摘要
随着图像大数据的爆发,特别是用户贡献数据的飞速增长,图像样本的语义内容越来越丰富,标签信息也随之越来越复杂.因此图像多标签学习的研究是近年来学术圈和产业界的研究热点之一,涌现了大量表现优异的方法和技术.基于此,本文将对近年来图像多标签学习上的研究成果进行总结.首先,对多标签学习进行简单介绍,并详述其主流方法的分类;随后,针对目前大数据时代的数据特性,总结了多标签学习面临的新的技术难点及其对应的解决方案;最后,在应用层面上介绍了多标签学习在医学、计算机科学等领域的应用实例.
With the fast growing number of images,especially the user-generated ones,the semantic content of images become richer,and labels become more complex.Therefore,the study on image multi-label learning is one of the hot research areas in both academia and industry,and a large number of efficient methods have emerged in recent years.This paper surveys the existing work on image multi-label learning in recent years.Firstly,we briefly describe the concept of multi-label learning and introduce two types of methods,that is,single-instance multi-label learning and multi-instance multi-label learning.Then,we summarize three challenges on multi-label learning caused by the big data characteristics,and provide related work which can handle these challenges.Finally,we elaborate two applications on image recognition and automatic drive to show that multi-label learning techniques can be effective for many application scenarios.
作者
袁梦奇
鲍秉坤
YUAN Mengqi;BAO Bingkun(School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003)
出处
《南京信息工程大学学报（自然科学版）》
CAS
2019年第6期682-689,共8页
Journal of Nanjing University of Information Science & Technology（Natural Science Edition）
基金
国家自然科学基金(61572503,61872424,6193000388)
南京邮电大学高层次人才启动基金(NY218001)
模式识别国家重点实验室开放课题(201900015)
关键词
多标签学习
图像标注
深度学习
大数据
multi-label learning
image annotation
deep learning
big data
