Multi-Label Active Learning Algorithms for Image Classification
Multi-Label Active Learning Algorithms for Image Classification
复制标题
用于图像分类的多标签主动学习算法
DOI：
10.1145/3379504
复制
发表时间：
2020-03
影响因子：
16.6
通讯作者：
Pengpeng Zhao
中科院分区：
文献类型：
--
作者：
Jian Wu;Victor S. Sheng;Jing Zhang（张静）;Hua Li;Tetiana Dadakova;Christine Leon Swisher;Zhiming Cui;Pengpeng Zhao
图像分类是图像理解中的一个关键问题，多标签图像分类是近年来的研究热点。然而，多标签图像分类的成功与否与训练集的构造方式密切相关。由于主动学习的目的是通过迭代地选择信息量最大的样本来构造有效的训练集，从而从标注器中查询标签，因此将其引入多标签图像分类。因此，多标签主动学习成为一个重要的研究方向。在这项工作中，我们首先回顾现有的多标签主动学习算法的图像分类。这些算法可以分为两大类，分别从两个方面：采样和注释。多标签主动学习最重要的组成部分是设计一个有效的抽样策略，根据各种信息措施，从未标记的数据池中主动选择具有最高信息含量的示例。因此，在这次调查中强调了不同的信息性措施。此外，本文还对多标签主动学习中存在的挑战性问题和未来的发展前景进行了深入研究，重点关注四个核心方面：示例维度，标签维度，注释和应用扩展。
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.
登录
查看更多内容
DOI：
10.1145/3123266.3123388
发表时间：
2017-10
期刊：
Proceedings of the 25th ACM international conference on Multimedia
影响因子：
--
作者：
Jian Wu;Anqian Guo;Victor S. Sheng;Pengpeng Zhao;Zhiming Cui;Hua Li
通讯作者：
Jian Wu;Anqian Guo;Victor S. Sheng;Pengpeng Zhao;Zhiming Cui;Hua Li
DOI：
--
发表时间：
2016
期刊：
J. Mach. Learn. Res.
影响因子：
--
作者：
O. R. Pupo;Eduardo Pérez;María del Carmen Rodríguez-Hernández;H. Fardoun;S. Ventura
通讯作者：
O. R. Pupo;Eduardo Pérez;María del Carmen Rodríguez-Hernández;H. Fardoun;S. Ventura
影响因子：
5.7
作者：
Entis, Jonathan J.;Doerga, Priya;Barrett, Lisa Feldman;Dickerson, Bradford C.
通讯作者：
Dickerson, Bradford C.
DOI：
10.1137/1.9781611972788.37
发表时间：
2008
期刊：
--
影响因子：
--
作者：
Gang Chen;Yangqiu Song;Fei Wang;Changshui Zhang
通讯作者：
Gang Chen;Yangqiu Song;Fei Wang;Changshui Zhang
DOI：
10.1109/isbi.2018.8363578
发表时间：
2018-04
期刊：
2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
影响因子：
--
作者：
Jian Wu;S. Ruan;C. Lian;S. Mutic;M. Anastasio;Hua Li
通讯作者：
Jian Wu;S. Ruan;C. Lian;S. Mutic;M. Anastasio;Hua Li