计算机工程与应用2026，Vol.62Issue(1)：20-28,9.DOI:10.3778/j.issn.1002-8331.2504-0200
基于深度学习的二分图像分割综述
Survey of Dichotomous Image Segmentation Based on Deep Learning
摘要
Abstract
Dichotomous image segmentation is a crucial task in the field of computer vision,aiming to accurately seg-ment target objects from natural images to provide foundational support for visual analysis and scene understanding.In recent years,deep learning-based dichotomous segmentation has advanced significantly with many algorithms.However,there remains a lack of comprehensive surveys that systematically analyze and summarize these deep learning-driven approaches.Firstly,a thorough review of existing deep learning-based dichotomous segmentation methods is elaborated and they are classified into three categories:based on global-local information,auxiliary information,and diffusion models.Subsequently,benchmark datasets and evaluation metrics in the field are elaborated,and systematic quantitative and quali-tative experimental comparisons are conducted on the above three types of representative algorithms based on these met-rics.Finally,the challenges in dichotomous image segmentation are summarized and an outlook on its future development directions is provided.关键词
二分图像分割/高精度/深度学习/全局-局部信息/扩散模型Key words
dichotomous image segmentation/high precision/deep learning/global-local information/diffusion model分类
信息技术与安全科学引用本文复制引用
杨茜,王安志,吴锦涛,任春洪..基于深度学习的二分图像分割综述[J].计算机工程与应用,2026,62(1):20-28,9.基金项目
国家自然科学基金地区科学基金(62162013) （62162013）
贵州省基础研究计划(自然科学)基金(黔科合基础MS[2025]249) （自然科学）
贵州师范大学学术新苗基金(黔师新苗[2022]30号). （黔师新苗[2022]30号）
