• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>ACM Computing Surveys >Multi-Label Active Learning Algorithms for Image Classification: Overview and Future Promise
【24h】

Multi-Label Active Learning Algorithms for Image Classification: Overview and Future Promise

机译：用于图像分类的多标签主动学习算法：概述和未来承诺

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Image classification is a key task in image understanding, and multi-label image classification has become a popular topic in recent years. However, the success of multi-label image classification is closely related to the way of constructing a training set. As active learning aims to construct an effective training set through iteratively selecting the most informative examples to query labels from annotators, it was introduced into multi-label image classification. Accordingly, multi-label active learning is becoming an important research direction. In this work, we first review existing multi-label active learning algorithms for image classification. These algorithms can be categorized into two top groups from two aspects respectively: sampling and annotation. The most important component of multi-label active learning is to design an effective sampling strategy that actively selects the examples with the highest informativeness from an unlabeled data pool, according to various information measures. Thus, different informativeness measures are emphasized in this survey. Furthermore, this work also makes a deep investigation on existing challenging issues and future promises in multi-label active learning with a focus on four core aspects: example dimension, label dimension, annotation, and application extension.
机译：图像分类是图像理解中的关键任务，近年来，多标签图像分类已成为一个流行的主题。然而，多标签图像分类的成功与构建训练集的方式密切相关。由于主动学习旨在通过迭代地选择要查询注释器查询标签的最具信息性示例来构建有效的培训，它被引入了多标签图像分类。因此，多标签主动学习正在成为一个重要的研究方向。在这项工作中，我们首先审查现有的多标签活动学习算法进行图像分类。这些算法分别可以分别从两个方面分成两个顶部组：采样和注释。根据各种信息测量，多标签主动学习的最重要组成部分是设计有效的采样策略，该策略是通过各种信息措施主动选择具有从未标记数据池中的最高信息的示例。因此，本调查中强调了不同的信息措施。此外，这项工作还对多标签主动学习中存在的挑战性问题和未来承诺进行了深入调查，重点关注四个核心方面：示例维度，标签维度，注释和应用程序扩展。

著录项

  • 来源
    《ACM Computing Surveys》 |2021年第2期|28.1-28.35|共35页
  • 作者

    Wu Jian; Sheng Victor S.; Zhang Jing; Li Hua; Dadakova Tetiana; Swisher Christine Leon; Cui Zhiming; Zhao Pengpeng;

  • 作者单位

    Soochow Univ Inst Artificial Intelligence Sch Comp Sci & Technol Suzhou 215006 Jiangsu Peoples R China|Human Longev Inc San Diego CA 92121 USA;

    Texas Tech Univ Dept Comp Sci Lubbock TX 79409 USA;

    Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China;

    Washington Univ Dept Radiat Oncol St Louis MO 63110 USA;

    Human Longev Inc San Diego CA 92121 USA;

    Human Longev Inc San Diego CA 92121 USA;

    Suzhou Univ Sci & Technol Sch Elect & Informat Engn Suzhou 215009 Jiangsu Peoples R China;

    Soochow Univ Inst Artificial Intelligence Sch Comp Sci & Technol Suzhou 215006 Jiangsu Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Image classification; multi-label image; active learning; sampling strategy; annotation;

    机译：图像分类;多标签图像;活动学习;采样策略;注释;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号