摘要
对尽量少的样本进行人工标注并获得较好的分类性能是图像分类应用的一个关键问题。针对标注样本选择,提出了一种综合样本不确定性度量和代表性度量的主动学习样本选择准则。基于最优标号和次优标号(Best vs.second-best,BvSB)的主动学习方法构建不确定性度量,利用分层聚类(Hierarchical Clustering,HC)方法得到数据集的分层聚类树,然后依据聚类树结构和已标注样本在其中的分布信息定义每个未标注样本的代表性度量。将新方法与随机样本选择以及BvSB主动学习方法进行了比较,对1个光学图像集和1个全极化SAR数据集分类问题的实验结果显示,新方法性能稳定,优于其他两种方法。
Using the least manually labeled samples to train a good classifier is a key problem in image classification. Ai- ming at selecting these samples for labeling, this paper proposed a criterion combining two different measures of sam- pies. uncertainty of classification and representativeness. The best vs. second-best (BvSB) method is used to get the measure of uncertainty. The dataset is first hierarchically clustered and then the measure of representativeness of each unlabeled sample is defined based on the structural information of clusters and the distribution information of those la- beled samples. The proposed method was compared with the random-selection method and BvSB method on an optical image dataset and a fully-polarimetric synthetic aperture radar (SAR) image dataset. The results show that it has stably better performance.
出处
《计算机科学》
CSCD
北大核心
2013年第8期309-312,共4页
Computer Science
基金
国家自然科学基金(41161065
40901207)资助
关键词
主动学习
分层聚类
图像分类
Active learning
Hierarchical clustering
Image classification