A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification
A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification
复制标题
DOI：
10.1109/jstsp.2011.2139193
复制
发表时间：
2011-06-01
影响因子：
7.5
通讯作者：
Munoz-Mari, Jordi
中科院分区：
文献类型：
--
作者：
Tuia, Devis;Volpi, Michele;Munoz-Mari, Jordi
定义有效的训练集是遥感图像分类例程成功的最微妙的阶段之一。问题的复杂性，有限的时间和财政资源，以及较高的类内方差，如果使用次优数据集进行训练，可能会使算法失败。主动学习的目的是通过采样迭代地提高模型的性能，从而建立有效的训练集。用户定义的试探法根据其类别成员资格的不确定性的函数对未标记的像素进行排序，然后要求用户为最不确定的像素提供标签。本文回顾和测试了几种主要的主动学习算法：委员会学习算法、大范围学习算法和后验概率学习算法。对于其中的每一个，讨论了遥感领域的最新进展，并详细介绍了一些启发式方法并进行了测试。考虑了几种具有挑战性的遥感场景，包括非常高的空间分辨率和高光谱图像分类。最后，为新用户和/或没有经验的用户提供了选择好的体系结构的指导原则。
Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.