因,提取单一级别语义特征的网络模型很难在保证分割能力的同时兼具泛化性。针对该问题,提出了一种集间两级语义互补的小样本语义分割方法。该方法使用具有强类别特征的支持集高级语义特征对具备泛化性的查询集中级语义特征加权,在增强查询集各目标类别的特征的同时保留查询集中级语义特征的泛化能力;另外,该模型通过对支持集中级语义特征优化、为查询集构建非参数学习的先验信息等方式增强两集信息之间的交互性以获得更丰富的判别信息。该方法在PASCAL-5i数据集上的进行仿真实验,mIoU值在1-shot和5-shot的设置上分别能达到45.3%和48.8%,其结果超越部分先进主流的小样本语义分割算法,且网络模型的参数量也控制在可以接受的范围之内。
英文摘要:
      Existing few-shot semantic segmentation model are usually only to extract single level semantic feature, but due to the small sample data of less sample size and different attributes of semantic features at each level, it is difficult for the network model to extract semantic features at a single level to ensure the segmentation ability and generalization. To solve this problem, a few-shot semantic segmentation based on inter-set semantic complementarity of two levels is proposed. In this method, the high-level semantic features of the support set with strong category are used to weight the generalization middle-level semantic features of the query set, and the generalization capability of the query set semantic features is preserved while the features of the query set target categories are enhanced. In addition, the model enhances the interaction between the two sets of information by optimizing support middle-level semantic feature and constructing non-parametric learning prior information for the query set, so as to obtain richer discriminant information. Experimental results based on PASCAL- data set show that the proposed method is effective in solving the problem of few-shot semantic segmentation. The mIoU value of the network can reach 44.6% and 48.8% in 1-shot and 5-shot settings, respectively, and its results surpass some state-of-the-art method. and the number of parameters in the network model is controlled within the acceptable range.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭