基于知识的零样本视觉识别综述
作者:
作者单位:

作者简介:

冯耀功(1992-),男,博士生,CCF学生会员,主要研究领域为深度学习,计算机视觉,零样本学习.
于剑(1969-),男,博士,教授,博士生导师,CCF会士,主要研究领域为人工智能,机器学习.
桑基韬(1985-),男,博士,教授,博士生导师,CCF高级会员,主要研究领域为多媒体计算,网络数据挖掘,可信赖机器学习.
杨朋波(1993-),男,博士生,CCF学生会员,主要研究领域为深度学习,计算机视觉,对抗鲁棒性.

通讯作者:

于剑,E-mail:jianyu@bjtu.edu.cn

基金项目:

国家重点研发计划(2017YFC1703506);国家自然科学基金(61632004,61832002,61672518);中央高校基本科研业务费专项资金(2020YJS030,2018JBZ006,2019JBZ110)


Survey on Knowledge-based Zero-shot Visual Recognition
Author:
Affiliation:

Fund Project:

National Key Research and Development Program of China (2017YFC1703506); National Natural Science Foundation of China (61632004, 61832002, 61672518); Fundamental Research Funds for the Central Universities (2020YJS030, 2018JBZ006, 2019JBZ110)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    零样本学习旨在通过运用已学到的已知类知识去认知未知类.近年来,“数据+知识驱动”已经成为当下的新潮流,而在计算机视觉领域内的零样本任务中,“知识”本身却缺乏统一明确的定义.针对这种情况,尝试从知识的角度出发,梳理了本领域内“知识”这一概念所覆盖的范畴,共划分为初级知识、抽象知识以及外部知识.基于前面对知识的定义和划分,梳理了当前的零样本学习(主要是图像分类任务的模型)工作,分为基于初级知识的零样本模型、基于抽象知识的零样本模型以及引入外部知识的零样本模型.还对领域内存在的域偏移和枢纽点问题进行了阐述,并基于问题对现有工作进行了总结归纳.最后总结了目前常用的图像分类任务的数据集和知识库、图像分类实验评估标准以及代表性的模型实验结果,并对未来的工作进行了展望.

    Abstract:

    Zero-shot learning aims to recognize the unseen classes by using the knowledge of the seen classes that has been learned. In recent years, ‘knowledge+data driven’ has become a new trend but lacking of unified definition of ‘knowledge’ in the current zero-shot tasks of computer vision. This study tries to define the ‘knowledge’ in this field and divided it into three categories, which are primary knowledge, abstract knowledge, and external knowledge. In addition, based on the definition and classification of knowledge, the current works on zero-shot learning (mainly in image classification task) are sorted out, they are divided into zero-shot models based on primary knowledge, zero-shot models based on abstract knowledge, and zero-shot models based on external knowledge. This study also introduces the problems which are domain shift and hubness in this field, and further summarizes existing works based on the problems. Finally, the paper summarizes the datasets and knowledge bases that commonly used in image classification tasks, the evaluation criteria of image classification experiment and the experimental results of representative models. The future works are also summarized and prospected.

    参考文献
    相似文献
    引证文献
引用本文

冯耀功,于剑,桑基韬,杨朋波.基于知识的零样本视觉识别综述.软件学报,2021,32(2):370-405

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2020-07-03
  • 最后修改日期:2020-08-11
  • 录用日期:
  • 在线发布日期: 2020-10-12
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号