Image sequence recognition with active learning using uncertainty sampling
Image sequence recognition with active learning using uncertainty sampling
复制标题
DOI：
10.1109/ijcnn.2013.6707060
复制
发表时间：
2013-08
期刊：
影响因子：
--
通讯作者：
Masatoshi Minakawa;B. Raytchev;Toru Tamaki;K. Kaneda
中科院分区：
文献类型：
--
作者：
Masatoshi Minakawa;B. Raytchev;Toru Tamaki;K. Kaneda
在本文中，我们考虑的情况下，庞大的数据集需要有效地标记为学习。假设数据可以自然地组织成许多称为chunklet的小组，其中每个小组都包含来自同一类的数据，并且每个类都有许多可用的chunklet。每个小块显示一些典型的变化代表类。我们研究了基于不确定性采样的主动学习方法在这种情况下的表现，以及与随机采样相比是否可以预期任何增益。我们还提出了一种新的策略来选择哪些小块被选择用于标记。7个包含姿态、表情和光照条件变化的实验验证了所提出的方法。
In this paper we consider the case when huge datasets need to be labeled efficiently for learning. It is assumed that the data can be naturally organized into many small groups, called chunklets, each one of which contains data from the same class, and many chunklets are available from each class. Each chunklet exhibits some of the typical variation representative for the class. We investigate how active learning methods based on uncertainty sampling perform in this setting, and whether any gains can be expected in comparison with random sampling. We also propose a novel strategy for selecting which chunklets to be selected for labeling. Experiments with 7containing variation in pose, expression and illumination conditions illustrate the proposed method.