中南民族大学学报（自然科学版）2024，Vol.43Issue(4)：513-521,9.DOI:10.20056/j.cnki.ZNMDZK.20240411
基于前景-背景特征交互的小样本语义分割
Few-shot semantic segmentation based on foreground-background feature interaction
摘要
Abstract
Establishing the relationship between the feature information of the target objects in the support image and the query image is the mainstream approach of existing few-shot semantic segmentation methods.However,most of these methods do not mine background information to assist the prediction of foreground target information.Therefore,a few-shot segmentation network that interacts with foreground and background features is proposed.Specifically,a new branch is added to the traditional two-branch few-shot segmentation network based on target information to explicitly predict the background region of the query image,and then the predicted background region is used to correct the predicted foreground target region.Meanwhile,in the K-shot scenario,the support bias is alleviated by adaptively adjusting the contribution proportion of a single support image in the support prototype.Finally,experiments are conducted on standard few-shot segmentation datasets.The results on the 1-shot setting of the PASCAL-5i dataset showed that the proposed method achieved 0.4%and 2.8%improvement in mIoU compared to NTRENet and MMNet,respectively.关键词
小样本学习/语义分割/非目标区域预测Key words
few-shot learning/semantic segmentation/no target region prediction分类
信息技术与安全科学引用本文复制引用
陆志明,陈少波..基于前景-背景特征交互的小样本语义分割[J].中南民族大学学报（自然科学版）,2024,43(4):513-521,9.基金项目
中央高校基本科研业务费专项资金资助项目(CZY22012) （CZY22012）
